collaborators

8 papers

cs.LG2026

HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures

Ziyun Qiao, Yue Min, Ruining Chen +1

Most data-mixing methods assume the corpus has already been partitioned into groups, and the choice of those groups determines what a mixer can express. Existing labels, including…

cs.LG2026

GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution

Yue Min, Ruining Chen, Yujun Li

Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critic…

cs.CV2026

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning

Yujun Li, Hongyuan Zhang, Yuan Yuan

Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether t…

cs.LG2026

GEM: Geometric Entropy Mixing for Optimal LLM Data Curation

Yue Min, Ziyun Qiao, Ruining Chen +1

LLM pre-training efficacy increasingly depends on data composition rather than sheer volume. Yet, optimal mixing is hindered by categorization flaws: human taxonomies suffer from o…

cs.LG2026

Can Language Models Discover Scaling Laws?

Haowei Lin, Haotian Ye, Wenzheng Feng +8

Discovering scaling laws for predicting model performance at scale is a fundamental and open-ended challenge, mostly reliant on slow, case specific human experimentation. To invest…

cs.LG2025

Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape

Tao Li, Zhengbao He, Yujun Li +3

Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tunin…