arXiv cs.AIResearchMetonymic Circuits for Abstract Concept Grounding in Vision Transformers (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchAMBER: Training Long-Horizon Web Agents through Append-Only Memory (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchWhen better traffic forecasts fail to improve signal control: a layered diagnostic study of forecast-to-decision value (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchWhen to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchFluidPD: In-Place Elasticity for SLO-Aware Prefill-Decode Disaggregated LLM Serving (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchEnergy-Conditioned Noise Schedule and Whitening for Spectral Diffusion (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchSPECTRUM: Proximal Spectral Modulation for Looped Self-Distillation (opens in a new tab)arXiv cs.AI · Oct 7, 2026
arXiv cs.AIResearchPrinciples that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction (opens in a new tab)arXiv cs.AI · Oct 7, 2026