Latest AI/ML News
8160 articles · arXiv cs.AI
arXiv:2610.00149v1 Announce Type: cross Abstract: Biological neurons achieve computational diversity through specialized types: tonic, bursting, adapt…
arXiv:2610.00148v1 Announce Type: cross Abstract: Open-ended artificial life systems must acquire diverse competencies from a single evolving genotype…
arXiv:2610.00132v1 Announce Type: cross Abstract: Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar s…
arXiv:2610.00126v1 Announce Type: cross Abstract: Agent developers increasingly compare prompts, tools, policies, and diagnosis algorithms through sim…
arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically rem…
arXiv:2610.00092v1 Announce Type: cross Abstract: Data agents over structured sources must fit database schema into the model's context window. Large…
arXiv:2610.00087v1 Announce Type: cross Abstract: The advancement of natural language processing (NLP) has expanded AI-based text classification in th…
arXiv:2610.00069v1 Announce Type: cross Abstract: Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to…
arXiv:2610.00065v1 Announce Type: cross Abstract: Legible planning is the creation of plans that best disambiguate their goals from a set of other can…
arXiv:2610.00063v1 Announce Type: cross Abstract: Instance-billed serverless platforms charge for CPU and memory over the lifetime of a warm instance,…
arXiv:2610.00054v1 Announce Type: cross Abstract: Reading an LLM judge's verdict from the logits of its first generated token is cheap, requires no ge…
arXiv:2610.00052v1 Announce Type: cross Abstract: We evaluate six language-model configurations on requests for six distinct random integers from 1-49…
arXiv:2610.00041v1 Announce Type: cross Abstract: Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child…
arXiv:2610.00008v1 Announce Type: cross Abstract: Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how c…
arXiv:2610.00007v1 Announce Type: cross Abstract: Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept loca…
arXiv:2610.02202v1 Announce Type: new Abstract: What makes great scientists great? Even as AI systems start to make progress on open problems, scienti…
arXiv:2610.02200v1 Announce Type: new Abstract: We show that multimodal models possess strong reasoning abilities and that an appropriate harness can…
arXiv:2610.02116v1 Announce Type: new Abstract: A comparative explainability framework is presented to audit DeBERTa-v3 under zero-shot classification…
arXiv:2610.02074v1 Announce Type: new Abstract: Privacy-preserving machine learning presents significant deployment challenges on the cloud for intell…
arXiv:2610.02072v1 Announce Type: new Abstract: The study of ceramic materials constitutes a cornerstone of archaeological research, yet the post-prod…