5 papers
Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning
Wentao Zhang, Mingkun Xu, Qi Zhang +6
Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves mode…
Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
Anupam Pani, Yanchao Yang
Eye gaze offers valuable cues about attention, short-term intent, and future actions, making it a powerful signal for modeling egocentric behavior. In this work, we propose a gaze-…
HiMaCon: Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
Ruizhe Liu, Pei Zhou, Qian Luo +4
Effective generalization in robotic manipulation requires representations that capture invariant patterns of interaction across environments and tasks. We present a self-supervised…
Mutual Information guided Visual Contrastive Learning
Hanyang Chen, Yanchao Yang
Representation learning methods utilizing the InfoNCE loss have demonstrated considerable capacity in reducing human annotation effort by training invariant neural feature extracto…
HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation
Li Sun, Jiefeng Wu, Feng Chen +2
Effective policy learning for robotic manipulation requires scene representations that selectively capture task-relevant environmental features. Current approaches typically employ…