10 posts published in the last hour
- 07:33PILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrieval
- 07:32StateTape: Action-Conditioned Evidence Lifecycle Modeling for Long-Horizon Coding Agents
- 07:32HyperZip: Efficient Data Compression through Personalized Diffusion LLMs with Hypernetworks
- 07:32Towards an AI Software Factory for Data Systems
- 07:32ThuRunel: Dynamic Decoupling for Structured Advisory Dialogue
- 07:03Illusory Truth or Mere Exposure? Model-Dependent Repetition Effects in LLM-Based Social Media Simulations
- 07:03Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
- 07:03From Surfaces to Volumes: Registered Geometry for Protein Representation Learning
- 07:03CheatBench: Measuring Reward Gaming in AI Agents
- 07:03OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
