🤝 Open to Collab

Jiahao Yuan

Jhcircle

JhCircle

AI & ML interests

LLM & agent rl, Feel free to reach out via email at [email protected] 🤗 for relevant opportunities or potential collaborations —— I’m always open to research discussions!

Recent Activity

upvoted a paper 15 days ago

From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery

upvoted a paper 15 days ago

SWE-Game: Can Coding Agents Build the Games We Want?

upvoted a paper about 2 months ago

Towards a Densing Law for User Representation Learning at Billion-Scale Capacity

View all activity

Organizations

None yet

upvoted 2 papers 15 days ago

From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery

Paper • 2610.09684 • Published 17 days ago • 18

SWE-Game: Can Coding Agents Build the Games We Want?

Paper • 2609.33678 • Published 17 days ago • 34

upvoted a paper about 2 months ago

Towards a Densing Law for User Representation Learning at Billion-Scale Capacity

Paper • 2608.23392 • Published Aug 24 • 28

upvoted a paper 3 months ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published Aug 6 • 105

liked a model 3 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated Sep 2 • 922k • • 11.8k

upvoted a paper 3 months ago

SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2607.14777 • Published Jul 16 • 106

upvoted a paper 4 months ago

OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning

Paper • 2606.26790 • Published Jun 25 • 59

upvoted a paper 5 months ago

Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling

Paper • 2605.27030 • Published May 26 • 29

New activity in Jhcircle/Kardia-R1 5 months ago

qingganmodel

#1 opened 5 months ago by

Tomes889

upvoted a paper 7 months ago

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Paper • 2604.02268 • Published Apr 2 • 100

commented a paper 7 months ago

Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning

Paper • 2512.01282 • Published Dec 1, 2025 • 3 •

updated a collection 7 months ago

Kardia-R1

Collection

Model Weight and Dataset of our WWW 2026 paper: Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric • 3 items • Updated Mar 15 • 1

New activity in Jhcircle/KardiaBench 7 months ago

When will it be available for download?

#2 opened 10 months ago by

sky21312

Dataset access application

#3 opened 8 months ago by

gorsonpy

updated a model 8 months ago

Jhcircle/Kardia-R1

Question Answering • 8B • Updated Mar 3 • 4 • 5

liked a model 8 months ago

Jhcircle/Kardia-R1

Question Answering • 8B • Updated Mar 3 • 4 • 5

updated a dataset 8 months ago

Jhcircle/KardiaBench

Viewer • Updated Mar 2 • 22.1k • 23 • 11

published a model 8 months ago

Jhcircle/Kardia-R1

Question Answering • 8B • Updated Mar 3 • 4 • 5

authored a paper 8 months ago

Query as Anchor: Scenario-Adaptive User Representation via Large Language Model

Paper • 2602.14492 • Published Feb 16 • 18

submitted a paper to Daily Papers 8 months ago

Query as Anchor: Scenario-Adaptive User Representation via Large Language Model

Paper • 2602.14492 • Published Feb 16 • 18

Jiahao Yuan

AI & ML interests

Recent Activity

Organizations

Jhcircle's activity

qingganmodel

When will it be available for download?

Dataset access application