Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2607.04171v4 Announce Type: replace-cross Abstract: How can richer training supervision improve robot control while keeping the deployed policy…
arXiv:2606.22346v2 Announce Type: replace-cross Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connec…
arXiv:2606.20811v2 Announce Type: replace-cross Abstract: We study the problem of system identification in heterogeneous settings, where different sys…
arXiv:2606.19998v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they…
arXiv:2606.17034v3 Announce Type: replace-cross Abstract: Post-hoc context erasing over the KV cache is challenging because a local edit has a global…
arXiv:2606.16138v2 Announce Type: replace-cross Abstract: Recovering dynamical systems from noisy observations is a recurring challenge across scienti…
arXiv:2606.13739v2 Announce Type: replace-cross Abstract: This paper examines trade-offs between AI safety and well-being relative to (i) one of the m…
arXiv:2606.09475v3 Announce Type: replace-cross Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadl…
arXiv:2606.08799v3 Announce Type: replace-cross Abstract: We study the generalization of ridge-regularized nonlinear least-squares models via on-avera…
arXiv:2606.05326v2 Announce Type: replace-cross Abstract: We study the dynamics of gradient descent in the Edge of Stability regime, where the learnin…
arXiv:2605.29307v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) search agents have shown strong promise on knowledge-intensive ta…
arXiv:2605.27696v3 Announce Type: replace-cross Abstract: Discrete visual tokenizers map images to ordered sequences of tokens, providing a natural re…
arXiv:2605.25765v2 Announce Type: replace-cross Abstract: Existing closed-form methods for concept unlearning in text-to-image diffusion models typica…
arXiv:2605.25629v3 Announce Type: replace-cross Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet exi…
arXiv:2605.20641v2 Announce Type: replace-cross Abstract: Inference optimization aims to minimize the latency and resource consumption of LLM inferenc…
arXiv:2605.14211v4 Announce Type: replace-cross Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely…
arXiv:2605.12890v2 Announce Type: replace-cross Abstract: The rapid advancement of large language models (LLMs) has made machine-generated text increa…
arXiv:2605.10851v2 Announce Type: replace-cross Abstract: We initiate the study of the Generalized Turing Test (GTT), a formal generalization of Turin…
arXiv:2605.10194v2 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) uses a model as its own teacher under privileged context,…
arXiv:2604.02543v2 Announce Type: replace-cross Abstract: As vision-language models (VLMs) are increasingly deployed in clinical decision support, mor…