4 papers
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
Chenhao Dang, Jing Ma, Mingjie Liao
The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-training. Online Data Mixing (O…
AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining
Jing Ma, Chenhao Dang, Mingjie Liao
Optimizing pretraining data composition is pivotal for LLM generalization. While dynamic mixing outperforms static strategies by capturing evolving training dynamics, current metho…
NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results
Xin Li, Jiachao Gong, Xijun Wang +75
This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-…
Breaking the Adversarial Robustness-Performance Trade-off in Text Classification via Manifold Purification
Chenhao Dang, Jing Ma
A persistent challenge in text classification (TC) is that enhancing model robustness against adversarial attacks typically degrades performance on clean data. We argue that this c…