13 posts published in the last hour
- 08:33Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
- 08:33Learning to Revise Reasoning with Segment-wise On-Policy Distillation
- 08:33Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves
- 08:32People really hate AI, so why can’t they get enough?
- 08:32Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
- 08:32Yandex Introduces Sona: A Single Generative Recommender That Replaces Entire Recommendation Cascade
- 08:32Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning
- 08:03DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
- 08:03A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns
- 08:03Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents
- 08:03Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
- 08:03Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
- 08:00AI News Brief Hourly Summary 2026-10-05 10h : 11 posts
