MLLM-as-a-Judge for Image Safety without Human Labeling
Paper
•
2501.00192
•
Published
•
29
Papers to Read
-
-
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 106 -
Xmodel-2 Technical Report
Paper • 2412.19638 • Published • 26 -
HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs
Paper • 2412.18925 • Published • 100 -
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Paper • 2501.01257 • Published • 52 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 282 -
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Paper • 2501.09686 • Published • 39 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 48 -
GuardReasoner: Towards Reasoning-based LLM Safeguards
Paper • 2501.18492 • Published • 86 -
WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training
Paper • 2501.18511 • Published • 19 -
LIMO: Less is More for Reasoning
Paper • 2502.03387 • Published • 60 -
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling
Paper • 2502.06703 • Published • 148 -
Expect the Unexpected: FailSafe Long Context QA for Finance
Paper • 2502.06329 • Published • 130 -
TextAtlas5M: A Large-scale Dataset for Dense Text Image Generation
Paper • 2502.07870 • Published • 43 -
LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
Paper • 2502.07374 • Published • 38 -
Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance
Paper • 2502.08127 • Published • 53 -
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models
Paper • 2502.07346 • Published • 52 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 48 -
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Paper • 2502.10248 • Published • 54 -
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
Paper • 2502.12115 • Published • 43 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 57 -
Qwen2.5-VL Technical Report
Paper • 2502.13923 • Published • 178 -
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper • 2502.14499 • Published • 188 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 139 -
S*: Test Time Scaling for Code Generation
Paper • 2502.14382 • Published • 61 -
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
Paper • 2502.14739 • Published • 99 -
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
Paper • 2503.07365 • Published • 55 -
Token-Efficient Long Video Understanding for Multimodal LLMs
Paper • 2503.04130 • Published • 88 -
R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model
Paper • 2503.05132 • Published • 52 -
Visual-RFT: Visual Reinforcement Fine-Tuning
Paper • 2503.01785 • Published • 74 -
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Paper • 2503.01743 • Published • 80 -
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
Paper • 2503.07536 • Published • 83 -
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
Paper • 2503.07920 • Published • 95 -
Unified Reward Model for Multimodal Understanding and Generation
Paper • 2503.05236 • Published • 112 -
Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
Paper • 2503.11579 • Published • 18 -
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
Paper • 2503.10639 • Published • 47 -
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Paper • 2503.10615 • Published • 16 -
VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
Paper • 2503.10291 • Published • 32 -
MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research
Paper • 2503.13399 • Published • 20 -
V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning
Paper • 2503.11495 • Published • 11 -
VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
Paper • 2503.13444 • Published • 15 -
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM
Paper • 2503.14478 • Published • 42 -
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 29 -
DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
Paper • 2503.06053 • Published • 136 -
TULIP: Towards Unified Language-Image Pretraining
Paper • 2503.15485 • Published • 43 -
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
Paper • 2503.16419 • Published • 65 -
Video-T1: Test-Time Scaling for Video Generation
Paper • 2503.18942 • Published • 85 -
Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
Paper • 2503.18923 • Published • 11 -
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 • 31 -
Qwen2.5-Omni Technical Report
Paper • 2503.20215 • Published • 112 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 37 -
CoLLM: A Large Language Model for Composed Image Retrieval
Paper • 2503.19910 • Published • 11 -
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Paper • 2503.19622 • Published • 29 -
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
Paper • 2503.19325 • Published • 70 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 16 -
Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
Paper • 2503.19855 • Published • 24 -
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
Paper • 2503.18931 • Published • 29 -
Defeating Prompt Injections by Design
Paper • 2503.18813 • Published • 18 -
Wan: Open and Advanced Large-Scale Video Generative Models
Paper • 2503.20314 • Published • 44 -
Gemini Robotics: Bringing AI into the Physical World
Paper • 2503.20020 • Published • 21 -
Video-R1: Reinforcing Video Reasoning in MLLMs
Paper • 2503.21776 • Published • 74 -
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Paper • 2503.21460 • Published • 67 -
ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition
Paper • 2503.21248 • Published • 19 -
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Paper • 2503.21696 • Published • 21 -
A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
Paper • 2503.21614 • Published • 32 -
Your ViT is Secretly an Image Segmentation Model
Paper • 2503.19108 • Published • 17 -
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Paper • 2503.24235 • Published • 40 -
Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
Paper • 2503.24290 • Published • 51