杨乐乐's picture

1 5

杨乐乐

ssl-asuka

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

upvoted a paper 5 days ago

MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning

authored a paper 5 days ago

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision

View all activity

Organizations

None yet

authored 2 papers 5 days ago

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision

Paper • 2508.08177 • Published Aug 11, 2025

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published 8 days ago • 91

submitted a paper to Daily Papers 5 days ago

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Paper • 2601.02151 • Published 8 days ago • 91

authored a paper 8 days ago

DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving

Paper • 2505.20665 • Published May 27, 2025 • 2