Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2610.00025v1 Announce Type: cross Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a fro…
arXiv:2610.00024v1 Announce Type: cross Abstract: Across three vision-language model architectures (LLaVA-1.5-7B, Qwen2.5-VL-7B, InternVL3-8B), we rep…
arXiv:2610.00017v1 Announce Type: cross Abstract: We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lift…
arXiv:2610.00006v1 Announce Type: cross Abstract: Pretrained Vision Transformers encode whether two image patches belong to the same object. This IsSa…
arXiv:2610.00003v1 Announce Type: cross Abstract: Vision models pretrained for frame-level appearance often struggle to infer hidden physical properti…
arXiv:2607.15270v3 Announce Type: cross Abstract: The snake-in-the-box problem asks for a longest induced path in the hypercube graph $Q_n$. We find a…
arXiv:2610.02199v1 Announce Type: new Abstract: Full-parameter fine-tuning of large language models (LLMs) incurs substantial optimizer state memory o…
arXiv:2610.02198v1 Announce Type: new Abstract: Several state-of-the-art methods for online reinforcement learning in continuous control improve polic…
arXiv:2610.02195v1 Announce Type: new Abstract: The generalized Schr\"odinger bridge on a graph moves mass between two distributions while charging a…
arXiv:2610.02191v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical pr…
arXiv:2610.02190v1 Announce Type: new Abstract: Step-size selection remains a central challenge in large-scale neural network optimization; conservati…
arXiv:2610.02189v1 Announce Type: new Abstract: Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as trans…
arXiv:2610.02186v1 Announce Type: new Abstract: Molecular learning models are strongly shaped by their underlying representations. Yet standard sequen…
arXiv:2610.02185v1 Announce Type: new Abstract: Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurre…
arXiv:2610.02182v1 Announce Type: new Abstract: Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstraine…
arXiv:2610.02179v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) aims to combine the strengths of RL-trained teachers in a…
arXiv:2610.02175v1 Announce Type: new Abstract: Protein function annotation needs to know which predictions to distrust, not only what a model predict…
arXiv:2610.02173v1 Announce Type: new Abstract: Ablate a component of a language model, and other components often appear to adjust and compensate. Th…
arXiv:2610.02159v1 Announce Type: new Abstract: Intrinsic rewards are designed to guide exploration in reinforcement learning by assigning value to an…
arXiv:2610.02158v1 Announce Type: new Abstract: We consider the problem of sampling from Gibbs distributions on matrix spaces whose potential energies…