FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Constructi…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
Anchor-Conditioned Compositional Control for Landscape Image Generation
AMN: An Adaptive Multi-Scale Fusion Network with Boundary and Uncertainty Modeling for Nu…
Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences
Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Co…
SRT: Super-Resolution for Time Series via Disentangled Rectified Flow
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
LFNO: Bridging Laplace and Fourier via Transient-Steady Decomposition
DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embedd…
A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Datase…
From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spat…
Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Ap…
Customer Churn Prediction on Structured Data Using FT-Transformer and Stacking Ensembles
Accelerating Birkhoff Projection for Manifold-Constrained Hyper-Connections
Eyes All Around: Design and Analysis of 360-Degree LiDAR Perception Using Equivariant Fea…
On the Complexity of Offline Reinforcement Learning with $Q^\star$-Approximation and Part…
Cosmo3DFlow: Wavelet Flow Matching for Spatial-to-Spectral Compression in Reconstructing …
Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unifie…
Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI (Full Ve…
Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequ…
WhiteTesseract: Reframing the Interpretation of Cultural Heritage through XR and Conversa…
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
DIVERGE: Diversity-Enhanced RAG for Open-Ended Information Seeking