L1 Augmented Attention as an Improved Vector Similarity Metric
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasonin…
Do Maps Still Matter for Machines: Revisiting the Role of Choropleth Maps in Foundation M…
Harness Engineering for LLM-Driven GPU Kernel Generation
Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting
A Geometric Perspective on Stabilizing Value Conflict Resolution
MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors
PRIME: Plasticity Recovery in Multi-Agent Environments for UAV-Assisted Emergency Communi…
Chemical filters for ultra-high-throughput materials screening and generation
Locality-Aware Density Control for Efficient Gaussian-based Image Representation
Exploratory and Assimilating Reflection: Reflective Recall Cycle for Long-term Memory
Entanglement geometry separates circuit cutting, classical hardness, and trainability
ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Mani…
A Hardware-oriented Approach for Efficient Bayesian Inference Computation and Deployment
Measuring and Improving Complex-Atomic Answer Consistency in Endoscopic VQA
I wanted it to feel more personal: Customization of social AI as AI individualism in prac…
PRiSM: Prototype Regularization for Few-Shot VLMs
FF-ProCams: Feed-Forward Gaussian Splatting for Projector-Camera System
Toward Optimal Adenovirus Detection Using YOLO26
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive P…
CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and …
From Sign Language Generation to Humanoid Execution: Vision-Language Guided Retargeting w…
Safety and alignment in an era of long-horizon models
Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning
DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance…
Lifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations
SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in …
AI is more likely than humans to form biases when hiring