arXiv:2608.28828v1 Announce Type: cross Abstract: Representation learning begins when training changes the features that define similarity between data. A…
Tag: AI
FigMirror: Ground It, Code It, Plot It
arXiv:2608.28814v1 Announce Type: cross Abstract: Converting scientific figures into executable code has gained increasing attention, yet existing methods…
Text-Driven Artistic Staging: Pose, Lighting, and Camera References from Paintings
arXiv:2608.28823v1 Announce Type: cross Abstract: Artists coordinate human pose, illumination, and camera placement to convey narrative and emotion, but…
Delegating Before Learning: Where Generative AI Sits in Students’ Professional Communication
arXiv:2608.28837v1 Announce Type: cross Abstract: We conducted an interview study with twelve students on their use of generative AI in academic…
Peer Oversight in Collective Decision Making
arXiv:2608.28754v1 Announce Type: cross Abstract: This article introduces peer $k$-oversight, a property of sequential collective decision mechanisms…
Defending Wearable VLMs Against Private Attribute Inference
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user…
The reach of a verification tool decides its value: A controlled study of verification surface, artifact quality, and cost in AI coding agents
arXiv:2608.28795v1 Announce Type: cross Abstract: Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g.…
ASTRA – Agentic System for Ticket Resolution and Analysis
arXiv:2608.28790v1 Announce Type: cross Abstract: Technical operations teams resolve large volumes of incidents by synthesizing fragmented evidence from…
OpenAI’s Astra model is on the way — and very good at breaking into computer systems
OpenAI previewed the precautions it is taking as it prepares to release Astra, its newest, cyber-critical LLM.
RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction
arXiv:2608.28718v1 Announce Type: cross Abstract: Video world models increasingly serve as data engines, action planners, and simulators for embodied AI,…