Key papers

• AgenticDataBench: A Comprehensive Benchmark for Data Agents (2026)
  Zhaoyan Sun et al.
  2.00
• Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation (2026)
  Zihan Su et al.
  1.94
• Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles (2026)
  Shaohan Wang et al.
  1.94
• Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception (2026)
  Lai Wei et al.
  1.94
• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence (2026)
  Xiang An et al.
  1.94
• FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search (2026)
  James Xu Zhao et al.
  1.94
• Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation (2026)
  Atin Pothiraj et al.
  1.94
• 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
• Visual-RFT: Visual Reinforcement Fine-Tuning (2025)
  Ziyu Liu et al.
  1.28
• Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning (2025)
  Qinghao Ye et al.
  1.28
• SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories (2025)
  Muzhi Zhu et al.
  1.28
• ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering (2025)
  Kaisi Guan et al.
  1.28
• A Unified Agentic Framework for Evaluating Conditional Image Generation (2025)
  Jifang Wang et al.
  1.28
• Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding (2025)
  Tao Zhang et al.
  1.28
• Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization (2025)
  Pritam Sarkar et al.
  1.28
• Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis (2025)
  Tianbao Xie et al.
  1.28
• NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search (2025)
  Sunhao Dai et al.
  1.28
• STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs (2025)
  Zongzhao Li et al.
  1.28
• Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO (2025)
  Muzhi Zhu et al.
  1.28
• SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems (2025)
  Peiran Li et al.
  1.28
• VGR: Visual Grounded Reasoning (2025)
  Jiacong Wang et al.
  1.28
• Visual Representation Alignment for Multimodal Large Language Models (2025)
  Heeji Yoon et al.
  1.28
• SAIL-VL2 Technical Report (2025)
  Weijie Yin et al.
  1.28
• D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2025)
  Hongze Mi 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
• RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning (2025)
  Sicheng Feng et al.
  1.28
• RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training (2025)
  Hongzhi Zang et al.
  1.28
• Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions (2025)
  Eyal Gutflaish et al.
  1.28
• TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval (2025)
  Özay Ezerceli et al.
  1.28
• ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning (2025)
  Shengyuan Ding et al.
  1.28
• Hybrid Attribution Priors for Explainable and Robust Model Training (2025)
  Zhuoran Zhang et al.
  1.28
• Simple Token-Level Confidence Improves Caption Correctness (2023)
  Suzanne Petryk et al.
  —
• Silkie: Preference Distillation for Large Visual Language Models (2023)
  Lei Li et al.
  —
• ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward Modeling (2024)
  Siming Yan et al.
  —
• HEMM: Holistic Evaluation of Multimodal Foundation Models (2024)
  Paul Pu Liang et al.
  —
• PiTe: Pixel-Temporal Alignment for Large Video-Language Model (2024)
  Yang Liu et al.
  —
• MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models (2024)
  Hang Hua et al.
  —