Orthogonal JEPA: Factorized Predictive States for Latent World Models
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabili…
Auditing Cross-Lingual Fairness in Language Model Watermarking
End-to-end Early Classification of Time Series in Non-Stationary Environments
Systematic Evaluation of TabPFN-TS for Zero-Shot Probabilistic Heat Load Forecasting in D…
Learning Early-to-Final Solution Consistency for MILP Acceleration
Designing Human-mediated AI Guidance: Ready Together for Personalized Family Emergency Pr…
Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Mult…
Auditing Recorded Predictive Lead Service-Line Classifications Against Physical Verificat…
Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
Spike-based Belief Propagation in Nonlinear Dynamical Systems
AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Textures
The impact of feature engineering and an optimisation framework for ocean colour machine …
Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in B…
TESTNAV: Pareto-Guided Search for Compositional Robustness Testing
Interpretable Feature Learning for RF Fingerprinting via Polar MKANs
EnvHarness: Awakening Static Worlds for Agent Learning
DIFFCZSL: Compositional Zero-Shot Learning Regularized by Diffusion Representations
Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning
Specification-delta-driven data governance: an empirical study of the «spec-delta» as the…
FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide D…
ADAPT: Physics-Aware Diffusion-based World Models for Adaptive Predictive Transferable HV…
Stopping and Routing LLM Judge Panels
SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
TT-net: Quantum Inspired Tensor Network Denoising in Conditional GANs
Coupled Optimal Transport with Landmark Constraints
Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crow…
Question-Guided Evidence Acquisition for Multimodal Visual Question Answering
SafeBranch: Branch-Pair Safety Alignment for Embodied Agents