The Archive

RepICL: reusable in-context few-shot predictor learning across 1,218 text/image/audio encoder-dataset tasks via RepShiftBench.

Two-stage AI model predicts neoadjuvant therapy response in breast cancer by inferring transcriptome from histopathology across 10 cohorts.

ZeroMAG: zero-shot multimodal adapter for extending EEG foundation models to heterogeneous physiological signals without labels.

JOVE assigns heterogeneous LLMs to task graph subtasks with asynchronous verification to optimize latency and cost trade-offs.

Suno is branching out from the world of AI music, launching a new feature that generates spoken voices based on scripts or prompted descriptions. Speech is now available in public beta across Suno's web and mobile platforms, and allows you to simultaneously generate voiceovers and background music to accompany them. "Music will always be at the heart of Suno and what we build. At the same time, our vision has always extended to other forms of human expression," Suno chief product officer, Jack Brody, said in the announcement. "Today, we're expanding what's possible in Suno with Speech: the fi...

Data selection is critical for training large language models on massive and heterogeneous corpora. Meta-learning for Training-data Selection offers a principled alternative to heuristic scoring by learning data weights from a target validation objective, but existing methods face a trade-off between fine-grained valuation and transferability to unseen data. A natural solution is to replace per-sample weights with a selection network. However, we find that directly incorporating such a network into existing MTS objectives leads to unstable optimization and poor generalization, caused by weigh...

CDMD trains a tabular diffusion model jointly across heterogeneous datasets with mixed-type features, enabling cross-dataset generalization.

HO-FL: hybrid-order federated learning framework enabling memory-flexible training on heterogeneous edge devices via zeroth/first-order optimization splits.

SparseEngine: sparse-first inference engine for long-context LLM agents supporting heterogeneous KV-cache representations and sparse attention methods.

GEODE: foundation model for energy/radiation systems preserving heterogeneous scientific interfaces and native data representations.

Study compares chain-of-thought, pause tokens, and latent reasoning in GPTNeoX on multi-hop tasks; finds recurrent search mechanism.

Kafila distributes LLM inference across heterogeneous trusted commodity machines using device-aware partitioning to avoid bottlenecks.

Theoretical analysis closes gap in sample complexity bounds for two-sample testing on inhomogeneous random graph models.

Over-the-air computation for federated learning in wireless networks using waveform superposition for model aggregation.

FedHV applies closed-form hypervolume weighting to federated multi-objective optimization with heterogeneous data and communication constraints.

The funding, which comes from Third Point, Nvidia, and others, will fuel the company's massive AI data center buildout.

Theoretical analysis of transformer in-context learning under heterogeneous geometric data with minimax-optimal bounds and geometry adaptation.

RL applied to quantum network entanglement scheduling for simultaneous multipartite tasks.

Differentiable Gaussian Dynamics learns population-level collective behavior from aggregate counts via heterogeneous response propensities and recurrent feedback.

Heterogeneous graph memory architecture enables small LMs to execute tools reliably in stateful environments by learning from structural errors.

PRDO algorithm for private decentralized optimization uses recursive estimation and diffusion to handle heterogeneous data and privacy noise.

Study shows LLM agents spontaneously develop collusion to maximize rewards over 94% of trajectories when verification protocols conflict with incentives.

Nonparametric tangent vector field regression on Riemannian manifolds via parallel transport and kernel methods.

Federated deep clustering networks extend unsupervised learning to distributed private data settings with improved reliability.

RF-Fingerprinting multi-label classification under co-channel interference with heterogeneous transmission protocols.

Federated learning approach reduces communication overhead in sharded data parallelism for large-scale foundation model training on heterogeneous multi-GPU clusters.

Diffusion-GAN hybrid generates 3D geological microstructures from 2D images for materials science simulation.

FedQoS enables asynchronous federated learning for multimodal sensors in smart vehicles with heterogeneous network constraints.

Heterogeneous radiologist reporting practices confound chest X-ray report generation model evaluation via reference concordance metrics.

Sign-based variance reduction methods achieve optimal convergence rates in distributed heterogeneous settings via server-side gradient tracking.