Latest AI/ML News
2784 articles · arXiv cs.CL
arXiv:2609.11768v1 Announce Type: cross Abstract: Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledg…
arXiv:2609.11752v1 Announce Type: cross Abstract: For industrial content risk control, the real deployment constraint is not average accuracy but how…
arXiv:2609.11716v1 Announce Type: cross Abstract: Post-training quantization compresses large language models (LLMs) by storing their weights at reduc…
arXiv:2609.11390v1 Announce Type: cross Abstract: State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire…
arXiv:2609.11326v1 Announce Type: cross Abstract: The undecidability of a program's static semantic properties is governed by Rice's theorem. Self-mod…
arXiv:2609.11274v1 Announce Type: cross Abstract: Recently, large language model (LLM) based ASR models have achieved significant progress, yet they g…
arXiv:2609.11261v1 Announce Type: cross Abstract: Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business…
arXiv:2609.11253v1 Announce Type: cross Abstract: Erasing concept-specific information from representations has been proven useful for mitigating bias…
arXiv:2609.11231v1 Announce Type: cross Abstract: This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating ro…
arXiv:2609.11209v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applica…
arXiv:2609.11198v1 Announce Type: cross Abstract: Generative AI and the practice of "vibe coding" are changing how archaeologists carry out computatio…
arXiv:2609.11163v1 Announce Type: cross Abstract: Structured pruning of large language models (LLMs) offers hardware-efficient compression, yet existi…
arXiv:2609.11146v1 Announce Type: cross Abstract: AI-generated text is flowing back into the training corpora of the next generation of models. Recurs…
arXiv:2609.11144v1 Announce Type: cross Abstract: Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it…
arXiv:2609.11127v1 Announce Type: cross Abstract: This paper introduces the complete technical solution for the KuaiRP series of role-playing models.…
arXiv:2609.11085v1 Announce Type: cross Abstract: Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers a…
arXiv:2609.11063v1 Announce Type: cross Abstract: Large language models learn similar behaviours, yet it remains unclear what structure they share or…
arXiv:2609.11022v1 Announce Type: cross Abstract: A model first sees an image from one physical measurement experiment, such as how far a block coaste…
arXiv:2609.10935v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) try to determine whether a specific record was used to train a m…
arXiv:2609.10883v1 Announce Type: cross Abstract: Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore…