PaperHub
影响力指数
46.97/100
前 9.9%
全站排名 #6,383
发表论文19 篇
平均评分4.9
年均产出6.3 篇/年

Peng Li

Associate Professor@Tsinghua University·中国·OpenReview
研究方向

AI4Math · Agent · Multi-modal · Pre-trained Models · Natural Language Processing · Machine Translation · Question Answering

5.0
20

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

ICLR 2026Rejected
4.8
25

AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection

ICLR 2026Rejected
4.5
19

Agent-Environment Alignment via Automated Interface Generation

ICLR 2026Rejected
4.5
25

Visual Abstract Thinking: Enhancing Multimodal Reasoning via Visual Abstraction

ICLR 2026Rejected
4.4
26

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

ICLR 2026Withdrawn
4.0
11

Inference-Time Scaling for Generalist Reward Modeling

ICLR 2026Rejected
4.0
20

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

ICLR 2026Rejected
3.5
21

Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks

ICLR 2026Withdrawn
6.4
25

Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations

NeurIPS 2025Poster
6.3
17

FormaRL: Enhancing Autoformalization with no Labeled Data

COLM 2025Poster
6.1
13

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

ICML 2025Poster
三作
5.8
19

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

ICLR 2025Rejected
5.5
34

Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization

COLM 2025Poster
三作
4.3
18

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models

ICLR 2025Withdrawn
3.7
5

Enabling Weak LLMs to Judge Response Reliability via Meta Ranking

ICLR 2025Rejected
三作
3.0
6

Enhancing Multi-Agent Learning in Real-World Interactive Environments through Process Reward Decomposition

ICLR 2025Rejected
三作
合作者 (20)