activity
20242026
collaborators

8 papers

cs.CV2026

WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation

Rafi Ibn Sultan, Hui Zhu, Xiangyu Zhou +4

Ensuring accessible pedestrian navigation requires reasoning about both semantic and spatial aspects of complex urban scenes, a challenge that existing Large Vision-Language Models…

cs.LG2025

Not All Tokens Are Meant to Be Forgotten

Xiangyu Zhou, Yao Qiang, Saleh Zare Zade +3

Large Language Models (LLMs), pre-trained on massive text corpora, exhibit remarkable human-level language understanding, reasoning, and decision-making abilities. However, they te…

cs.CV2025

GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

Rafi Ibn Sultan, Chengyin Li, Hui Zhu +3

In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobili…

cs.LG2025

Learning to Poison Large Language Models for Downstream Manipulation

Xiangyu Zhou, Yao Qiang, Saleh Zare Zade +4

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilit…

cs.LG2025

Automatic Calibration for Membership Inference Attack on Large Language Models

Saleh Zare Zade, Yao Qiang, Xiangyu Zhou +4

Membership Inference Attacks (MIAs) have recently been employed to determine whether a specific text was part of the pre-training data of Large Language Models (LLMs). However, exi…

cs.CV2025

Interpretability-Aware Vision Transformer

Yao Qiang, Chengyin Li, Prashant Khanduri +1

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance.…