Litian Gong — accepted AI-conference papers

2026

AutoFocus-IL: VLM-Based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations

Litian Gong, Fatemeh Bahrani, Yutai Zhou, Amin Banayeeanzade, Jiachen Li, Erdem Bıyık

ICRA 2026poster

We present AutoFocus-IL, a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rather than distractors and spurious correlations. Saliency regularization has emerged as a promising way to achie…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2026

ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models

Zhaoyang Li, Zhan Ling, Yuchen Zhou, Litian Gong, Erdem Biyik, Hao Su

CVPR 2026

Large Vision-Language Models (LVLMs) excel at captioning, visual question answering, and robotics by combining vision and language, yet they often miss obvious objects or hallucinate nonexistent ones in atypical scenes. We examine these failures through the lens of uncertainty, focusing on contextua

Cited by 0 Source ↗code ↗Scholar ↗