1 citations · 1 across the 9 of their papers we have counts for
4 papers · 1 filter
From Copying to Composition: How Language Models Develop In-Context Learning
Minglai Yang, Xinyu Guo, Renxiong Wang +3
In-context learning (ICL) allows language models to adapt their behavior from instructions and demonstrations in a prompt, but accuracy alone does not reveal how contextual informa…
Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-Based RL
Minglai Yang, Xinyu Guo, Zhengliang Shi +8
Rubric-based reinforcement learning, in which an LLM judge scores responses against prompt-specific criteria, has become a standard way to post-train language models on tasks witho…
TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Tracking
Haonan Tang, Yanjun Chen, Lezhi Jiang +2
The TrackNet series has established a strong baseline for fast-moving small object tracking in sports. However, existing iterations face significant limitations: V1-V3 struggle wit…
AlignSAE: Concept-Aligned Sparse Autoencoders
Minglai Yang, Xinyu Guo, Zhengliang Shi +4
Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidde…