collaborators

14 papers

cs.AI2026

Multi-Head Attention Residuals

Cheng Luo, Zefan Cai, Junjie Hu

Transformers propagate information across depth through a single additive residual stream: every sublayer reads only the most recent state. Attention residuals relax this by lettin…

cs.CL2026

Test-Time Training with Next-Token Prediction

Xuan Ouyang, Zefan Cai, Junjie Hu

Next-token prediction is the self-supervised signal that trains language models, and every observed prompt token provides the same signal at test time. We study whether this signal…

cs.CV2026

MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models

Haozhe Zhao, Zefan Cai, Shuzheng Si +5

Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex m…

cs.CL2026

CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

Congmin Zheng, Jiachen Zhu, Jianghao Lin +6

Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…

cs.MA2026

GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering

Stockton Jenkins, Ramya Korlakai Vinayak, Junjie Hu

Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs…

cs.LG2026

Delta Attention Residuals

Cheng Luo, Zefan Cai, Junjie Hu

Attention Residuals replace standard additive residual connections with learned softmax attention over previous layer outputs, enabling selective cross-layer routing. However, stan…