Latest papers from arXiv — updated daily across cs.AI, cs.LG, cs.CL, and cs.CV.
200 papers — updated daily from arXiv
Pavel Iakovets, Liyanapathiranage Sudeepika Wajirakumari Samarathunga, Martin Thomas Horsch +1 more
arXiv:2607.01306v1 Announce Type: new Abstract: Counterfactual explanations explain machine learning predictions by identifying minimal input changes that would alter a model's decision. Although many existing methods…
Holger R. Roth, Ziyue Xu, Chester Chen +3 more
arXiv:2607.01366v1 Announce Type: new Abstract: Federated learning (FL) research often depends on many small but consequential algorithmic choices: optimizer variants, server aggregation rules, local training…
Aryuemaan Kumar Chowdhury, Afreen Shaik, Yaparla Bhargavi +1 more
arXiv:2607.01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family…
Yongjian Tang, Ezgi Sarikayak, Doruk Tuncel +2 more
arXiv:2607.01425v1 Announce Type: new Abstract: Understanding large, complex codebases, especially those with obfuscated structures and incomplete documentation, remains a significant challenge. Existing code…
Qian Chen, Chengyuan Liu, Xin Yu
arXiv:2607.01426v1 Announce Type: new Abstract: Autonomous customer-service agents are shifting from conversational interfaces toward operational execution roles: they retrieve firm records, apply service policies, and …
Samuel Schapiro, Core Francisco Park, Felix Sosa +1 more
arXiv:2607.01433v1 Announce Type: new Abstract: Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended questions, in what…
Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge +1 more
arXiv:2607.01436v1 Announce Type: new Abstract: Diffusion language models, which generate text by denoising a token canvas bidirectionally instead of emitting tokens left to right, have become competitive with…
Karthikeya Aditya Vissa, Sankalp Mane, Ananya Mantravadi +2 more
arXiv:2607.01465v1 Announce Type: new Abstract: Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right …
Ananya Mantravadi, Harshit Rajgarhia, Prasanna Desikan +1 more
arXiv:2607.01470v1 Announce Type: new Abstract: Clinical protocol-execution tasks -- checking a lab value, applying a threshold, placing a correctly structured FHIR order -- are natural candidates for RL from world…
Ye Liu, Srijan Bansal, Bo Pang +6 more
arXiv:2607.01480v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the …
Jiacheng Miao, Jonathan K Pritchard, James Zou
arXiv:2607.01507v1 Announce Type: new Abstract: Empirical research rarely admits a unique analysis. Different analytical choices can lead to different conclusions from the same data, yet these hidden forking paths are…
Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno +1 more
arXiv:2607.01510v1 Announce Type: new Abstract: AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should…