A new theoretical study establishes minimax optimality for score-entropy discrete diffusion (SEDD), a discrete diffusion model used for generating natural language and graph-structured data. The resea…
Researchers introduced NeuroStrata, a connectivity-aware deep representation learning framework for EEG-based mental stress analysis, achieving a peak accuracy of 97.3% using the LAION-CLIP-ViT-L14 ba…
Researchers at arXiv introduced a hybrid model combining an N-dimensional Langevin equation with a neural-ordinary differential equation to forecast non-stationary electricity day-ahead prices, tested…
Researchers introduced TracingFlow, a simulation-free Flow Matching framework that generalizes to second-order dynamics by regressing acceleration fields with neural networks, providing an exact solut…
AstraZeneca researchers developed an LLM-as-a-Judge evaluation framework for ChatInvent, an agentic drug discovery assistant, achieving human-aligned scoring with a majority-vote agreement of 0.86 aft…
Researchers introduced RODE, a matrix-aware optimizer that decouples radial and directional updates, outperforming Muon variants across language modeling and image classification tasks. At 1.5B scale,…
Researchers introduced a neurosymbolic framework that uses large language models (LLMs) as adaptive proposal distributions to generate causal hypotheses for adverse pregnancy outcomes (APOs), scoring …
Researchers introduced Thermo-FL, a thermal-aware federated fine-tuning framework for large language models on edge devices, which uses device temperature to control local adapter training and sparse …
Researchers introduced aiXamine, a unified black-box platform that evaluates LLM trustworthiness across safety, security, and privacy, and found that stronger safety alignment increases over-refusal, …
Researchers propose COEC (Calibrated Orthogonal-Equivalence Compensation), a training-free framework that applies alternating left and right orthogonal rotations to retained weights in structured prun…
Researchers introduced Tydra, a hybrid Transformer-State Space Model (SSM) architecture for tabular in-context learning that interleaves attention and SSM layers. Across 30 OpenML datasets, Tydra redu…
Researchers introduced a reinforcement learning framework for Continuous-Time Jump Markov Decision Processes (CTJMDPs) with general discrete state spaces, addressing a gap in existing continuous-time …
Researchers introduced a Time-Aware transformer-based prediction model for Acute Exacerbation of Chronic Obstructive Pulmonary Disease (AECOPD) that uses only home ventilator respiratory data to enabl…
Researchers propose TH-GNN, a heterogeneous temporal graph neural network that detects LLM-agent shilling attacks on recommender systems by jointly modeling temporal, structural, and semantic signals.…
Researchers introduced Winder, a joint-embedding architecture that uses a phase-equivariant self-supervised objective to organize cardiac representations into phase-invariant and phase-rotating subspa…
Alibaba Group Holding Ltd. shares plunged 10% after the company priced a $10.2 billion share placement to fund its artificial intelligence investments.…
A new documentary 'Into the Woods' raises awareness about forests, and AI can aid forest visits, according to an analysis by Lance Eliot for Forbes. The film explores forests anew, and the piece discu…
President Trump said communities that reject data centers are "making a mistake," arguing the facilities create jobs and money and are not taking power from the grid, in an interview with Michael Cohe…
Indie game Replaced, developed by Sad Cat Studios, offers a pixel-art, sci-fi action platformer set in an alternate 1980s America, where players control an AI named R.E.A.C.H. escaping a dystopian cit…
Axios found that none of nearly 20 potential 2028 Democratic presidential contenders support Bernie Sanders' call to pause AI development, and only former Chicago Mayor Rahm Emanuel offered a critique…