๐Ÿ“š Zotero Library

My reading list โ€” synced from Zotero

317 papers
Qwen3 Technical Report
Yang, Li, Yang et al. ยท 2025-05-14 ยท preprint
Computer Science - Computation and Language
Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
Dao, Gu ยท 2024-05-31 ยท preprint
Computer Science - Machine Learning
Attention Is All You Need
Vaswani, Shazeer, Parmar et al. ยท 2023-08-02 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Rethinking Attention with Performers
Choromanski, Likhosherstov, Dohan et al. ยท 2022-11-19 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine LearningStatistics - Machine Learning
On the Relationship between Self-Attention and Convolutional Layers
Cordonnier, Loukas, Jaggi ยท 2020-01-10 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningStatistics - Machine Learning
Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel
Tsai, Bai, Yamada et al. ยท 2019-11-11 ยท preprint
Computer Science - Machine LearningStatistics - Machine Learning
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Katharopoulos, Vyas, Pappas et al. ยท 2020-08-31 ยท preprint
Computer Science - Machine LearningStatistics - Machine Learning
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Chen, Xue, Li et al. ยท 2024-12-13 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Yang, Wang, Zhang et al. ยท 2025-12-04 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Scaling RL to Long Videos
Chen, Huang, Shi et al. ยท 2025-09-30 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
LongCat-Flash-Omni Technical Report
Team, Wang, Bayan et al. ยท 2025-11-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Distributed, Parallel, and Cluster ComputingComputer Science - Machine LearningComputer Science - MultimediaComputer Science - Sound
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Qiu, Wang, Zheng et al. ยท 2025-05-10 ยท preprint
Computer Science - Computation and Language
Gated Delta Networks: Improving Mamba2 with Delta Rule
Yang, Kautz, Hatamizadeh ยท 2025-03-06 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
The Platonic Representation Hypothesis
Huh, Cheung, Wang et al. ยท 2024-07-25 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningComputer Science - Neural and Evolutionary Computing
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Tang, An, Yan et al. ยท 2026-02-09 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Kimi K2.5: Visual Agentic Intelligence
Team, Bai, Bai et al. ยท 2026-02-02 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Clark, Zhang, Ma et al. ยท journalArticle
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Ge, Chan, Wang et al. ยท 2025-05-08 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
MambaMia: A State-Space-Model-Based Compression for Efficient Video Understanding in Large Multimodal Models
Kim, Seo ยท 2025-06-16 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Hyun, Hwang, Han et al. ยท 2025-07-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
MambaMia: A State-Space-Model-Based Compression for Efficient Video Understanding in Large Multimodal Models
Kim, Seo ยท 2025-06-16 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
Di, Yu, Zhang et al. ยท 2025-03-01 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Multi-Agent Collaboration via Evolving Orchestration
Dang, Qian, Luo et al. ยท 2025-10-21 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Multiagent Systems
Kimi K2: Open Agentic Intelligence
Team, Bai, Bao et al. ยท 2025-07-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO
Cheng, Hou, Tao et al. ยท 2025-11-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding
Li, Yin, Tan et al. ยท 2025-11-17 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Qiu, Wang, Zheng et al. ยท 2025-05-10 ยท preprint
Computer Science - Computation and Language
Qwen3-VL Technical Report
Bai, Cai, Chen et al. ยท 2025-11-26 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Round and Round We Go! What makes Rotary Positional Encodings useful?
Barbero, Vitvitskyi, Perivolaropoulos et al. ยท 2025-05-13 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs
Kim, Kim, Han ยท 2025-10-15 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Wei, Liu, Zang et al. ยท 2025-05-30 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
Li, Qin, Ou et al. ยท 2025-10-08 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Rotary Position Embedding for Vision Transformer
Heo, Park, Han et al. ยท 2024-07-16 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
SAM 3D: 3Dfy Anything in Images
Team, Chen, Chu et al. ยท 2025-11-20 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
VIDEOP2R: Video Understanding from Perception to Reasoning
Jiang, Wang, Zhao et al. ยท 2025-11-14 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
NVIDIA Nemotron Nano V2 VL
NVIDIA, Deshmukh, Chumachenko et al. ยท 2025-11-07 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
Ren, Yao, Li et al. ยท 2024-03-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
Li, Di, Zhai et al. ยท 2025-06-24 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MiMo-VL Technical Report
Team, Yue, Lin et al. ยท 2025-06-04 ยท preprint
Computer Science - Computation and Language
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Team, Hong, Yu et al. ยท 2025-08-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Pegasus-v1 Technical Report
Jung, Go, Yi et al. ยท 2024-04-23 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
Qwen2.5-VL Technical Report
Bai, Chen, Liu et al. ยท 2025-02-19 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Scaling Latent Reasoning via Looped Language Models
Zhu, Wang, Hua et al. ยท 2025-11-03 ยท preprint
Computer Science - Computation and Language
Cambrian-S: Towards Spatial Supersensing in Video
Yang, Yang, Huang et al. ยท 2025-11-06 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
EVA-CLIP: Improved Training Techniques for CLIP at Scale
Sun, Fang, Wu et al. ยท 2023-03-27 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Perception Encoder: The best visual embeddings are not at the output of the network
Bolya, Huang, Sun et al. ยท 2025-04-28 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
Cho, Madotto, Mavroudi et al. ยท 2025-07-23 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Seed1.5-VL Technical Report
Guo, Wu, Zhu et al. ยท 2025-05-11 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Comanici, Bieber, Schaekermann et al. ยท 2025-10-16 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Zhang, Zhang, Li et al. ยท 2025-05-13 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Video models are zero-shot learners and reasoners
Wiedemer, Li, Vicol et al. ยท 2025-09-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningComputer Science - Robotics
The Art of Scaling Reinforcement Learning Compute for LLMs
Khatri, Madaan, Tiwari et al. ยท 2025-10-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
Qwen3-Omni Technical Report
Xu, Guo, Hu et al. ยท 2025-09-22 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionElectrical Engineering and Systems Science - Audio and Speech Processing
Perception Encoder: The best visual embeddings are not at the output of the network
Bolya, Huang, Sun et al. ยท 2025-04-28 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning
Su, Pan, Lv et al. ยท 2025-10-04 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Huang, Xu, Wang et al. ยท 2025-10-03 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Quantile Advantage Estimation for Entropy-Safe Reasoning
Wu, Huang, Wu et al. ยท 2025-09-26 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
Yuan, Chen, Zhang et al. ยท 2025-10-13 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
Tan, Geng, Zhang et al. ยท 2025-09-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
Learning to Reason as Action Abstractions with Scalable Mid-Training RL
Zhang, Yu, Feng et al. ยท 2025-10-11 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine LearningStatistics - Machine Learning
NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
Tian, Li, Luo et al. ยท 2025-10-09 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Better & Faster Large Language Models via Multi-token Prediction
Gloeckle, Idrissi, Roziรจre et al. ยท 2024-04-30 ยท preprint
Computer Science - Computation and Language
Scalable Diffusion Models with Transformers
Peebles, Xie ยท 2023-03-02 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Flow Matching for Generative Modeling
Lipman, Chen, Ben-Hamu et al. ยท 2023-02-08 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine LearningStatistics - Machine Learning
Qwen2.5-Omni Technical Report
Xu, Guo, He et al. ยท 2025-03-26 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - SoundElectrical Engineering and Systems Science - Audio and Speech Processing
Emerging Properties in Unified Multimodal Pretraining
Deng, Zhu, Li et al. ยท 2025-07-27 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Assran, Bardes, Fan et al. ยท 2025-06-11 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningComputer Science - Robotics
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
Lee, Kim, Baek et al. ยท 2024-08-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Tong, Brown, Wu et al. ยท 2024-12-04 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Shen, Xiong, Zhao et al. ยท 2024-10-22 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
Hyun, Hwang, Han et al. ยท 2025-07-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
GR-3 Technical Report
Cheang, Chen, Cui et al. ยท 2025-07-22 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Robotics
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Ren, Wei, Guo et al. ยท 2025-03-05 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Ma, Zheng, Shi et al. ยท 2025-08-07 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Distributed, Parallel, and Cluster Computing
Emerging Properties in Unified Multimodal Pretraining
Deng, Zhu, Li et al. ยท 2025-07-27 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Zhou, Yu, Babu et al. ยท 2024-08-20 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
$ฯ€_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
Intelligence, Black, Brown et al. ยท 2025-04-22 ยท preprint
Computer Science - Machine LearningComputer Science - Robotics
Real-Time Execution of Action Chunking Flow Policies
Black, Galliker, Levine ยท 2025-06-09 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine LearningComputer Science - Robotics
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
Zhao, Kumar, Levine et al. ยท 2023-04-23 ยท preprint
Computer Science - Machine LearningComputer Science - Robotics
$ฯ€_0$: A Vision-Language-Action Flow Model for General Robot Control
Black, Brown, Driess et al. ยท 2024-11-13 ยท preprint
Computer Science - Machine LearningComputer Science - Robotics
Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning
Jung, Hong, Yoon et al. ยท 2025/06/18 ยท conferencePaper
Gemini Robotics: Bringing AI into the Physical World
Team, Abeyruwan, Ainslie et al. ยท 2025-03-25 ยท preprint
Computer Science - Robotics
DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Yu, Zhang, Zhu et al. ยท 2025-05-20 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Group Sequence Policy Optimization
Zheng, Liu, Li et al. ยท 2025-07-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
Geng, Wang, Ma et al. ยท 2025-07-29 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Emerging Properties in Unified Multimodal Pretraining
Deng, Zhu, Li et al. ยท 2025-05-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
Luo, Ji, Zhong et al. ยท 2021-05-08 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
Wang, Wu, Zhang et al. ยท 2025-03-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
Wang, Zhang, Zohar et al. ยท 2024-03-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Information Retrieval
E5-V: Universal Embeddings with Multimodal Large Language Models
Jiang, Song, Zhang et al. ยท 2024-07-17 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Information Retrieval
VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
Jiang, Meng, Yang et al. ยท 2025-01-02 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Meng, Jiang, Liu et al. ยท 2025-07-07 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Mastering Diverse Domains through World Models
Hafner, Pasukonis, Ba et al. ยท 2024-04-17 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine LearningStatistics - Machine Learning
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
Tong, Brown, Wu et al. ยท 2024-12-04 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Shen, Xiong, Zhao et al. ยท 2024-10-22 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Learning to Model the World with Language
Lin, Du, Watkins et al. ยท 2024-05-31 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Generalizing Verifiable Instruction Following
Pyatkin, Malik, Graf et al. ยท 2025-07-03 ยท preprint
Computer Science - Computation and Language
Skywork-R1V3 Technical Report
Shen, Pei, Peng et al. ยท 2025-07-10 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
BlueLM-2.5-3B Technical Report
Xiong, Chen, Wang et al. ยท 2025-07-08 ยท preprint
Computer Science - Artificial Intelligence
Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning
Huan, Li, Zheng et al. ยท 2025-07-01 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Reinforcing General Reasoning without Verifiers
Zhou, Liu, Sims et al. ยท 2025-05-27 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Wang, Wei, Peng et al. ยท 2025-06-06 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MiMo-VL Technical Report
Team, Yue, Lin et al. ยท 2025-06-04 ยท preprint
Computer Science - Computation and Language
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Peng, Wang, Wang et al. ยท 2025-06-09 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Kimi-VL Technical Report
Team, Du, Yin et al. ยท 2025-06-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
Xie, Gao, Ren et al. ยท 2025-02-20 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
Dong, Lu, Li et al. ยท 2024-07-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles
Toh, Chia, Ghosal et al. ยท 2025-05-21 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
RLPR: Extrapolating RLVR to General Domains without Verifiers
Yu, Ji, Wang et al. ยท 2025-06-23 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
Cui, Zhang, Chen et al. ยท 2025-05-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Qwen3 Technical Report
Yang, Li, Yang et al. ยท 2025-05-14 ยท preprint
Computer Science - Computation and Language
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
Chow, Tennenholtz, Gur et al. ยท 2024-12-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
PRESERVING DIVERSITY IN SUPERVISED FINE-TUNING OF LARGE LANGUAGE MODELS
Li, Chen, Xu et al. ยท 2025 ยท journalArticle
Skywork Open Reasoner 1 Technical Report
He, Liu, Liu et al. ยท 2025-05-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Yan, Jiang, Ren et al. ยท 2025-05-25 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Ma, Du, Shen et al. ยท 2025-05-23 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
BLEUBERI: BLEU is a surprisingly effective reward for instruction following
Chang, Kim, Krumdick et al. ยท 2025-05-16 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Emerging Properties in Unified Multimodal Pretraining
Deng, Zhu, Li et al. ยท 2025-05-20 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Image2Struct: Benchmarking Structure Extraction for Vision-Language Models
Roberts, Lee, Wong et al. ยท 2024-10-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Chu, Zhai, Yang et al. ยท 2025-01-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Peng, Chris, Wang et al. ยท 2025-04-08 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
Research, An, Bae et al. ยท 2024-12-09 ยท preprint
Computer Science - Computation and Language
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
Chen, Zhang, Zhu et al. ยท 2025-05-08 ยท preprint
Computer Science - Computation and Language
Seed1.5-VL Technical Report
Guo, Wu, Zhu et al. ยท 2025-05-11 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
Chris, Wei, Peng et al. ยท 2025-04-25 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging
Chen, Zhang, Zhu et al. ยท 2025-05-08 ยท preprint
Computer Science - Computation and Language
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Chu, Zhai, Yang et al. ยท 2025-01-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Extract Free Dense Misalignment from CLIP
Nam, Im, Kim et al. ยท 2025-04 ยท journalArticle
Weight Ensembling Improves Reasoning in Language Models
Dang, Baek, Wen et al. ยท 2025-04-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Chen, Tu, Wang et al. ยท 2025-04-10 ยท preprint
Computer Science - Computation and Language
HybridFlow: A Flexible and Efficient RLHF Framework
Sheng, Zhang, Ye et al. ยท 2025-03-30 ยท conferencePaper
Computer Science - Distributed, Parallel, and Cluster ComputingComputer Science - Machine Learning
SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild
Zeng, Huang, Liu et al. ยท 2025-03-24 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
HybridFlow: A Flexible and Efficient RLHF Framework
Sheng, Zhang, Ye et al. ยท 2025-03-30 ยท conferencePaper
Computer Science - Distributed, Parallel, and Cluster ComputingComputer Science - Machine Learning
FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models
Song, Zheng, Li et al. ยท 2025-03-21 ยท preprint
Computer Science - Computation and Language
TESS 2: A Large-Scale Generalist Diffusion Language Model
Tae, Ivison, Kumar et al. ยท 2025-02-19 ยท preprint
Computer Science - Computation and Language
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
He, Luo, Bai et al. ยท 2024-06-06 ยท preprint
Computer Science - Computation and Language
Exploring open-ended gameplay features with Micro RollerCoaster Tycoon
Green, Yen, Earle et al. ยท 2021-05-10 ยท preprint
Computer Science - Artificial Intelligence
VLMs as GeoGuessr Masters: Exceptional Performance, Hidden Biases, and Privacy Risks
Huang, Huang, Liu et al. ยท 2025-02-16 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
PIGEON: Predicting Image Geolocations
Haas, Skreta, Alberti et al. ยท 2024-05-28 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Yang, He, Pan et al. ยท 2025-03-13 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Quark: Controllable Text Generation with Reinforced Unlearning
Lu, Welleck, Hessel et al. ยท 2022-11-16 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Chen, Wang, Cao et al. ยท 2025-01-13 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale
Guo, Zheng, Bai et al. ยท 2024-12-06 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Tschannen, Gritsenko, Wang et al. ยท 2025-02-20 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models
Wu, Tao, Wang et al. ยท 2024-12-08 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark
Gupta, Verma, Anantheswaran et al. ยท 2024-10-06 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Meng, Du, Liu et al. ยท 2025-03-10 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
Huang, Jia, Zhai et al. ยท 2025-03-09 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Visual-RFT: Visual Reinforcement Fine-Tuning
Liu, Sun, Zang et al. ยท 2025-03-03 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning
Zhuang, Huang, Zhang et al. ยท 2024-09-25 ยท preprint
Computer Science - Computation and Language
Probabilistic Language-Image Pre-Training
Chun, Kim, Park et al. ยท 2024-12-06 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Qwen2.5 Technical Report
Qwen, Yang, Yang et al. ยท 2025-01-03 ยท preprint
Computer Science - Computation and Language
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Li, Cao, Griggs et al. ยท 2025-02-18 ยท preprint
Computer Science - Artificial Intelligence
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Wu, Chen, Pan et al. ยท 2024-12-13 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
DeepSeek-V3 Technical Report
DeepSeek-AI, Liu, Feng et al. ยท 2024-12-27 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
s1: Simple test-time scaling
Muennighoff, Yang, Shi et al. ยท 2025-02-03 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment
Kazemnejad, Aghajohari, Portelance et al. ยท 2024-10-02 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Zhai, Bai, Lin et al. ยท 2024-10-07 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Reinforcement Learning: An Overview
Murphy ยท 2024-12-06 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
Training language models to follow instructions with human feedback
Ouyang, Wu, Jiang et al. ยท 2022-03-04 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
Hou, Lv, Lu et al. ยท 2025-01-20 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Qwen2 Technical Report
Yang, Yang, Hui et al. ยท 2024-09-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Lambert, Morrison, Pyatkin et al. ยท 2024-12-06 ยท preprint
Computer Science - Computation and Language
Free Process Rewards without Process Labels
Yuan, Li, Chen et al. ยท 2024-12-02 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Making Large Language Models Better Reasoners with Step-Aware Verifier
Li, Lin, Zhang et al. ยท 2023-05-24 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Wang, Li, Shao et al. ยท 2024-02-19 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
PRIME: Prioritizing Interpretability in Failure Mode Extraction
Rezaei, Saberi, Moayeri et al. ยท 2024-03-14 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
Song, Su, Qu et al. ยท 2025-01-07 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Guan, Zhang, Liu et al. ยท 2025-01-08 ยท preprint
Computer Science - Computation and Language
Scalable Vision Language Model Training via High Quality Data Curation
Dong, Kang, Yin et al. ยท 2025-01-10 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Zhang, Zheng, Wu et al. ยท 2025-01-13 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
Luo, Shen, Zhu et al. ยท 2024-04-08 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
STaR: Bootstrapping Reasoning With Reasoning
Zelikman, Wu, Mu et al. ยท 2022-05-20 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Let's Verify Step by Step
Lightman, Kosaraju, Burda et al. ยท 2023-05-31 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
OpenAI o1 System Card
OpenAI, Jaech, Kalai et al. ยท 2024-12-21 ยท preprint
Computer Science - Artificial Intelligence
Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models
Puerto, Chubakov, Zhu et al. ยท 2024-07-03 ยท preprint
Computer Science - Computation and Language
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Zeng, Cheng, Yin et al. ยท 2024-12-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Snell, Lee, Xu et al. ยท 2024-08-06 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Zeng, Cheng, Yin et al. ยท 2024-12-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
Critique-out-Loud Reward Models
Ankner, Paul, Cui et al. ยท 2024-08-21 ยท preprint
Computer Science - Machine Learning
Solving math word problems with process- and outcome-based feedback
Uesato, Kushman, Kumar et al. ยท 2022-11-25 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Iterative Reasoning Preference Optimization
Pang, Yuan, Cho et al. ยท 2024-06-26 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Training Verifiers to Solve Math Word Problems
Cobbe, Kosaraju, Bavarian et al. ยท 2021-11-18 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Improve Mathematical Reasoning in Language Models by Automated Process Supervision
Luo, Liu, Liu et al. ยท 2024-06-05 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?
Huang, Zou, Li et al. ยท 2024-11-25 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
O1 Replication Journey: A Strategic Progress Report -- Part 1
Qin, Li, Zou et al. ยท 2024-10-08 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
Xu, Jin, Li et al. ยท 2024-11-25 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
Shoeybi, Patwary, Puri et al. ยท 2020-03-13 ยท preprint
Computer Science - Computation and Language
Reducing Activation Recomputation in Large Transformer Models
Korthikanti, Casper, Lym et al. ยท 2022-05-10 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Improve Mathematical Reasoning in Language Models by Automated Process Supervision
Luo, Liu, Liu et al. ยท 2024-06-05 ยท preprint
Computer Science - Computation and LanguageComputer Science - Machine Learning
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Wang, Chen, Wang et al. ยท 2024-11-15 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
The Llama 3 Herd of Models
Dubey, Jauhri, Pandey et al. ยท 2024-08-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Wang, Bai, Tan et al. ยท 2024-10-03 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Qwen2 Technical Report
Yang, Yang, Hui et al. ยท 2024-09-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Wang, Bai, Tan et al. ยท 2024-10-03 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
LLaVA-OneVision: Easy Visual Task Transfer
Li, Zhang, Guo et al. ยท 2024-10-26 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Rotary Position Embedding for Vision Transformer
Heo, Park, Han et al. ยท 2024-07-16 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function
Rafailov, Hejna, Park et al. ยท 2024-08-12 ยท preprint
Computer Science - Machine Learning
Improve Vision Language Model Chain-of-thought Reasoning
Zhang, Zhang, Li et al. ยท 2024-10-21 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models
Peng, Fu, Gao et al. ยท 2024-08-30 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Lee, Kim, Park et al. ยท 2024-05-27 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
Yue, Ni, Zhang et al. ยท 2024-06-13 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognitioneval
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Lu, Bansal, Xia et al. ยท 2024-01-21 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learningeval
Improved Baselines with Visual Instruction Tuning
Liu, Li, Li et al. ยท 2024-05-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Large Language Models Can Self-Improve
Huang, Gu, Hou et al. ยท 2022-10-25 ยท preprint
Computer Science - Computation and Language
Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
Yue, Zhang, Jin ยท 2024-05-29 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Calibrated Self-Rewarding Vision Language Models
Zhou, Fan, Cheng et al. ยท 2024-05-31 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Phantom of Latent for Large Language and Vision Models
Lee, Chung, Kim et al. ยท 2024-09-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Aligning Large Multimodal Models with Factually Augmented RLHF
Sun, Shen, Cao et al. ยท 2023-09-25 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
Zhou, Cui, Yoon et al. ยท 2024-03-16 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Scaling Laws for Reward Model Overoptimization
Gao, Schulman, Hilton ยท 2022-10-19 ยท preprint
Computer Science - Machine LearningStatistics - Machine Learning
Dense Reward for Free in Reinforcement Learning from Human Feedback
Chan, Sun, Holt et al. ยท 2024-02-01 ยท preprint
Computer Science - Machine Learning
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness
Yu, Zhang, Yao et al. ยท 2024-05-27 ยท preprint
Computer Science - Computation and Language
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
Wang, Wang, Xu et al. ยท 2024-02-23 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs
Ouali, Bulat, Martinez et al. ยท 2024-08-19 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Ivison, Wang, Liu et al. ยท 2024-06-13 ยท preprint
Computer Science - Computation and Language
Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
Peng, Kumar, Zhang et al. ยท 2019-10-07 ยท preprint
Computer Science - Machine LearningStatistics - Machine Learning
Parrot Captions Teach CLIP to Spot Text
Lin, He, Wang et al. ยท 2024-02-01 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Alabdulmohsin, Zhai, Kolesnikov et al. ยท 2024-01-09 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningI.2.10I.2.6
Graph-RISE: Graph-Regularized Image Semantic Embedding
Juan, Lu, Li et al. ยท 2019-02-13 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningStatistics - Machine Learning
PaLI: A Jointly-Scaled Multilingual Language-Image Model
Chen, Wang, Changpinyo et al. ยท 2023-06-05 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
PaLI-3 Vision Language Models: Smaller, Faster, Stronger
Chen, Wang, Beyer et al. ยท 2023-10-17 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
PaliGemma: A versatile 3B VLM for transfer
Beyer, Steiner, Pinto et al. ยท 2024-07-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Sigmoid Loss for Language Image Pre-Training
Zhai, Mustafa, Kolesnikov et al. ยท 2023-09-27 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
Proximal Policy Optimization Algorithms
Schulman, Wolski, Dhariwal et al. ยท 2017-08-28 ยท preprint
Computer Science - Machine Learning
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, Sharma, Mitchell et al. ยท 2024-07-29 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment
Gordon, Bitton, Shafir et al. ยท 2024-07-17 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Yu, Yao, Zhang et al. ยท 2024-03-08 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Detecting and Preventing Hallucinations in Large Vision Language Models
Gunjal, Yin, Bas ยท 2024-02-11 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Fine-Grained Human Feedback Gives Better Rewards for Language Model Training
Wu, Hu, Shi et al. ยท 2023-10-30 ยท preprint
Computer Science - Computation and Language
ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling
Yan, Bai, Chen et al. ยท 2024-04-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
Huang, Sun, Xie et al. ยท journalArticle
Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
Chefer, Gur, Wolf ยท 2021-03-29 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Polos: Multimodal Metric Learning from Human Feedback for Image Captioning
Wada, Kaneda, Saito et al. ยท 2024-02-28 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
Parcalabescu, Cafagna, Muradjan et al. ยท 2022 ยท conferencePaper
68TxxComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionI.2.10I.2.7
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
Liang, Zhang, Kwon et al. ยท 2022-10-19 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningComputer Science - Multimedia
Dealing with Semantic Underspecification in Multimodal NLP
Pezzelle ยท 2023-07 ยท conferencePaper
WizardLM: Empowering Large Language Models to Follow Complex Instructions
Xu, Sun, Zheng et al. ยท 2023-06-10 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
ALLaVA: Harnessing GPT4V-Synthesized Data for Lite Vision-Language Models
Chen, Chen, Zhang et al. ยท 2024-06-17 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
McKinzie, Gan, Fauconnier et al. ยท 2024-04-18 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Li, Zhang, Wang et al. ยท 2024-03-27 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
TextGrad: Automatic "Differentiation" via Text
Yuksekgonul, Bianchi, Boen et al. ยท 2024-06-11 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Pryzant, Iter, Li et al. ยท 2023-10-19 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Hessel, Holtzman, Forbes et al. ยท 2022-03-23 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Rich Human Feedback for Text-to-Image Generation
Liang, He, Li et al. ยท 2024-04-08 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Lee, Kim, Park et al. ยท 2024-05-27 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Evaluating Text-to-Image Synthesis: Survey and Taxonomy of Image Quality Metrics
Hartwig, Engel, Sick et al. ยท 2024-04-15 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Graphics
ALOHa: A New Measure for Hallucination in Captioning Models
Petryk, Chan, Kachinthaya et al. ยท 2024-04-03 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Li, Li, Xiong et al. ยท 2022-02-15 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Chameleon Team ยท 2024-05-16 ยท preprint
Computer Science - Computation and Language
ALOHa: A New Measure for Hallucination in Captioning Models
Petryk, Chan, Kachinthaya et al. ยท 2024-04-03 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
Li, Li, Xiong et al. ยท 2022-02-15 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Udandarao, Prabhu, Ghosh et al. ยท 2024-04-08 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Progress measures for grokking via mechanistic interpretability
Nanda, Chan, Lieberum et al. ยท 2023-10-19 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Machine Learning
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Udandarao, Prabhu, Ghosh et al. ยท 2024-04-04 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Hessel, Holtzman, Forbes et al. ยท 2022-03-23 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
Li, Zhang, Wang et al. ยท 2024-03-27 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
CoLLaVO: Crayon Large Language and Vision mOdel
Lee, Park, Kim et al. ยท 2024-06-02 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MoAI: Mixture of All Intelligence for Large Language and Vision Models
Lee, Park, Kim et al. ยท 2024-07-14 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
TroL: Traversal of Layers for Large Language and Vision Models
Lee, Chung, Kim et al. ยท 2024-06-19 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Assessing Generative Models via Precision and Recall
Sajjadi, Bachem, Lucic et al. ยท 2018-10-28 ยท preprint
Computer Science - Machine LearningStatistics - Machine Learning
gScoreCAM: What Objects Is CLIP Looking At?
Chen, Li, Biaz et al. ยท 2023 ยท bookSection
Exploring CLIP for Assessing the Look and Feel of Images
Wang, Chan, Loy ยท 2022-11-23 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention
Guo, Zhang, Qiu et al. ยท 2022-12-18 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
Parcalabescu, Frank ยท 2023 ยท conferencePaper
68TxxComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionI.2.10I.2.7
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
Mindermann, Brauner, Razzak et al. ยท 2022-09-26 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Gafni, Polyak, Ashual et al. ยท 2022-03-24 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - GraphicsComputer Science - Machine Learning
Transformer Interpretability Beyond Attention Visualization
Chefer, Gur, Wolf ยท 2021-04-05 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality
Hsieh, Zhang, Ma et al. ยท 2023-06-26 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
CIDEr: Consensus-based Image Description Evaluation
Vedantam, Zitnick, Parikh ยท 2015-06-02 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Information Retrieval
CapsFusion: Rethinking Image-Text Data at Scale
Yu, Sun, Zhang et al. ยท 2024-04-05 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
FOIL it! Find One mismatch between Image and Language caption
Shekhar, Pezzelle, Klimovich et al. ยท 2017 ยท conferencePaper
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment
Liu, Yan, Abbeel ยท 2023-02-03 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Probing Image-Language Transformers for Verb Understanding
Hendricks, Nematzadeh ยท 2021-06-16 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Evaluating Object Hallucination in Large Vision-Language Models
Li, Du, Zhou et al. ยท 2023-10-25 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
Object Hallucination in Image Captioning
Rohrbach, Hendricks, Burns et al. ยท 2018 ยท conferencePaper
Vision Transformers Need Registers
Darcet, Oquab, Mairal et al. ยท 2024-04-12 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Semantic Pyramid for Image Generation
Shocher, Gandelsman, Mosseri et al. ยท 6/2020 ยท conferencePaper
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
Bousselham, Boggust, Chaybouti et al. ยท 2024-04-04 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
MoDE: CLIP Data Experts via Clustering
Ma, Huang, Xie et al. ยท 2024-04-24 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Question Aware Vision Transformer for Multimodal Reasoning
Ganz, Kittenplon, Aberdam et al. ยท 2024-02-08 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Adventures of Trustworthy Vision-Language Models: A Survey
Vatsa, Jain, Singh ยท 2024-03-24 ยท journalArticle
Robustness
Text2LIVE: Text-Driven Layered Image and Video Editing
Bar-Tal, Ofri-Amar, Fridman et al. ยท 2022-05-25 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks
Li, Wang, Duan et al. ยท 2023-04-12 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Selvaraju, Cogswell, Das et al. ยท 02/2020 ยท journalArticle
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
FILIP: Fine-grained Interactive Language-Image Pre-Training
Yao, Huang, Hou et al. ยท 2021-11-09 ยท preprint
Computer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Interpreting CLIP's Image Representation via Text-Based Decomposition
Gandelsman, Efros, Steinhardt ยท 2023/10/13 ยท conferencePaper
Optimizing Relevance Maps of Vision Transformers Improves Robustness
Chefer, Schwartz, Wolf ยท 2022-12-06 ยท journalArticle
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
Chefer, Alaluf, Vinker et al. ยท 2023-05-31 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - GraphicsComputer Science - Machine Learning
Attention is not Explanation
Jain, Wallace ยท 2019-05-08 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and Language
Shortcut Learning in Deep Neural Networks
Geirhos, Jacobsen, Michaelis et al. ยท 2020-11-10 ยท journalArticle
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine LearningQuantitative Biology - Neurons and Cognition
When and why vision-language models behave like bags-of-words, and what to do about it?
Yuksekgonul, Bianchi, Kalluri et al. ยท 2023-03-23 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Explaining Classifiers with Causal Concept Effect (CaCE)
Goyal, Feder, Shalit et al. ยท journalArticle
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
Singh, Shrivastava, Vatsa et al. ยท 2024-03-29 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers
Aflalo, Du, Tseng et al. ยท 2022-08-22 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment
Gordon, Bitton, Shafir et al. ยท 2023-12-05 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Extract Free Dense Labels from CLIP
Zhou, Loy, Dai ยท 2022-07-27 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern Recognition
Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
Mukhoti, Lin, Poursaeed et al. ยท 6/2023 ยท conferencePaper
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
Hu, Liu, Kasai et al. ยท 2023-10-1 ยท conferencePaper
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
Xu, Liu, Wu et al. ยท journalArticle
RLmotivation
Benchmark for Compositional Text-to-Image Synthesis
Park, Azadi, Liu et al. ยท journalArticle
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
Ku, Jiang, Wei et al. ยท 2023-12-22 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
Elazar, Ravfogel, Jacovi et al. ยท 2021-02-19 ยท preprint
Computer Science - Computation and Language
ATTENTION-BASED INTERPRETABILITY WITH CONCEPT TRANSFORMERS
Rigotti, Miksovic, Giurgiu et al. ยท 2022 ยท journalArticle
Contrastive Explanations for Model Interpretability
Jacovi, Swayamdipta, Ravfogel et al. ยท 2021-09-14 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Machine Learning
Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives
Dhurandhar, Chen, Luss et al. ยท 2018 ยท conferencePaper
SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
Yu, Cheng, Wang et al. ยท 2023-10-28 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Multimedia
Unicom: Universal and Compact Representation Learning for Image Retrieval
An, Deng, Yang et al. ยท 2023-04-12 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
LXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, Bansal ยท 2019-12-03 ยท preprint
Computer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
TVLT: Textless Vision-Language Transformer
Tang, Cho, Nie et al. ยท journalArticle
What Does BERT Look at? An Analysis of BERTโ€™s Attention
Clark, Khandelwal, Levy et al. ยท 2019 ยท conferencePaper
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
Kim, Son, Kim ยท journalArticle
CoCa: Contrastive Captioners are Image-Text Foundation Models
Yu, Wang ยท journalArticle
ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data
Varma, Delbrouck, Hooper et al. ยท 2023-08-22 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computer Vision and Pattern Recognition
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding
Hu, Xu, Ye et al. ยท 2024-03-19 ยท preprint
Computer Science - Computer Vision and Pattern Recognition
Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training
Wan, Cho, Stengel-Eskin et al. ยท 2024-03-04 ยท preprint
Computer Science - Artificial IntelligenceComputer Science - Computation and LanguageComputer Science - Computer Vision and Pattern RecognitionComputer Science - Machine Learning
A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions
Urbanek, Bordes, Astolfi et al. ยท 2023-12-13 ยท preprint
Computer Science - Computer Vision and Pattern Recognition