11 posts published in the last hour
- 05:33When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare
- 05:33ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI
- 05:33ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence
- 05:32Actionable Meta-Requirements for AI Robustness Auditing
- 05:32Meet Grok Voice 3.0: SpaceXAI Voice Agent Model Ranks #1 on Artificial Analysis
- 05:32Measuring the Inference Energy Efficiency of Open-Weight LLMs across Benchmarks, Reasoning Modes, and Hardware
- 05:03Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference
- 05:03Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions
- 05:03Controllable Diverse Sampling through Pullback Directions
- 05:03Harness^2: Recursive Agent Harnessing for an Open World
- 05:03ConicFlow: constrained Inference-time optimal control for flow matching models