Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response …
Explorar
Noticias de IA
21271 elementos — filtrados, clasificados y sin duplicados
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Work…
Large genome models used to design new viruses
Learning When to Trust via Selective Context Preference Optimization
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Scalable estimation of VARMA models
Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents
UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression
On-Policy Self-Distillation without Any Supervision
QuanTiMedAI: Quantum-Enhanced Time-Series Model guided by Agentic AI for Cardiac Arrest M…
The Tamed Subgradient Unadjusted Langevin Algorithm beyond Convexity
TS-RAG: Retrieval Augmented Generation for Time Series Forecasting
Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Lik…
Why health AI interfaces must adapt to user expertise
Handling Missing Data in Probabilistic Regression Trees
HOPE: Hand-Object Pressure Estimation from Monocular Videos
SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models
Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Co…
Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Struc…
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
Learning visual representations for compositional analysis of artworks and photographs
Mind the Gaps: Mixture-of-Minds for Human Simulation
From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architectur…
Does Latent Context Help? A Controlled Evaluation of Inverse Reinforcement Learning in Ar…
Domain-Grounded Candidate Selection for Agentic Image Editing: A Shadow Removal Case
BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emot…
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
TRACE: Learned Proprioceptive Odometry for Legged Robots under Unreliable Contact Conditi…