Yi Zhang

Field-level prediction of mid-plane stress tensor fields in concrete target penetration: a cross-velocity graph neural operator surrogate

Wenpu Du, Peng Zhou, Yunlong Xia, et al.

A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient Dynamics

Wenpu Du, Peng Zhou, Yunlong Xia, et al.

Threshold Structure of Optimal Policies in Restart POMDPs

Konstantin Avrachenkov, Alexey Piunovskiy, Yi Zhang

Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling

Yucheng Li, Huiqiang Jiang, Yang Xu, et al.

Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action

Yi Zhang, Yinda Chen, Che Liu, et al.

Supplement Generation Training for Enhancing Agentic Task Performance

Young Min Cho, Daniele Bonadiman, Divya Bhargavi, et al.

Arbitration Failure, Not Perceptual Blindness: How Vision-Language Models Resolve Visual-Linguistic Conflicts

Farhad Nooralahzadeh, Omid Rohanian, Yi Zhang, et al.

UGID: Unified Graph Isomorphism for Debiasing Large Language Models

Zikang Ding, Junchi Yao, Junhao Li, et al.

This paper addresses social biases embedded in large language models by proposing UGID, a method that treats the model's internal structure as a graph and forces it to process similar inputs (that differ only in sensitive attributes like gender or race) in the same way. The approach works by constraining both the attention mechanisms and hidden representations in bias-sensitive areas of the model, while using special techniques to prevent the model from losing its core knowledge and safety features.