PaperHub

Zhaopeng Tu

~Zhaopeng_Tu1

23
论文总数
11.5
年均投稿
5.7
平均评分
接收情况15/23
会议分布
ICLR
12
NeurIPS
8
ICML
3

发表论文 (23 篇)

202516 篇

7.0
4

RaSA: Rank-Sharing Low-Rank Adaptation

ICLR 2025Poster
7.0
4

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

ICLR 2025Poster
8.2
3

SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning

NeurIPS 2025Poster
6.4
4

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

NeurIPS 2025Poster
7.1
5

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

NeurIPS 2025Poster
3.7
3

Insight Over Sight? Exploring the Vision-Knowledge Conflicts in Multimodal LLMs

ICLR 2025withdrawn
6.8
4

Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards

NeurIPS 2025Poster
4.2
5

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

ICLR 2025withdrawn
5.8
4

Competing Large Language Models in Multi-Agent Gaming Environments

ICLR 2025Poster
5.3
3

Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

ICLR 2025Rejected
6.0
4

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

NeurIPS 2025Poster
6.3
3

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM’s Reasoning Capability

ICML 2025Poster
4.4
4

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

ICML 2025Rejected
4.9
4

Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models

ICML 2025Poster
7.3
4

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

NeurIPS 2025Spotlight
6.8
4

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

NeurIPS 2025Poster
合作者 (20)