Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Does Latent Planning Survive Point Clouds? Action-Conditioned JEPA World Models for Geome…
Using Grounded Theory for Agent Behavior Analysis at Scale
LOCI: A Locator-Critic with Refinement Loop
TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information
Capability-Stratified Degradation in Ternary Language Models
Self-Evolving Skills via Surrogate-Guided Solve-and-Reproduce
MedTVL: Harnessing Vision and Language for Medical Time Series Classification
Beyond Token-Level Guidance: Inference-Time Alignment of Specialized LLMs via Cross-Famil…
One AI Signal, Many Human Judgments: A Bayesian Cascade Analysis of AI-based Credibility …
Online Estimation of Dynamic Origin-Destination Matrices Using Reinforcement Learning wit…
Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurcha…
ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation
PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies
CineForge: Self-Improving Agents for Long-Horizon Video Generation
Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization und…
BCPPO: Bachelier-Inspired Constrained Proximal Policy Optimization for Tail-Risk-Aware Sa…
Using Prosody to Predict Syntactic Structure
CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
The Differential Reasoning Router: Operationalizing Cost-Aware LLM Annotation in E-commer…
DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
Motus2: A Self-Evolving General World Model for Dexterous Manipulation
Science sandboxes measure the scientific capability of AI agents
MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative…
SIR: Self-improving Red-teaming for Compute Use Agents
Text-Driven Artistic Staging: Pose, Lighting, and Camera References from Paintings
VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Predi…
Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving
How Identity and Opinion Shape Political Sycophancy in LLMs
VIBE: Video Instruction-aligned Background music gEneration