FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic Fairness
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving
Anthropic found a hidden space where Claude puzzles over concepts
Humanoid robots controlled by surgeons did world-first operation on live pigs
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
Wat3R: Underwater 3D Geometry Learning without Annotations
Geometry and Gradient-based Partitioning for Panoramic Outdoor Reconstruction
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Gener…
MulTTiPop: A Multitrack Transcription Dataset for Pop Music
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Validity of LLMs as data annotators: AMALIA on authority
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
LTM: Large-scale Terrain Model for Wildfire-prone Landscapes
Bringing Ode Poetry to life with MAI’s audio models
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph …
Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Re…
A Practical Investigation of Training-free Relaxed Speculative Decoding
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decen…
Humanoid robots just removed a gallbladder in a live surgery
ImputeViz: A Visual Analytics Dashboard for Diagnosing Missing Data and Comparing Imputat…
CAAD: Causality-Aware Multivariate Time Series Anomaly Detection via Multi-Scale Alignmen…
Whareformer: Learning to Track What is Where in Long Egocentric Videos
Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models wit…
Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
Systematic Evaluation of Learning Rate Scheduling Strategies Across Heterogeneous Archite…
CT-CLIP Representations for Multimodal Lung Cancer Survival Prediction
Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Auto…
VEGAS: Human-Aligned Video Caption Evaluation via Gaze