Latest AI/ML News
435 articles · 🧠 Research
arXiv:2608.02345v2 Announce Type: replace-cross Abstract: A/B testing remains the standard for rolling out new features in the technology industry. Ea…
arXiv:2608.01035v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end auto…
arXiv:2608.01014v2 Announce Type: replace-cross Abstract: Preference optimization improves mathematical reasoning in large language models (LLMs), but…
arXiv:2607.29516v2 Announce Type: replace-cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer…
arXiv:2607.28351v2 Announce Type: replace-cross Abstract: Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mec…
arXiv:2607.28125v2 Announce Type: replace-cross Abstract: Numerous unsupervised domain adaptation (UDA) algorithms exist, but for clinical practice, s…
arXiv:2607.28008v2 Announce Type: replace-cross Abstract: Representation engineering reads and steers capability directions in large language models,…
arXiv:2607.24519v3 Announce Type: replace-cross Abstract: EEG foundation-model gains may depend on cohort, montage, or probe design. We evaluated five…
arXiv:2607.23815v2 Announce Type: replace-cross Abstract: Large language models are increasingly used as semantic operators for filtering, extracting,…
arXiv:2607.23556v2 Announce Type: replace-cross Abstract: Temporal graphs are increasingly used to model dynamic systems in diverse domains such as so…
arXiv:2607.15740v2 Announce Type: replace-cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synt…
arXiv:2607.13124v2 Announce Type: replace-cross Abstract: Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated o…
arXiv:2607.08339v2 Announce Type: replace-cross Abstract: State-of-the-art code models achieve impressive performance, yet the extent to which they in…
arXiv:2607.00033v2 Announce Type: replace-cross Abstract: Dexterous robot manipulation can benefit from the abundance of human demonstrations, but tra…
arXiv:2606.28455v2 Announce Type: replace-cross Abstract: World models can predict future physical states, but prediction accuracy alone does not expl…
arXiv:2606.21497v2 Announce Type: replace-cross Abstract: Modern deep neural networks are trained using error backpropagation, which requires sequenti…
arXiv:2606.16316v2 Announce Type: replace-cross Abstract: Retrieving external knowledge is crucial for real-world tasks but remains difficult when que…
arXiv:2606.12838v2 Announce Type: replace-cross Abstract: Predicting single-cell transcriptional responses to genetic, chemical and cytokine perturbat…
arXiv:2606.08123v2 Announce Type: replace-cross Abstract: Model selection for safety-relevant visual recognition is often based on clean aggregate per…
arXiv:2606.04743v2 Announce Type: replace-cross Abstract: Agents are widely deployed as assistants over documents, tools, and code. However, they typi…