Kele Shao (SII)

keleshao's activity

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

upvoted 2 papers 11 days ago

Don't Just Fine-tune the Agent, Tune the Environment

Paper • 2510.10197 • Published 14 days ago • 27

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression

Paper • 2510.08525 • Published 16 days ago • 21

upvoted a paper 16 days ago

UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAG

Paper • 2510.03663 • Published 22 days ago • 15

upvoted a paper 17 days ago

OBS-Diff: Accurate Pruning For Diffusion Models in One-Shot

Paper • 2510.06751 • Published 17 days ago • 21

upvoted a paper 22 days ago

RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning

Paper • 2510.02240 • Published 23 days ago • 17

upvoted 2 papers 3 months ago

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

Paper • 2508.00414 • Published Aug 1 • 91

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

Paper • 2507.20198 • Published Jul 27 • 26

upvoted a paper 5 months ago

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Paper • 2505.21334 • Published May 27 • 21