Why quantum computing may be the White Houses new AI
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
DiScoFormer: One transformer for density and score, across distributions
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Sce…
One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel L…
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
The Fundamental Limits of Valid Transport Map Estimation
StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors
Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Scalar Representations of Neural Network Training Dynamics
Residual-Guided Expert Specialization for Incomplete Multimodal Learning
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse T…
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes
Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforc…
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learni…
Import AI 463: Self-improving robots; a 10k Chinese GPU cluster; and an elegiac essay for…
Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Gra…
Grounding LLM Reasoning under Incomplete Graph Evidence
From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic V…
The Many-Body Problem of the Data Centre
SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation
Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents
A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-En…
Physically-Constrained Harmonic Separation for Robust Heart and Respiratory Rate Estimati…
FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Genera…
Automating the Design of Embodied AgentArchitectures