collaborators

6 papers

cs.LG2026

CODEBLOCK: Learning to Supervise Code at the Right Granularity

Zhijie Deng, Ling Li, Jinlong Pang +4

Supervised fine-tuning of code LLMs typically applies uniform cross-entropy loss to all response tokens, implicitly assuming that every token provides equally useful learning signa…

cs.LG2025

Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks

Xinjie Xu, Shuyu Cheng, Dongwei Xu +2

In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to practical deployment. In…

cs.RO2025

Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild

Derek Ming Siang Tan, Shailesh, Boyang Liu +8

To perform outdoor visual navigation and search, a robot may leverage satellite imagery to generate visual priors. This can help inform high-level search strategies, even when such…

cs.CV2025

Boosting Ray Search Procedure of Hard-label Attacks with Transfer-based Priors

Chen Ma, Xinjie Xu, Shuyu Cheng +1

One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach…

cs.CV2025

Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoring

Mingjie Xu, Andrew Estornell, Hongzheng Yang +4

The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding,…

cs.CL2025

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection

Zhijie Deng, Chris Yuhao Liu, Zirui Pang +5

Large Language Models (LLMs) have demonstrated strong capabilities in memorizing vast amounts of knowledge across diverse domains. However, the ability to selectively forget specif…