Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2506.20040v4 Announce Type: replace Abstract: Interpreting language models remains challenging due to the existence of residual stream, which li…
arXiv:2504.09192v5 Announce Type: replace Abstract: The primary goal of my Ph.D. study is to develop provably efficient and practical algorithms for d…
arXiv:2504.06209v2 Announce Type: replace Abstract: Predicting future observations plays a central role in machine learning, biology, economics, and m…
arXiv:2503.19081v2 Announce Type: replace Abstract: Scientific foundation models (SciFMs) aim to learn generalizable representations of physical syste…
arXiv:2410.20317v2 Announce Type: replace Abstract: Molecular dynamics (MD) simulations are a principled but computationally expensive approach for st…
arXiv:2410.02159v3 Announce Type: replace Abstract: Language models (LMs) can "memorize" information, i.e., encode training data in their weights in s…
arXiv:2408.02689v3 Announce Type: replace Abstract: Traffic forecasting uses recent measurements by sensors installed at chosen locations to forecast…
arXiv:2406.13547v2 Announce Type: replace Abstract: ModSecurity is widely recognized as the standard open-source Web Application Firewall (WAF), maint…
arXiv:2406.02447v5 Announce Type: replace Abstract: Federated Learning (FL) aims at unburdening the training of deep models by distributing computatio…
arXiv:2302.02006v2 Announce Type: replace Abstract: Major Internet advertising platforms offer budget pacing tools as a standard service for advertise…
arXiv:2609.40347v1 Announce Type: cross Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-tempo…
arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires…
arXiv:2609.40305v1 Announce Type: cross Abstract: Improving text-to-image models has traditionally relied on increasing model size or the number of de…
arXiv:2609.40295v1 Announce Type: cross Abstract: Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying…
arXiv:2609.40245v1 Announce Type: cross Abstract: Robot navigation in dynamic, human-centered environments requires socially-compliant decisions groun…
arXiv:2609.40236v1 Announce Type: cross Abstract: Converting free-text radiology reports into structured labels supports cohort building, quality assu…
arXiv:2609.40165v1 Announce Type: cross Abstract: We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrain…
arXiv:2609.40159v1 Announce Type: cross Abstract: Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering appl…
arXiv:2609.40140v1 Announce Type: cross Abstract: Extreme heat is where urban adaptation needs kilometer-scale data the most, but the simulations trai…
arXiv:2609.40093v1 Announce Type: cross Abstract: Expert parallelism (EP) enables inference of large Mixture-of-Experts (MoE) models by placing their…