Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and Englis…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell…
Geometry-aware Latent Autoregressive Generative Model for PDEs in Complex Domains
A Machine Learning-Driven Solution for Denoising Inertial Confinement Fusion Images
The Alexander-Hirschowitz theorem for neurovarieties
Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Eart…
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
Wave Function Backpropagation with Explicit Temporal-Interval Dynamics
BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through I…
ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation
A Stable Aggregation Method for Quantum Federated Learning
Commit-first LLM judging inherits the judge's own errors
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-In…
Risk-Aware Decision-Making for Autonomous Overtaking: A World Model-Based Mixture-of-Expe…
Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction w…
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversatio…
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning
CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Lan…
Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents
CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for…
When Guardrails Look Effective: Construct Validity Failures in LLM Agent Commerce Evaluat…
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
Hidden State Poisoning Attacks against Mamba-based Language Models
MMAI Gym for Science: Training Liquid Foundation Models for Drug Discovery
Exploring Collaboration between a language and a non-language agent
SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation p…
Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers
A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clo…