activity
20242026
most citedPreference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator

1 citations · 1 across the 5 of their papers we have counts for

collaborators

6 papers

cs.AI2026

PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models

Xuliang Wang, Yuetao Chen, Maochan Zhen +5

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerat…

cs.CL2026

PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards

Mukesh Ghimire, Aosong Feng, Liwen You +3

Current techniques for post-training Large Language Models (LLMs) rely either on costly human supervision or on external verifiers to boost performance on tasks such as mathematica…

cs.CL2025

PCMind-2.1-Kaiyuan-2B Technical Report

Kairong Luo, Zhenbo Sun, Xinyu Shi +9

The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relie…

cs.AI20251 cited

Preference Optimization via Contrastive Divergence: Your Reward Model is Secretly an NLL Estimator

Zhuotong Chen, Fang Liu, Xuan Zhu +2

Existing studies on preference optimization (PO) have centered on constructing pairwise preference data following simple heuristics, such as maximizing the margin between preferred…

cs.CL2024

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning

Jiayu Li, Xuan Zhu, Fang Liu +1

Fine-tuning large language models (LLMs) for specific tasks requires diverse, high-quality training data. However, obtaining sufficient relevant data remains a significant challeng…

cs.LG2024

Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization

Zhuotong Chen, Fang Liu, Jennifer Zhu +2

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However…