activity
20242026
collaborators

7 papers

cs.CV2026

DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Models

Xuanhua Yin, Chuanzhi Xu, Shunqi Mao +2

Few-step text-to-image models increasingly replace slower generators, yet acceleration can silently change distributions over unspecified attributes even when individual outputs re…

cs.CV2026

Ctrl-Z Sampling: Scaling Diffusion Sampling with Controlled Random Zigzag Explorations

Shunqi Mao, Wei Guo, Chaoyi Zhang +3

Diffusion models generate conditional samples by progressively denoising Gaussian noise, yet the denoising trajectory can stall at visually plausible but low-quality outcomes with…

cs.CV2026

Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding

Shunqi Mao, Chaoyi Zhang, Weidong Cai

Existing vision-language models (VLMs) often suffer from visual hallucination, where the generated responses contain inaccuracies that are not grounded in the visual input. Efforts…

cs.CY2026

LLM Nepotism in Organizational Governance

Shunqi Mao, Wei Guo, Dingxin Zhang +2

Large language models are increasingly used to support organizational decisions from hiring to governance, raising fairness concerns in AI-assisted evaluation. Prior work has focus…

cs.CV2025

Multimodal Causal Reasoning Benchmark: Challenging Vision Large Language Models to Discern Causal Links Across Modalities

Zhiyuan Li, Heng Wang, Dongnan Liu +4

Multimodal Large Language Models (MLLMs) have showcased exceptional Chain-of-Thought (CoT) reasoning ability in complex textual inference tasks including causal reasoning. However,…

cs.CV2024

Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Module

Dingxin Zhang, Jianhui Yu, Tengfei Xue +3

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model…