Chenyan Xiong Research Group at CMU

university

https://www.cs.cmu.edu/~cx/

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

zhongshsh authored a paper 14 days ago

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

zhongshsh authored a paper 14 days ago

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

zhongshsh authored a paper 14 days ago

AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web

View all activity

Papers

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

RePro: Training Language Models to Faithfully Recycle the Web for Pretraining

View all Papers

zhongshsh

authored 3 papers 14 days ago

Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality

Paper • 2602.08004 • Published Feb 8 • 5

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Paper • 2604.20087 • Published Apr 22 • 15

AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web

Paper • 2604.10938 • Published Apr 13

zhongshsh

updated a dataset 15 days ago

cx-cmu/AgentWebBench-corpus

Viewer • Updated 15 days ago • 1 • 843

zhongshsh

published a dataset 25 days ago

cx-cmu/AgentWebBench-corpus

Viewer • Updated 15 days ago • 1 • 843

ethanning

authored a paper about 2 months ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Paper • 2605.05724 • Published May 7 • 16

ethanning

submitted a paper to Daily Papers about 2 months ago

Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes

Paper • 2605.05724 • Published May 7 • 16

yiyangd

submitted a paper to Daily Papers 2 months ago

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

Paper • 2604.20012 • Published Apr 21 • 5

ethanning

authored a paper 2 months ago

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Paper • 2604.20087 • Published Apr 22 • 15

wuwendy

updated a dataset 2 months ago

cx-cmu/agent_trajectories

Updated Apr 23 • 63 • 1

zhongshsh

submitted a paper to Daily Papers 2 months ago

SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

Paper • 2604.20087 • Published Apr 22 • 15

zhongshsh

updated 3 models 3 months ago

updated a Space 3 months ago

AutoGEO Mini

👁

Inference Model for AutoGEO work

ethanning

authored a paper 3 months ago

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Paper • 2604.01029 • Published Apr 1 • 8

ethanning

submitted a paper to Daily Papers 3 months ago

Revision or Re-Solving? Decomposing Second-Pass Gains in Multi-LLM Pipelines

Paper • 2604.01029 • Published Apr 1 • 8

lixiaochuan2020

submitted a paper to Daily Papers 4 months ago

Benchmark Test-Time Scaling of General LLM Agents

Paper • 2602.18998 • Published Feb 22 • 10

yuzc19

updated 2 models 4 months ago

cx-cmu/repro-rephraser-4B

Text Generation • 196k • Updated Feb 18 • 497 • • 2

cx-cmu/repro-rephraser-1B

Text Generation • 1B • Updated Feb 18 • 3

AI & ML interests

Recent Activity

Papers

Team members 14

cx-cmu's activity

AutoGEO Mini