Knowledge Engineer Group @ Tsinghua University

university

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

THU-KEG

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

Kikkk updated a dataset 9 days ago

THU-KEG/AgentIF

RicardoL1u new activity 16 days ago

THU-KEG/RM-Bench:Many chosen rows are truncated

linny2002 updated a model 19 days ago

THU-KEG/LLaDA-8B-BGPO-sudoku

View all activity

Papers

DeepPrune: Parallel Scaling without Inter-trace Redundancy

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

View all Papers

Kikkk

updated a dataset 9 days ago

THU-KEG/AgentIF

Viewer • Updated 9 days ago • 707 • 101 • 5

RicardoL1u

in THU-KEG/RM-Bench 16 days ago

Many chosen rows are truncated

#3 opened 22 days ago by

AlexShengzhiMeta

linny2002

updated 4 models 19 days ago

THU-KEG/LLaDA-8B-BGPO-sudoku

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

THU-KEG/LLaDA-8B-BGPO-countdown

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

THU-KEG/LLaDA-8B-BGPO-code

Reinforcement Learning • 8B • Updated 19 days ago • 28 • 1

THU-KEG/LLaDA-8B-BGPO-math

Reinforcement Learning • 8B • Updated 19 days ago • 34 • 1

NeoZ123

updated a collection 22 days ago

LLaDA-8B-BGPO

Boundary-Guided Policy Optimization for Memory-Efficient RL of Diffusion Large Language Models • 4 items • Updated 22 days ago • 4

NeoZ123

updated a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-sudoku

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

NeoZ123

published a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-sudoku

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

NeoZ123

updated a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-countdown

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

NeoZ123

published a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-countdown

Reinforcement Learning • 8B • Updated 19 days ago • 30 • 1

NeoZ123

updated a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-code

Reinforcement Learning • 8B • Updated 19 days ago • 28 • 1

NeoZ123

published a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-code

Reinforcement Learning • 8B • Updated 19 days ago • 28 • 1

NeoZ123

updated a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-math

Reinforcement Learning • 8B • Updated 19 days ago • 34 • 1

NeoZ123

published a model 22 days ago

THU-KEG/LLaDA-8B-BGPO-math

Reinforcement Learning • 8B • Updated 19 days ago • 34 • 1

tsq2000

in THU-KEG/DeepPrune-Judge-4B 22 days ago

Update license metadata and add paper abstract

#1 opened 23 days ago by

tsq2000

updated a collection 23 days ago

DeepPrune

Parallel Scaling without Inter-trace Redundancy • 3 items • Updated 23 days ago • 1