collaborators

5 papers

cs.LG2025

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models

Hyunin Lee, Yong Zhang, Hoang Vu Nguyen +8

Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance…

cs.LG2025

Reinforcement Learning for Flow-Matching Policies

Samuel Pfrommer, Yixiao Huang, Somayeh Sojoudi

Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and text…

cs.LG2025

Spooky Action at a Distance: Normalization Layers Enable Side-Channel Spatial Communication

Samuel Pfrommer, George Ma, Yixiao Huang +1

This work shows that normalization layers can facilitate a surprising degree of communication across the spatial dimensions of an input tensor. We study a toy localization task wit…

cs.CL2025

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

Yixiao Huang, Hanlin Zhu, Tianyu Guo +5

Large language models (LLMs) can acquire new knowledge through fine-tuning, but this process exhibits a puzzling duality: models can generalize remarkably from new facts, yet are a…

cs.LG2025

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Ziheng Cheng, Yixiao Huang, Hui Xu +4

Text-to-Image (T2I) models have achieved remarkable success in generating visual content from text inputs. Although multiple safety alignment strategies have been proposed to preve…