Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Mu…
MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion…
TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation
LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driv…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
BREIT: A Framework for Brain Stroke Reconstruction using Multi-Frequency 3D EIT
When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning Models
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimizati…
From Materials Database to Materials Bank: Assetizing Data for AI Driven Materials Innova…
PGUDA: Pressure-Guided Unsupervised Domain Adaptation with Cross-Modal Knowledge Distilla…
Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL
SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport
Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech…
From Spectral Methods to Sample Complexity Bounds for Fourier Neural Operators
OnPoint: Offline-to-Online Multi-Level Distillation for Point-Supervised Online Temporal …
Ahmad Osman on why local AI is catching up
Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input La…
Scaling Up Thermodynamic AI Models
MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image …
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Indu…
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
Self-Supervised Temporal Regularization for Landmark-Based Cardiac Segmentation with Auto…
WorldOdysseyBench: An Open-World Benchmark for Long-Horizon Stability of Interactive Worl…
FARS: A Fully Automated Research System Deployed at Scale