The Archive

The largest grid operator in the U.S. says it will cut power to large data centers to prevent blackouts starting next year.

Multi-agent LLM framework with Bayesian networks for uncertainty quantification in actuarial risk modeling and regulatory compliance.

Test-time adaptation method for LLM-based traffic forecasting on evolving sensor networks with dynamic graph structure.

Empirical analysis of attention patterns in LLM-based automated program repair to explain inconsistent patch generation performance.

kiloVAD: ultra-compact speech activity detection model using structured pruning and quantization-aware training for edge deployment.

LLM-based AI system automates discovery of quantum error-correcting codes for fault-tolerant quantum computing by iteratively optimizing code structure and decoding.

DRIFT hybrid forecasting framework combines direct and recursive action-conditioned models for ICU physiological time-series prediction with treatment interventions.

Shieldstral 3B multimodal safety classifier achieves SOTA on content moderation via unified QA framework, matching models 7x larger on text safety benchmarks.

OpenAI's Akshay Nathan details ChatGPT Work product strategy: Sites, memory, subagents, finance, no-code tools scaling from 0 to 10M users.

HiSkill hierarchical skill graph framework organizes LLM agent trajectories into structured graphs linking high-level skills to atomic operations for long-horizon tasks.

AngelSpec unified training framework adaptively switches between multi-token prediction and block-parallel diffusion for speculative LLM decoding across heterogeneous workloads.

Online learning algorithms for distributed constraint optimization applied to large-scale satellite scheduling via decomposition and iterative pricing methods.

Agentic workflow automates translation of quantum protocols to hardware experiments on Pasqal neutral-atom QPUs with researcher-in-the-loop validation.

Zero-shot sEMG movement classification via Compositional Prototype Interpolation and Synthetic Adaptation for prosthesis control without re-training per combination.

Joint agent-speculator RL aligns next tool-call prediction with deployed agent behavior by unifying speculator and agent in single model, reducing latency.

Evaluation of adversarial robustness in five Arabic language models under multi-granularity attacks exposes security vulnerabilities in non-English LLMs.

Physics-informed spectral deep operator network (SpectONet) for Euler-Bernoulli beam vibration using nonuniform sensor placement.

MC-ALFCG algorithm for stochastic nonconvex composite optimization over Markovian-sampled gradients with variance reduction.

WorkSurface-Bench evaluates enterprise agents on multi-source knowledge routing across documents, tables, and graphs with 1,151 tasks.

WALoMA: multitask 6G wireless foundation model using masked autoencoders to reduce dependence on labeled channel data.

Rule-based Visiting Circulation model for trip destination prediction in unseen metropolitan areas using behavioral patterns.

Method to detect CSAM-generating LoRAs from weight fingerprints (singular vectors) without generating outputs, enabling safer moderation.

Concept bottleneck model for echocardiography shows loss invariance determines learned concepts; validates volume grounding without residual paths.

Analysis of how image quality degradation (noise, darkness) affects neural network robustness in autonomous driving perception systems.

Since launching last year, the startup today has more than 8 million people using the open-source or hosted version of its models, and now generates annual recurring revenue of $21 million.

Multi-UAV cooperative control framework combining shared voxel-map occupancy model with multi-agent Soft Actor-Critic decentralized policy.

LLM-generated sustainability-framed recommendation explanations as behavioral nudges; tests how different framings influence user choice.

Dynamic Constraint Learning framework learns local surrogates for constrained optimization when constraint functions are unknown.

HYSET evaluates tool sets jointly for LLM agents via hyperedge prediction, improving on sequential tool retrieval.