arXiv:2609.11918v1 Announce Type: cross Abstract: Generalization under distribution shift remains a core challenge in modern machine learning, yet…
Author: script
Understanding Operator Attitudes Toward AI-Supported Decision Making in Maritime Operations
arXiv:2609.11805v1 Announce Type: cross Abstract: Maritime Autonomous Surface Ships (MASS) and AI- supported decision assistants are expected to transform…
Thinking with Looped Flows
arXiv:2609.11801v1 Announce Type: cross Abstract: Humans and machines often solve harder problems by spending more time on computation. In deep learning,…
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
arXiv:2609.11804v1 Announce Type: cross Abstract: Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens…
RetroThinker: Enabling Retrospective Thinking in Speech LLMs
arXiv:2609.11864v1 Announce Type: cross Abstract: Speech large language models (SpeechLLMs) offer reduced latency and retain paralinguistic nuances that…
Anthropic CEO outlines plan to slow AI development
Anthropic’s Dario Amodei and OpenAI’s Sam Altman seem to agree that it’s time to “pace the frontier.” What would that actually look like?
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
arXiv:2609.11842v1 Announce Type: cross Abstract: Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise…
AI News Brief Hourly Summary 2026-09-12 22h : 13 posts
13 posts published in the last hour 19:32ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI 19:32LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation 19:32Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English…
ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI
arXiv:2609.11737v1 Announce Type: cross Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how…
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
arXiv:2609.11739v1 Announce Type: cross Abstract: Large language model serving costs scale directly with output sequence length, yet standard preference…