On the Impact of Class Imbalance on the Learning Dynamics of Deep Neural Networks:An Intu…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Appro…
Mode-as-Sequence: Translating Multimodal Motion Prediction into Unified Sequential Mode M…
MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
Explainable Multi-Task Retinal Imaging Reveals Microvascular Signals for Systemic Risk St…
DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection
Harnessing AtomisticSkills for Agentic Atomistic Research
IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcemen…
Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
Nano World Models: A Minimalist Implementation of Future Video Prediction
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing
Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed …
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs
KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing
VineLM: Trie-Based Fine-Grained Control for Agentic Workflows
Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorit…
Catching MRI outliers: unsupervised detection and localization of MRI artefacts and clini…
AI-Driven Alpha Decay: Algorithmic Homogenization, Reflexive Signal Erosion, and the Para…
AI-Driven Adaptive Adversaries and the Erosion of Cryptographic Trust in Public Key Syste…
Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Incl…
PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajecto…
Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Tex…
TRAFA: Anticipating User Actions to Reduce Errors in Procedural Tasks with Predictive Fee…
Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Trans…
Batch Normalization Amplifies Memorization and Privacy Risks
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's D…