The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

Introduce PerceptionRubrics, a rubric-based evaluation framework for addressing real-world brittleness of models using 1,038 images and over 12,000 instance-specific rubrics.

This study systematically evaluates Vision Mamba models for detecting AI-generated images, finding that while they show promise, their current strengths and limitations must be understood relative to…

The paper introduces DexVerse, a large-scale and modular benchmark for dexterous manipulation with 100 tasks, 3 robot arms, 6 hands, and configurable visual variations.

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

PRIMA is a framework that significantly improves 3D quadruped mesh recovery by integrating biological knowledge and a test-time adaptation strategy, achieving state-of-the-art results on diverse and c…

This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.

Places in the Wild introduces a massive, high-resolution RAW photograph dataset of 67,574 images captured in situ across 810 locations, providing unprecedented detail for ecologically valid vision res…

This paper presents ArtiTwinSplat, a framework for constructing articulated, photo-realistic digital twins of objects directly from RGB-D videos in real-world environments.

The paper presents AutoDex, a system that automatically collects real-world data for robust dexterous grasping, achieving a 4.8x throughput improvement over teleoperation and higher success rate than…

The paper reframes industrial visual sim-to-real transfer as a domain-gap problem categorized by the availability of explicit object geometry (CAD), arguing that the required prior evidence dictates t…

The paper introduces TeachObs, a comprehensive, human-validated benchmark for multimodal teaching observation, and evaluates frontier LLMs, finding that no single model consistently outperforms others…

RoboDream introduces an embodiment-centric world model that synthesizes photorealistic, physically feasible robot demonstrations by decoupling motion generation from environment synthesis, significant…

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.