Key papers

• DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems (2026)
  Maojun Sun et al.
  1.94
• Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation (2026)
  Zihan Su et al.
  1.94
• P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads (2026)
  Yun Luo et al.
  1.94
• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception (2026)
  Lai Wei et al.
  1.94
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents (2026)
  Bowen Ye et al.
  1.94
• Watch, Remember, Reason: Human-View Video Understanding with MLLMs (2026)
  Jiahao Meng et al.
  1.94
• Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings (2026)
  Shubhang Bhatnagar et al.
  1.94
• Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence (2026)
  Xuanle Zhao et al.
  1.94
• Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation (2026)
  Sihan Wang et al.
  1.94
• SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture (2026)
  Haiwen Diao et al.
  1.89
• MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning (2026)
  Yuxin Liu et al.
  1.89
• CurveStream: Boosting Streaming Video Understanding in MLLMs via Curvature-Aware Hierarchical Visual Memory Management (2026)
  Chao Wang et al.
  1.78
• The Jumping Reasoning Curve? Tracking the Evolution of Reasoning Performance in GPT-[n] and o-[n] Models on Multimodal Puzzles (2025)
  Vernon Y. H. Toh et al.
  1.28
• EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents (2025)
  Rui Yang et al.
  1.28
• V2V-LLM: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multi-Modal Large Language Models (2025)
  Hsu-kuang Chiu et al.
  1.28
• SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories (2025)
  Muzhi Zhu et al.
  1.28
• DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding (2025)
  Xinyu Ma et al.
  1.28
• VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning (2025)
  Xinhao Li et al.
  1.28
• SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025)
  Hardy Chen et al.
  1.28
• Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging (2025)
  Shiqi Chen et al.
  1.28
• MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness (2025)
  Yunlong Tang et al.
  1.28
• Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning? (2025)
  Junhao Cheng et al.
  1.28
• Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO (2025)
  Muzhi Zhu et al.
  1.28
• VGR: Visual Grounded Reasoning (2025)
  Jiacong Wang et al.
  1.28
• AHELM: A Holistic Evaluation of Audio-Language Models (2025)
  Tony Lee et al.
  1.28
• The Landscape of Agentic Reinforcement Learning for LLMs: A Survey (2025)
  Guibin Zhang et al.
  1.28
• SAIL-VL2 Technical Report (2025)
  Weijie Yin et al.
  1.28
• GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoning (2025)
  Guizhen Chen et al.
  1.28
• UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning (2025)
  Ye Liu et al.
  1.28
• Visual Jigsaw Post-Training Improves MLLMs (2025)
  Penghao Wu et al.
  1.28
• Apriel-1.5-15b-Thinker (2025)
  Shruthan Radhakrishna et al.
  1.28
• VIDEOP2R: Video Understanding from Perception to Reasoning (2025)
  Yifan Jiang et al.
  1.28
• Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation (2025)
  Inferix Team et al.
  1.28
• From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images (2025)
  Yiming Chen et al.
  1.28
• JMMMU-Pro: Image-based Japanese Multi-discipline Multimodal Understanding Benchmark via Vibe Benchmark Construction (2025)
  Atsuyuki Miyai et al.
  1.28
• Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection (2025)
  Kaixin Ding et al.
  1.28
• Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation (2025)
  Huajie Tan et al.
  1.28
• Multimodal Web Navigation with Instruction-Finetuned Foundation Models (2023)
  Hiroki Furuta et al.
  —
• Tiny LVLM-eHub: Early Multimodal Experiments with Bard (2023)
  Wenqi Shao et al.
  —
• PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion (2023)
  Yiduo Guo et al.
  —
• Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models (2023)
  Haoning Wu et al.
  —
• Silkie: Preference Distillation for Large Visual Language Models (2023)
  Lei Li et al.
  —
• MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models (2024)
  Hang Hua et al.
  —
• Mitigating Object Hallucination via Concentric Causal Attention (2024)
  Yun Xing et al.
  —
• CAMEL-Bench: A Comprehensive Arabic LMM Benchmark (2024)
  Sara Ghaboura et al.
  —