Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.39847v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing…
arXiv:2609.39843v1 Announce Type: cross Abstract: Density estimation is a fundamental problem in statistics and machine learning. In this work, we int…
arXiv:2609.39838v1 Announce Type: cross Abstract: Chain-of-thought monitoring as an approach for AI oversight and control is threatened by the possibi…
arXiv:2609.39836v1 Announce Type: cross Abstract: Contrastive vision-language models map visual and textual representations into a shared normalized e…
arXiv:2609.39829v1 Announce Type: cross Abstract: Modern machine learning depends heavily on massive datasets, but obtaining high-quality annotations…
arXiv:2609.39827v1 Announce Type: cross Abstract: Pre-pretraining (PPT) on synthetic non-natural language data improves token efficiency during langua…
arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is tr…
arXiv:2609.39788v1 Announce Type: cross Abstract: Latent communication enables multi-agent systems to exchange information directly in internal repres…
arXiv:2609.39768v1 Announce Type: cross Abstract: Certifying a deployed neural network raises decision problems that the verification literature has n…
arXiv:2609.39702v1 Announce Type: cross Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to t…
arXiv:2609.39701v1 Announce Type: cross Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and…
arXiv:2609.39687v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher t…
arXiv:2609.39684v1 Announce Type: cross Abstract: Privacy has become an increasingly important concern in the Document Analysis community, to the exte…
arXiv:2609.39679v1 Announce Type: cross Abstract: Audio deepfake detection (ADD) must remain effective when new spoofing attacks emerge after deployme…
arXiv:2609.39645v1 Announce Type: cross Abstract: Multi-agent collaboration lets large language models (LLMs) improve question answering through delib…
arXiv:2609.39635v1 Announce Type: cross Abstract: Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces witho…
arXiv:2609.39601v1 Announce Type: cross Abstract: Precise grounding matters. It specifies which object is the target and where that object is, even in…
arXiv:2609.39600v1 Announce Type: cross Abstract: Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency a…
arXiv:2609.39588v1 Announce Type: cross Abstract: We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introd…
arXiv:2609.39584v1 Announce Type: cross Abstract: Edge computing has emerged as a critical computing paradigm in modern distributed systems by migrati…