Yiheng Shu

yhshu's activity

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

updated a dataset 4 days ago

osunlp/AgentCL

Viewer • Updated 4 days ago • 300 • 854 • 1

authored 2 papers 4 months ago

REMem: Reasoning with Episodic Memory in Language Agent

Paper • 2602.13530 • Published Feb 28

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Paper • 2606.02461 • Published Jun 2 • 6

upvoted 2 papers 4 months ago

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Paper • 2606.02540 • Published Jun 1 • 10

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Paper • 2606.02461 • Published Jun 2 • 6

commented a paper 4 months ago

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Paper • 2606.02461 • Published Jun 2 • 6 •

2

submitted a paper to Daily Papers 4 months ago

AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents

Paper • 2606.02461 • Published Jun 2 • 6

published a dataset 4 months ago

osunlp/AgentCL

Viewer • Updated 4 days ago • 300 • 854 • 1

upvoted 2 papers 4 months ago

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published May 28 • 55

QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks

Paper • 2605.24218 • Published May 22 • 44

upvoted a paper 10 months ago

Differentiable Evolutionary Reinforcement Learning

Paper • 2512.13399 • Published Dec 15, 2025 • 22

liked a model 10 months ago

openai/gpt-oss-120b

Text Generation • 117B • Updated Aug 26, 2025 • 4.45M • • 5.36k

upvoted a paper 10 months ago

Auto-scaling Continuous Memory for GUI Agent

Paper • 2510.09038 • Published Oct 10, 2025 • 1

liked a dataset 11 months ago

BatsResearch/planetarium

Viewer • Updated Feb 25, 2025 • 584k • 299 • 18

upvoted a paper 11 months ago

JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence

Paper • 2510.23538 • Published Oct 27, 2025 • 100

upvoted a paper 12 months ago

Agent Learning via Early Experience

Paper • 2510.08558 • Published Oct 9, 2025 • 257

liked a dataset about 1 year ago

google/frames-benchmark

Viewer • Updated Oct 15, 2024 • 824 • 14.4k • 267

liked a dataset over 1 year ago

osunlp/Mind2Web-2

Viewer • Updated Dec 14, 2025 • 130 • 186 • 17

authored a paper over 1 year ago

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Paper • 2506.21506 • Published Jun 26, 2025 • 52

upvoted a paper over 1 year ago

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Paper • 2506.21506 • Published Jun 26, 2025 • 52