Disentangling Computation in Multi-Task Neural Networks with the Green's Operator
Research
Research News
New papers, breakthroughs and academic AI research
ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Delegation?
Research
Embedding Physical Reasoning into Diffusion-Based Shadow Generation Under the Sun and Sky
Research
Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling
Research
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Research
How Should Diffusion Language Models Edit Code?
Research
Social Choice Foundations for Simulation-Augmented Generation
Research
OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and Reasoning
Research
ContextAdapt: Evaluating Contextual Adaptation and Value Alignment in LLMs
Research
PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained Generation
Research
NinaXander: Feasibility and Limits of Composing Frozen Language Models Across Architecture Families via a Shared Latent Space
Research
Rethinking Generative Image Compression at Extremely Low Bitrates
Research