Haoran Li PRO

haoranli-ml's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 5 months ago

SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning

Paper • 2602.08234 • Published Feb 9 • 76

CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs

Paper • 2602.05258 • Published Feb 5 • 7

upvoted a collection 5 months ago

CoPE

Collection

CoPE is a drop-in enhancement of RoPE that delivers consistent gains within the training context and during long-context extrapoaltion. • 9 items • Updated May 20 • 2

upvoted a paper 7 months ago

Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning

Paper • 2511.16043 • Published Nov 20, 2025 • 110

upvoted a paper 8 months ago

HoPE: Hybrid of Position Embedding for Length Generalization in Vision-Language Models

Paper • 2505.20444 • Published May 26, 2025 • 5