collaborators

6 papers

cs.CV2026

AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models

Yiran Qiao, Yiren Lu, Yunlai Zhou +4

3D Gaussian Splatting (3DGS) is increasingly recognized as a powerful paradigm for real-time, high-fidelity 3D reconstruction. However, its per-scene optimization pipeline limits s…

cs.CV2025

Counterfactual Visual Explanation via Causally-Guided Adversarial Steering

Yiran Qiao, Disheng Liu, Yiren Lu +3

Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction.…

cs.CV2025

When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?

Tuo Liang, Zhe Hu, Jing Li +8

Understanding humor-particularly when it involves complex, contradictory narratives that require comparative reasoning-remains a significant challenge for large vision-language mod…

cs.CV2025

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

Yiren Lu, Yunlai Zhou, Yiran Qiao +5

Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most…

cs.CV2025

CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Data

Disheng Liu, Yiran Qiao, Wuche Liu +5

True intelligence hinges on the ability to uncover and leverage hidden causal relations. Despite significant progress in AI and computer vision (CV), there remains a lack of benchm…

cs.LG2025

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Zirui He, Haiyan Zhao, Yiran Qiao +4

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper p…