100 IA vai abrir mais espaço para atendimento humano, diz diretor do Itaú canaltech.com.br · 8h 27m ago
100 Mais uma polêmica: GTA 6 terá trava de região no PS5, mas XBOX fica livre canaltech.com.br · 9h 55m ago
100 Sam Altman deleted TikTok because he could not stop scrolling. OpenAI killed Sora for the same reason. thenextweb.com · 11h 7m ago
100 A Man Gave Border Agents His Phone Passcode. It Wiped Everything. Now He’s Facing Federal Charges decrypt.co · 11h 13m ago
100 Adaptive Depth in Looped Transformers: Diagnosing Learned Halting Gates and Trajectory Readouts arxiv.org · 3d 23h ago
100 Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches arxiv.org · 3d 23h ago
100 Leveraging Biokinetic Knowledge Priors for Data-Scarce Bioprocess Modeling arxiv.org · 3d 23h ago
100 From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime arxiv.org · 3d 23h ago
100 HypNO: A Graph-Based Neural Operator with Physics-Informed Message Passing for Hyperbolic Conservation Laws arxiv.org · 3d 23h ago
100 Conflict Resolution under Degraded Surveillance in Air Corridors Using Multi-Agent Reinforcement Learning arxiv.org · 3d 23h ago
100 SevDiff: Severity-Conditioned Diffusion for Long-Tail Conflict Trajectory Generation arxiv.org · 3d 23h ago
100 Beyond SBDD: Geometric Deep Learning in Polypharmacology and Multi-target Drug Design arxiv.org · 3d 23h ago
100 SenCos-GEM: SENet-Calibrated and Law-of-Cosines-Constrained Geometry-Enhanced Molecular Representation for Property Prediction arxiv.org · 3d 23h ago
87 How to Build an End-to-End OCR Pipeline with Baidu’s Unlimited-OCR for High-Resolution Images and Multi-Page PDF Parsing marktechpost.com · 3d 23h ago
71 Fast and Efficient Approximate Nearest Neighbor Search for High-Dimensional LLM Embeddings arxiv.org · 3d 23h ago
71 SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval arxiv.org · 3d 23h ago
71 Search-on-Graph: Iterative Informed Navigation for Large Language Model Reasoning on Knowledge Graphs arxiv.org · 3d 23h ago
71 TopoGuard: Graph Theory Based Defenses Against Split-Knowledge Attacks on RAG arxiv.org · 3d 23h ago
71 Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs arxiv.org · 3d 23h ago
71 Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems arxiv.org · 3d 23h ago
71 Scalable Low-Cost Laboratory Automation: A Digital Twin-Integrated Robotic Platform for Autonomous Liquid Handling (RAINBOTTM) arxiv.org · 3d 23h ago
71 Deep Reinforcement-Learning-Guided Model Predictive Control for Preventing Overtakes in Autonomous Racing arxiv.org · 3d 23h ago
71 Distributed Model-Based Diffusion For Scalable Multi-Robot Trajectory Optimization arxiv.org · 3d 23h ago
71 FORGE-plus: Force-Budgeted Recovery for Contact-Rich Assembly with a Frozen LLM Supervisor arxiv.org · 3d 23h ago
71 Grasp, Handover, Rotate: Bimanual Object Reorientation via Compositional Diffusion and Energy-Based Optimization arxiv.org · 3d 23h ago
71 Transformer-based Diffusion models for Hydrological Time Series Probabilistic Imputation and Forecasting arxiv.org · 3d 23h ago
71 ConfidenceBench: Evaluating Confidence Calibration in Large Language Models arxiv.org · 3d 23h ago
71 Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation arxiv.org · 3d 23h ago
71 RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring arxiv.org · 3d 23h ago
71 ODeform: Learning Continuous 4D Motion for Shape Deformation with Neural ODEs arxiv.org · 3d 23h ago
71 Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis arxiv.org · 3d 23h ago
71 Explainable graph attention network for stress recognition (StressGAT) via differential action units arxiv.org · 3d 23h ago
71 ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes? arxiv.org · 3d 23h ago
71 MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer arxiv.org · 3d 23h ago
71 FSB-Net: Frequency-Spatial Boundary Network for Brain Stroke Lesion Segmentation in Non-Contrast CT arxiv.org · 3d 23h ago
71 HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving arxiv.org · 3d 23h ago