每天自动聚合 AI 领域最新动态
Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed fa...
Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapsh...
Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypern...
As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become cri...
Modern ASR models trained on heterogeneously annotated data treat transcription style (verbatim vs. intended) as an u...
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike st...
We present AutoIndex, a framework for learning representation programs: executable transformations that map raw docum...
The Traffic Assignment Problem is a fundamental but computationally expensive component of transportation planning. W...
Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic m...
This paper is a practitioner guide to graph-based workflow pathways for long-running, stateful, multi-step generative...
As LLM adoption becomes more widespread, there is a growing interest in detecting LLM-generated content, for example ...
Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components re...