Knowledge Engineer Group @ Tsinghua University

university

https://keg.cs.tsinghua.edu.cn/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

tsq2000 submitted a paper 14 days ago

MAIC-UI: Making Interactive Courseware with Generative UI

NeoZ123 updated a collection about 2 months ago

NeoZ123 updated a model about 2 months ago

THU-KEG/DeepDive-30B-A3B-C-GRPO

View all activity

Papers

MAIC-UI: Making Interactive Courseware with Generative UI

WildReward: Learning Reward Models from In-the-Wild Human Interactions

View all Papers

submitted a paper to Daily Papers 14 days ago

MAIC-UI: Making Interactive Courseware with Generative UI

Paper • 2604.25806 • Published 15 days ago • 8

updated a collection about 2 months ago

CaRR & C-GRPO

Data and models for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards". • 6 items • Updated Mar 25 • 1

updated 4 models about 2 months ago

THU-KEG/DeepDive-30B-A3B-C-GRPO

31B • Updated Mar 25 • 3

THU-KEG/DeepDive-4B-C-GRPO

4B • Updated Mar 25 • 5

THU-KEG/DeepDive-30B-A3B-SFT

31B • Updated Mar 25 • 4

THU-KEG/DeepDive-4B-SFT

4B • Updated Mar 25 • 6

updated a dataset about 2 months ago

THU-KEG/CaRR-DeepDive

Preview • Updated Mar 25 • 235 • 1

authored a paper 2 months ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 53

submitted a paper to Daily Papers 2 months ago

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

Paper • 2603.12201 • Published Mar 12 • 53

updated a collection 2 months ago

CaRR & C-GRPO

Data and models for the paper "Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards". • 6 items • Updated Mar 25 • 1

published 4 models 2 months ago

THU-KEG/DeepDive-30B-A3B-C-GRPO

31B • Updated Mar 25 • 3

THU-KEG/DeepDive-30B-A3B-SFT

31B • Updated Mar 25 • 4

THU-KEG/DeepDive-4B-C-GRPO

4B • Updated Mar 25 • 5

THU-KEG/DeepDive-4B-SFT

4B • Updated Mar 25 • 6

submitted a paper to Daily Papers 2 months ago

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published Mar 6 • 93

updated a collection 3 months ago

WildReward

Learning Reward Models from In-the-Wild Interactions • 4 items • Updated Mar 2 • 2