13 posts published in the last hour
- 02:34Coding with the Enemy: Can Human Developers Detect AI Agent Sabotage?
- 02:34TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
- 02:33ThermoLLM: LLM-Based Multi-Zone HVAC Control with a Spatiotemporal Context
- 02:33Baidu Releases ERNIE 5.5 Flash Base: A 280B MoE Base Model With 14B Active Parameters
- 02:33StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance
- 02:32Current Muse Scores 47% on Meta’s Personal Superintelligence Index
- 02:32Hypnos: Learning Generalisable Representations of Sleep Physiology via Next-Token Prediction
- 02:04TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
- 02:04Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
- 02:03Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
- 02:03Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
- 02:03Crusoe sells troubled Wyoming data center project to Google
- 02:03LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning