Keyang Xuan

keyangx3's activity

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

upvoted a paper 1 day ago

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

Paper • 2605.26029 • Published 2 days ago • 9

upvoted a paper 9 days ago

Interactive Evaluation Requires a Design Science

Paper • 2605.17829 • Published 12 days ago • 14

submitted a paper to Daily Papers 9 days ago

Interactive Evaluation Requires a Design Science

Paper • 2605.17829 • Published 12 days ago • 14

liked a dataset 11 days ago

lwaekfjlk/artifact-bench

Viewer • Updated 14 days ago • 30.5k • 2.17k • 9

upvoted a paper 16 days ago

Useful Memories Become Faulty When Continuously Updated by LLMs

Paper • 2605.12978 • Published 17 days ago • 18

upvoted a paper about 1 month ago

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Paper • 2602.05115 • Published Feb 4 • 20

upvoted a paper 4 months ago

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Paper • 2602.07276 • Published Feb 7 • 11

authored a paper 4 months ago

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Paper • 2602.07276 • Published Feb 7 • 11

commented a paper 4 months ago

Large Language Model Reasoning Failures

Paper • 2602.06176 • Published Feb 5 • 12 •

3

upvoted a paper 4 months ago

Large Language Model Reasoning Failures

Paper • 2602.06176 • Published Feb 5 • 12

authored 5 papers 4 months ago

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Paper • 2602.05115 • Published Feb 4 • 20

ResearchTown: Simulator of Human Research Community

Paper • 2412.17767 • Published Dec 23, 2024 • 14

Sotopia-RL: Reward Design for Social Intelligence

Paper • 2508.03905 • Published Aug 5, 2025 • 23

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Paper • 2504.09897 • Published Apr 14, 2025

TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents

Paper • 2510.06579 • Published Oct 8, 2025

submitted a paper to Daily Papers 4 months ago

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Paper • 2602.05115 • Published Feb 4 • 20

upvoted a paper 4 months ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published Feb 1 • 45

upvoted a paper 10 months ago

Sotopia-RL: Reward Design for Social Intelligence

Paper • 2508.03905 • Published Aug 5, 2025 • 23