Pengfei Liu
~Pengfei_Liu1
19
论文总数
9.5
年均投稿
平均评分
接收情况11/19
会议分布
ICLR
11
NeurIPS
3
COLM
3
ICML
2
发表论文 (19 篇)
202514 篇
4
On Evaluating LLM Alignment by Evaluating LLMs as Judges
NeurIPS 2025Poster
4
Progress or Regress? Self-Improvement Reversal in Post-training
ICLR 2025Poster
3
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
COLM 2025Poster
4
CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
ICLR 2025Rejected
4
Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
ICLR 2025Spotlight
4
Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale
ICLR 2025Rejected
3
Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
ICML 2025Poster
4
LIMO: Less is More for Reasoning
COLM 2025Poster
4
LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling
NeurIPS 2025Poster
4
BeHonest: Benchmarking Honesty in Large Language Models
ICLR 2025Rejected
5
OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance
ICML 2025Poster
5
TOMVALLEY: EVALUATING THE THEORY OF MIND REASONING OF LLMS IN REALISTIC SOCIAL CONTEXT
ICLR 2025withdrawn
4
FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
COLM 2025Poster
3
OMNIBAL: TOWARDS FAST INSTRUCT-TUNING FOR VISION-LANGUAGE MODELS VIA OMNIVERSE COMPUTATION BALANCE
ICLR 2025withdrawn
20245 篇
3
Alignment for Honesty
NeurIPS 2024Poster
5
Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
ICLR 2024withdrawn
4
Gauging Learnability in Supervised Fine-tuning Data
ICLR 2024withdrawn
3
Generative Judge for Evaluating Alignment
ICLR 2024Poster
3
FacTool: Factuality Detection in Generative AI - A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios
ICLR 2024Rejected