21 papers
Sample-Efficient Learning from Agent Experience
Chenhui Gou, Haoqin Tu, Yunhao Fang +2
Real-world agent learning is often constrained by costly environment interactions, such as running time-consuming experiments or obtaining human feedback. In-context learning offer…
Explain Before You Answer: A Survey on Compositional Visual Reasoning
Fucai Ke, Joy Hsu, Zhixi Cai +10
Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground inte…
ARIS: Agentic and Relationship Intelligence System for Social Robots
Stavya Datta, Fucai Ke, Leimin Tian +1
Foundational models have advanced social robotics, enabling richer perception and communicative interaction with users. However, current systems still struggle with multi-turn enga…
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
Sukai Huang, Chenyuan Zhang, Fucai Ke +4
Instruction granularity is an important yet poorly controlled variable in language-guided embodied AI. Existing benchmarks typically pair each task with a single static instruction…
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
Saikat Dutta, Biplab Banerjee, Hamid Rezatofighi
Open-Vocabulary Semantic Segmentation (OVSS) assigns pixel-level labels from an open set of text-defined categories, demanding reliable generalization to unseen classes at inferenc…
Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding
Abdelrahman Shaker, Muhammad Maaz, Chenhui Gou +3
Video understanding models often struggle with high computational requirements, extensive parameter counts, and slow inference speed, making them inefficient for practical use. To…