17 papers
CoCo-IR: Contextual Composed Image Retrieval
Shengcao Cao, Tanmaya Shekhar Dabral, Zhongli Ding +6
Current instruction-based image retrieval systems are powerful but limited to single-turn interactions, failing to capture the iterative nature of complex, real-world visual search…
PPTArena: A Benchmark for PowerPoint Editing
Michael Ofengenden, Yunze Man, Ziqi Pang +2
We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions. Unlike benchmarks that rely on image-PDF…
A Two-Validator Web Interface for Structured Geometry Figure Annotation
Sabin-Codrut Badea, Adrian-Marius Dumitran
Annotating geometric figures from scanned documents has long been addressed by adapting generic annotation tools, tools not originally designed for such tasks, to use cases where t…
Vesta: A Generalist Embodied Reasoning Model
Johan Bjorck, Zhiqi Li, Yunze Man +29
Robots operating in open-world environments must seamlessly integrate localization, spatial reasoning, navigation, and long-horizon planning. While specialist models excel at indiv…
LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight
Yunze Man, Shihao Wang, Guowen Zhang +7
To act in the world, a model must name what it sees and know where it is in 3D. Today's vision-language models (VLMs) excel at open-ended 2D description and grounding, yet multi-ob…
BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
Qiusi Zhan, Hyeonjeong Ha, Rui Yang +7
Recent advances in Vision-Language Models (VLMs) have propelled embodied agents by enabling direct perception, reasoning, and planning task-oriented actions from visual inputs. How…