Mind the Phase: Effective Rank and Representation Health in Legged Locomotion
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Revi…
LoGAN: Multilingual Font Localization with Generative Agents
MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation
Foundation Models for Generalizable Semantic and Goal-Oriented Communication
CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Multimodal Resource-Exhaustion Attacks on Vision-Language Models via Joint Pixel-Prompt O…
Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supe…
TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Tempor…
Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM Pruning
AtomCite: Verification and Correction of Supplied Page-Level Citations in Multi-Page Docu…
ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Im…
HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions
Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing
MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation …
SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Lan…
EPC-3D-Diff: Equivariant Physics Consistent Conditional 3D Latent Diffusion for CBCT to C…
Support Topology and Gradient Mixing in Sinkhorn Layers
AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent Trajectories
Temporal Heterogeneous Graph Transformer for Credit Card Fraud Detection
BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents
Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corpora
TC-Next: Zero-Shot Multimodal Cyclone Forecasting
From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models
Constrained Online Learning with Noisy Constraint Values
AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering