Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.40143v1 Announce Type: new Abstract: Compact regulatory DNA can free up space in vector payloads, reduce synthesis and assay burden, and ex…
arXiv:2609.40137v1 Announce Type: new Abstract: We present Game-Guided Skill Discovery (GGSD), a framework that uses self-play in games to discover mo…
arXiv:2609.40131v1 Announce Type: new Abstract: Rank-constrained tensor neural networks reduce the parameterization of high-order inputs, but they do…
arXiv:2609.40127v1 Announce Type: new Abstract: Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank…
arXiv:2609.40120v1 Announce Type: new Abstract: Motivated by the computational challenges of large-scale Cox regression, we study stochastic minimizat…
arXiv:2609.40117v1 Announce Type: new Abstract: Time-series forecasting models achieve strong benchmark performance but exhibit severe systematic bias…
arXiv:2609.40089v1 Announce Type: new Abstract: Continued pretraining enables language models to adapt to new domains and knowledge, but often at the…
arXiv:2609.40075v1 Announce Type: new Abstract: Partial Optimal Transport (POT) extends the classical optimal transport problem by relaxing the strict…
arXiv:2609.40070v1 Announce Type: new Abstract: When inference demand exceeds available compute capacity, model providers must decide which requests s…
arXiv:2609.40063v1 Announce Type: new Abstract: Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can l…
arXiv:2609.40047v1 Announce Type: new Abstract: Gromov-Wasserstein multidimensional scaling (GW-MDS) learns low-dimensional representations from relat…
arXiv:2609.40034v1 Announce Type: new Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing predict…
arXiv:2609.40030v1 Announce Type: new Abstract: Adapting a pretrained generative model to an arbitrary preference expressed as a utility function unde…
arXiv:2609.40003v1 Announce Type: new Abstract: World-model agents are usually evaluated in simulators that can wait for the policy; live games impose…
arXiv:2609.39995v1 Announce Type: new Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existin…
arXiv:2609.39967v1 Announce Type: new Abstract: Recursive reasoning models apply a small shared Transformer block many times to refine a latent state.…
arXiv:2609.39934v1 Announce Type: new Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the sele…
arXiv:2609.39929v1 Announce Type: new Abstract: Long-context failures of RoPE-based language models can arise from RoPE's intrinsic tradeoff between m…
arXiv:2609.39912v1 Announce Type: new Abstract: Parallel search may generate a correct answer that final-answer voting fails to select. We formulate t…
arXiv:2609.39911v1 Announce Type: new Abstract: Patient preference, defined as a patient's demonstrated willingness and capacity to adhere to clinical…