collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

CausalMix: Data Mixture as Causal Inference for Language Model Training

Zinan Tang, Yukun Zhang, Shaomian Zheng +6

In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely o…

cs.LG2026

On Representation Redundancy in Large-Scale Instruction Tuning Data Selection

Youwei Shu, Shaomian Zheng, Dingnan Jin +5

Data quality is a crucial factor in large language models training. While prior work has shown that models trained on smaller, high-quality datasets can outperform those trained on…

cs.LG2026

UniGeM: Unifying Data Mixing and Selection via Geometric Exploration and Mining

Changhao Wang, Yunfei Yu, Xinhao Yao +5

The scaling of Large Language Models (LLMs) is increasingly limited by data quality. Most methods handle data mixing and sample selection separately, which can break the structure…

cs.LG2025

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Gangwei Jiang, Caigao Jiang, Zhaoyi Li +5

Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced c…

cs.LG2025

M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance

Qingpei Guo, Kaiyou Song, Zipeng Feng +9

We present M2-omni, a cutting-edge, open-source omni-MLLM that achieves competitive performance to GPT-4o. M2-omni employs a unified multimodal sequence modeling framework, which e…