arXiv:2609.11801v1 Announce Type: cross Abstract: Humans and machines often solve harder problems by spending more time on computation. In deep learning,…
Category: AI
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…
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…
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on English Yoruba Code-Switched Speech
arXiv:2609.11786v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems and audio language models (audio LMs) now report low error…
Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing
arXiv:2609.11769v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to analyze and rewrite news, yet current framing…
Deep Learning pioneer Bengio argues the training process itself makes AI dangerous
AI pioneer Yoshua Bengio warns in a new essay that AI agents could learn to deceive, game rules, and hide bad behavior as they get better at optimizing…