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 4
papers 4 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 262
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2604.12374 • Published • 36
Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
Paper • 2605.05242 • Published • 107
ZhuofengLi
authored a
paper 7 days ago
eigentom
authored a
paper 7 days ago
ZhuofengLi
authored a
paper 7 days ago
ZhuofengLi
submitted a
paper to Daily Papers 10 days ago
eigentom
authored 4
papers about 1 month ago
RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought
Paper • 2506.04277 • Published
VEU-Bench: Towards Comprehensive Understanding of Video Editing
Paper • 2504.17828 • Published
SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding
Paper • 2603.16124 • Published • 3
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 262
DongfuJiang
authored 3
papers about 2 months ago
EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning
Paper • 2603.12698 • Published • 1
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Paper • 2603.19220 • Published • 67
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 98
ZhuofengLi
authored a
paper about 2 months ago
ZhuofengLi
submitted a
paper to Daily Papers about 2 months ago
DongfuJiang
updated a
dataset 6 months ago
ZhuofengLi
authored a
paper 7 months ago
DongfuJiang
authored a
paper 7 months ago