Tsinghua NLP Group

university

http://nlp.csai.tsinghua.edu.cn/

THUNLP

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

hbx submitted a paper about 4 hours ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

hbx authored a paper 16 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

hbx submitted a paper 17 days ago

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

View all activity

Papers

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

View all Papers

TsinghuaNLP 's papers 5

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

Tsinghua NLP Group

Submitted by

Bingxiang He

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

Tsinghua NLP Group

6 2

Submitted by

Chenyang Song

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Tsinghua NLP Group

2 1

Submitted by

Bingxiang He

116

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Tsinghua NLP Group

974 6

Submitted by

ssz

FaithLens: Detecting and Explaining Faithfulness Hallucination

Tsinghua NLP Group

105 2

AI & ML interests

Recent Activity

Papers

Team members 4

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments

DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

FaithLens: Detecting and Explaining Faithfulness Hallucination