Wenhao Chai

wchai's activity

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

published a dataset about 3 hours ago

FrontierCS2/FrontierCS-2-runs

Updated about 3 hours ago

published 9 models 4 days ago

wchai/aurora_dev_13b

Updated May 29, 2024

wchai/aurora_dev_7b_video

Updated Jun 7, 2024

wchai/aurora_dev_7b

Updated May 29, 2024

wchai/aurora_dev_13b_video

Updated Jun 7, 2024

wchai/AuroraCap-7B-VID

7B • Updated Sep 25, 2024 • 3

wchai/AuroraCap-8B-IMG

8B • Updated Sep 29, 2024 • 1

wchai/AuroraCap-8B-IMG-xtuner

Updated Sep 29, 2024 • 1

wchai/Aurora_history

Updated Oct 2, 2024

wchai/AuroraCap-7B-IMG

7B • Updated Oct 3, 2024 • 2

upvoted a paper 14 days ago

From Evidence to Action: How Tool-Using Agents Fail

Paper • 2610.07753 • Published 15 days ago • 46

upvoted 2 papers 19 days ago

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Paper • 2609.38155 • Published 22 days ago • 116

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published 20 days ago • 92

submitted a paper to Daily Papers 21 days ago

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published 22 days ago • 40

upvoted a paper 21 days ago

EasyPPO: Stabilizing the Critic Is Key

Paper • 2609.36802 • Published 22 days ago • 40

New activity in GMLRVigil/BenchCheck-LongVideo about 1 month ago

videochat3-4b: frame-budget ladder rows (23044 rows; 32/128/512 complete, 1024 partial)

#6 opened about 1 month ago by

wchai

qwen3vl-32b: frame-budget ladder rows (19265 rows; 32/128/512 complete, 1024 partial)

#5 opened about 1 month ago by

wchai

llava-ov2-8b: frame-budget ladder rows (16708 rows; 32/128/512 complete, 1024 partial)

#4 opened about 1 month ago by

wchai

upvoted an article about 1 month ago

view article

Article

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

• 

quao627

•

Sep 15

• 15

submitted a paper to Daily Papers about 1 month ago

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

Paper • 2609.15309 • Published Sep 14 • 13