Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Multi-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight…
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Adaptive Turn-Taking for Real-time Multi-Party Voice Agents
Uncertainty Estimation for Molecular Diffusion Models
Accelerating Speculative Diffusions via Block Verification
Person Identification from Contextual Motion
SmartFont: Dynamic Condition Allocation for Few-Shot Font Generation
MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold
IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing
From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent
OR-Action: Multi-Role Video Understanding with Fine-Grained Actions
DuET: Dual Expert Trajectories for Diffusion Image Editing
Simultaneous Latent Budget Trees for Stratified Classification
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer O…
Distributional Loss for Robust Classification
LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis
Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summa…
Google DeepMind is worried about what happens when millions of agents start to interact
Modern analog computing for solving differential and matrix equations
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
MiniPIC: Flexible Position-Independent Caching in <100LOC
Disparate Impact in Synthetic Data Generation
Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Ep…
Limits of spectral learning under noise
Making a vintage LLM from scratch
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quanti…
TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and …