10 posts published in the last hour
- 04:34VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
- 04:34FloMo: 3D Scene Flow as a World Action Model Intermediate for Learning from Human Video
- 04:33Molecular Prior Networks
- 04:33Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving
- 04:33Do Agentic Policies Need to Look at Every Step? Geometric Abstraction for Reasoning and Action
- 04:03GeoFaham: Domain-Specialized Multi-Agent Geospatial Analytics for Disaster Response
- 04:03Rethinking GA2Ms: performance and out-of-distribution generalisation
- 04:03Learned Smartphone ISP on Mobile GPUs: Mobile AI 2026 Challenge Report
- 04:03RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report
- 04:02LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation