MLLM-as-a-Judge for Image Safety without Human Labeling
Paper
•
2501.00192
•
Published
•
31
Papers to Read
-
-
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 107 -
Xmodel-2 Technical Report
Paper • 2412.19638 • Published • 27 -
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
Paper • 2412.18925 • Published • 101 -
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Paper • 2501.01257 • Published • 53 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 287 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 41 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 49 -
GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper • 2501.18492 • Published • 87 -
WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
Paper • 2501.18511 • Published • 20 -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 61 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 151 -
Expect the Unexpected: FailSafe Long Context QA for Finance
Paper • 2502.06329 • Published • 131 -
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
Paper • 2502.07870 • Published • 45 -
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Paper • 2502.07374 • Published • 39 -
Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance
Paper • 2502.08127 • Published • 55 -
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
Paper • 2502.07346 • Published • 54 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 49 -
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Paper • 2502.10248 • Published • 56 -
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Paper • 2502.12115 • Published • 45 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 58 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 182 -
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper • 2502.14499 • Published • 192 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 143 -
S*: Test Time Scaling for Code Generation
Paper • 2502.14382 • Published • 63 -
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Paper • 2502.14739 • Published • 103 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 60 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 94 -
R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
Paper • 2503.05132 • Published • 57 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 78 -
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Paper • 2503.01743 • Published • 85 -
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Paper • 2503.07536 • Published • 85 -
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Paper • 2503.07920 • Published • 97 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 121 -
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
Paper • 2503.11579 • Published • 20 -
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
Paper • 2503.10639 • Published • 50 -
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Paper • 2503.10615 • Published • 17 -
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
Paper • 2503.10291 • Published • 36 -
MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research
Paper • 2503.13399 • Published • 21 -
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
Paper • 2503.11495 • Published • 12 -
VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
Paper • 2503.13444 • Published • 16 -
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
Paper • 2503.14478 • Published • 47 -
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 30 -
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
Paper • 2503.06053 • Published • 138 -
TULIP: Towards Unified Language-Image Pretraining
Paper • 2503.15485 • Published • 48 -
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Paper • 2503.16419 • Published • 72 -
Video-T1: Test-Time Scaling for Video Generation
Paper • 2503.18942 • Published • 88 -
Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
Paper • 2503.18923 • Published • 12 -
Reasoning to Learn from Latent Thoughts
Paper • 2503.18866 • Published • 13 -
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?
Paper • 2503.19990 • Published • 34 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 143 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 40 -
CoLLM: A Large Language Model for Composed Image Retrieval
Paper • 2503.19910 • Published • 14 -
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 30 -
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
Paper • 2503.19325 • Published • 72 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 19 -
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
Paper • 2503.19855 • Published • 26 -
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
Paper • 2503.18931 • Published • 30 -
Defeating Prompt Injections by Design
Paper • 2503.18813 • Published • 19 -
Wan: Open and Advanced Large-Scale Video Generative Models
Paper • 2503.20314 • Published • 49 -
Gemini Robotics: Bringing AI into the Physical World
Paper • 2503.20020 • Published • 25 -
Video-R1: Reinforcing Video Reasoning in MLLMs
Paper • 2503.21776 • Published • 78 -
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Paper • 2503.21460 • Published • 77 -
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
Paper • 2503.21248 • Published • 20 -
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Paper • 2503.21696 • Published • 22 -
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
Paper • 2503.21614 • Published • 39 -
Your ViT is Secretly an Image Segmentation Model
Paper • 2503.19108 • Published • 21 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 53 -
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Paper • 2503.24290 • Published • 62 -
RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
Paper • 2503.24388 • Published • 30 -
Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation
Paper • 2503.24379 • Published • 75 -
JudgeLRM: Large Reasoning Models as a Judge
Paper • 2504.00050 • Published • 60 -
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
Paper • 2503.24376 • Published • 38 -
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
Paper • 2504.00595 • Published • 35 -
Z1: Efficient Test-time Scaling with Code
Paper • 2504.00810 • Published • 26 -
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Paper • 2503.24377 • Published • 17 -
Improved Visual-Spatial Reasoning via R1-Zero-Like Training
Paper • 2504.00883 • Published • 62 -
Understanding R1-Zero-Like Training: A Critical Perspective
Paper • 2503.20783 • Published • 45 -
PaperBench: Evaluating AI's Ability to Replicate AI Research
Paper • 2504.01848 • Published • 36 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 260 -
GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation
Paper • 2504.02782 • Published • 56 -
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
Paper • 2504.02587 • Published • 30 -
MedSAM2: Segment Anything in 3D Medical Images and Videos
Paper • 2504.03600 • Published • 8 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 172 -
One-Minute Video Generation with Test-Time Training
Paper • 2504.05298 • Published • 98 -
Rethinking Reflection in Pre-Training
Paper • 2504.04022 • Published • 77 -
Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)
Paper • 2504.03151 • Published • 13 -
Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought
Paper • 2504.05599 • Published • 81 -
DDT: Decoupled Diffusion Transformer
Paper • 2504.05741 • Published • 73 -
OmniCaptioner: One Captioner to Rule Them All
Paper • 2504.07089 • Published • 20 -
VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning
Paper • 2504.06958 • Published • 10 -
Are We Done with Object-Centric Learning?
Paper • 2504.07092 • Published • 6 -
Kimi-VL Technical Report
Paper • 2504.07491 • Published • 121 -
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper • 2504.07128 • Published • 82 -
VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning
Paper • 2504.07956 • Published • 45 -
MM-IFEngine: Towards Multimodal Instruction Following
Paper • 2504.07957 • Published • 34 -
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Paper • 2504.08685 • Published • 121 -
GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
Paper • 2504.08736 • Published • 47 -
FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
Paper • 2504.09925 • Published • 38 -
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
Paper • 2504.10479 • Published • 241 -
VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
Paper • 2504.08837 • Published • 42 -
TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning
Paper • 2504.09641 • Published • 16 -
xVerify: Efficient Answer Verifier for Reasoning Model Evaluations
Paper • 2504.10481 • Published • 84 -
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Paper • 2504.08672 • Published • 53 -
Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding
Paper • 2504.10465 • Published • 28 -
Efficient Reasoning Models: A Survey
Paper • 2504.10903 • Published • 18 -
CLIMB: CLustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training
Paper • 2504.13161 • Published • 87 -
VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
Paper • 2504.13122 • Published • 21 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 58 -
ToolRL: Reward is All Tool Learning Needs
Paper • 2504.13958 • Published • 39 -
VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
Paper • 2504.15279 • Published • 62 -
TTRL: Test-Time Reinforcement Learning
Paper • 2504.16084 • Published • 80 -
Describe Anything: Detailed Localized Image and Video Captioning
Paper • 2504.16072 • Published • 49 -
Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models
Paper • 2504.15271 • Published • 62 -
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper • 2504.17192 • Published • 58 -
IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
Paper • 2504.15415 • Published • 20 -
The Bitter Lesson Learned from 2,000+ Multilingual Benchmarks
Paper • 2504.15521 • Published • 57