Latest AI/ML News
9894 articles · arXiv cs.LG
arXiv:2609.38205v1 Announce Type: cross Abstract: System prompts are the primary lever practitioners use to control language model behavior, yet what…
arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overla…
arXiv:2609.40361v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are rapidly advancing clinical diagnosis, yet their adaptatio…
arXiv:2609.40360v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large…
arXiv:2609.40359v1 Announce Type: new Abstract: We find that major reported improvements in decoding words from non-invasive brain recordings are larg…
arXiv:2609.40335v1 Announce Type: new Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preservi…
arXiv:2609.40316v1 Announce Type: new Abstract: Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recu…
arXiv:2609.40312v1 Announce Type: new Abstract: Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error sourc…
arXiv:2609.40292v1 Announce Type: new Abstract: How is computation organized and reused across tasks and time in a trained recurrent network? Most ana…
arXiv:2609.40287v1 Announce Type: new Abstract: Physics-constrained generative models aim to generate physical fields that match a target distribution…
arXiv:2609.40284v1 Announce Type: new Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer…
arXiv:2609.40265v1 Announce Type: new Abstract: Real-world time-series applications increasingly require models that can handle time series forecastin…
arXiv:2609.40235v1 Announce Type: new Abstract: Continuous diffusion language models generate all tokens in parallel, yet high-quality generation can…
arXiv:2609.40221v1 Announce Type: new Abstract: Training LLM agents with reinforcement learning (RL) is bottlenecked by environments, which must provi…
arXiv:2609.40193v1 Announce Type: new Abstract: We establish near-linear accuracy bounds for the classical Moreau--Yosida unadjusted Langevin algorith…
arXiv:2609.40190v1 Announce Type: new Abstract: Sampling several answers and keeping the one a verifier scores highest is one of the simplest ways to…
arXiv:2609.40170v1 Announce Type: new Abstract: MANETs enable flexible infrastructure-less wireless connectivity in dynamic and resource-constrained e…
arXiv:2609.40149v1 Announce Type: new Abstract: Policy regularization in offline reinforcement learning balances policy improvement against reliance o…
arXiv:2609.40148v1 Announce Type: new Abstract: Power-law learning curves are often treated as fixed properties of a model and its data, although lear…
arXiv:2609.40147v1 Announce Type: new Abstract: We establish an exponential iteration lower bound in the number of states for Howard's policy iteratio…