11 posts were published in the last hour
- 3:31 : PURe: A Plug-and-Play Product-Unit Residual Module for Vision Networks
- 3:31 : Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription
- 3:31 : Learning to Walk With Less: A Dyna-Style Approach to Quadrupedal Locomotion
- 3:31 : A primer on optimal transport for causal inference with observational data
- 3:31 : Minimal Ingredients for Reward Assignment from Expert Demonstrations
- 3:2 : DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
- 3:2 : Towards a Theoretical Understanding of Two Tower Recommendation Models
- 3:2 : Harnessing the Synergy between LLM Agents and Knowledge Graphs for Urban Socioeconomic Prediction
- 3:2 : Contextual Information Policy Optimization for Search Agents
- 3:2 : Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
- 3:0 : AI News Brief Hourly Summary 2026-08-11 05h : 11 posts