activity
20242026
most citedUnderstanding Likelihood Over-optimisation in Direct Alignment Algorithms

1 citations · 1 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2026

FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution

Jianrong Ding, Jianyuan Zhong, Zhengyan Shi +1

Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult because the true impact of a n…

cs.LG2026

Learning to Solve Complex Problems via Dataset Decomposition

Wanru Zhao, Lucas Caccia, Zhengyan Shi +3

Curriculum learning is a class of training strategies that organizes the data being exposed to a model by difficulty, gradually from simpler to more complex examples. This research…

cs.CV2025

Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning

Kai Jiang, Zhengyan Shi, Dell Zhang +2

Class Incremental Learning (CIL) aims to continuously learn new categories while retaining the knowledge of old ones. Pre-trained models (PTMs) show promising capabilities in CIL.…

cs.CL2025

Optimising Language Models for Downstream Tasks: A Post-Training Perspective

Zhengyan Shi

Language models (LMs) have demonstrated remarkable capabilities in NLP, yet adapting them efficiently and robustly to specific tasks remains challenging. As their scale and complex…

cs.CL20241 cited

Understanding Likelihood Over-optimisation in Direct Alignment Algorithms

Zhengyan Shi, Sander Land, Acyr Locatelli +2

Direct Alignment Algorithms (DAAs), such as Direct Preference Optimisation (DPO) and Identity Preference Optimisation (IPO), have emerged as alternatives to online Reinforcement Le…

cs.CL2024

Understanding the Role of User Profile in the Personalization of Large Language Models

Bin Wu, Zhengyan Shi, Hossein A. Rahmani +2

Utilizing user profiles to personalize Large Language Models (LLMs) has been shown to enhance the performance on a wide range of tasks. However, the precise role of user profiles a…