Watch Before You Answer: Learning from Visually Grounded Post-Training
Paper • 2604.05117 • Published • 35
AI & ML interests
None defined yet.
Recent Activity
View all activity
DongfuJiang
authored 3
papers 1 minute ago
DongfuJiang
authored a
paper 2 minutes ago
pingnieuk
authored 9
papers 1 day ago
VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction
Paper • 2602.13294 • Published • 13
Beyond Closed-Pool Video Retrieval: A Benchmark and Agent Framework for Real-World Video Search and Moment Localization
Paper • 2602.10159 • Published • 3
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
Paper • 2603.12698 • Published • 1
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Paper • 2603.16124 • Published • 3
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 98
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
Paper • 2603.27862 • Published • 31
SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
Paper • 2603.20691 • Published • 10
MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models
Paper • 2604.23321 • Published
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 102
pingnieuk
authored a
paper 2 days ago
ZhuofengLi
authored a
paper 4 days ago
IPF
authored a
paper 4 days ago
yuz9yuz
authored a
paper 4 days ago
ZhuofengLi
authored a
paper 4 days ago
ZhuofengLi
submitted a
paper to Daily Papers 6 days ago
yuz9yuz
authored a
paper 22 days ago