InstanceBench: Diagnosing Referential Reasoning and Target Identity in Referring Expression Segmentation
Research
Research News
New papers, breakthroughs and academic AI research
The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers
Research
Gaussian Material Fields for Volumetric Multi-Energy CT Decomposition
Research
SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language Models
Research
SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision Models
Research
Spatial Latent Reasoning for Embodied Reference Understanding
Research
RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary Detection
Research
TERRA: Learning Transportable Latent Actions through Temporal Effect Representation and Relational Alignment
Research
LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object Detection
Research
It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank
Research
OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning
Research
UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
Research