Yiming Yang
~Yiming_Yang1
24
论文总数
12.0
年均投稿
平均评分
接收情况16/24
会议分布
ICLR
15
NeurIPS
5
ICML
4
发表论文 (24 篇)
202514 篇
6
Optimizing Temperature for Language Models with Multi-Sample Inference
ICML 2025Poster
4
Regularized Langevin Dynamics for Combinatorial Optimization
ICML 2025Poster
4
Maximal Update Parametrization and Zero-Shot Hyperparameter Transfer for Fourier Neural Operators
ICML 2025Poster
4
Sampling-Enhanced Large Neighborhood Search for Solving Integer Linear Programs
ICLR 2025withdrawn
4
TFG-Flow: Training-free Guidance in Multimodal Generative Flow
ICLR 2025Poster
4
Lean-STaR: Learning to Interleave Thinking and Proving
ICLR 2025Spotlight
4
Enhancing Training Data Attribution with Representational Optimization
NeurIPS 2025Spotlight
4
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving
ICLR 2025Poster
4
Self-Play Preference Optimization for Language Model Alignment
ICLR 2025Poster
4
Large Language Models are Demonstration Pre-Selectors for Themselves
ICML 2025Poster
4
Large Language Models are Demonstration Pre-Selectors for Themselves
ICLR 2025Rejected
4
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
NeurIPS 2025Poster
5
Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
ICLR 2025Poster
4
Improve Vision Language Model Chain-of-thought Reasoning
ICLR 2025withdrawn
202410 篇
5
Learning to Branch with Offline Reinforcement Learning
ICLR 2024Rejected
3
DIFUSCO-LNS: Diffusion-Guided Large Neighbourhood Search for Integer Linear Programming
ICLR 2024Rejected
3
An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
NeurIPS 2024Rejected
4
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
NeurIPS 2024Poster
4
Learning Performance-Improving Code Edits
ICLR 2024Spotlight
4
Parsimonious Demonstrations and Fine-Tuning for Large Language Models
ICLR 2024withdrawn
4
SALMON: Self-Alignment with Instructable Reward Models
ICLR 2024Poster
3
Functional Interpolation for Relative Positions improves Long Context Transformers
ICLR 2024Poster
4
Aligning Large Multimodal Models with Factually Augmented RLHF
ICLR 2024Rejected
5
AutoMix: Automatically Mixing Language Models
NeurIPS 2024Poster