Papers
-
Subject-Specific Low-Field MRI Synthesis via a Neural Operator
-
PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration
-
DSO: Dual-Scale Neural Operators for Stable Long-term Fluid Dynamics Forecasting
-
The Value of Information in Resource-Constrained Pricing
-
LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems
-
Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection
-
MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
-
Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning
-
Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators
-
Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model
-
Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets
-
Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning
-
C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D Late Gadolinium-enhanced Magnetic Resonance
-
Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting
-
Efficient Detection of Bad Benchmark Items with Novel Scalability Coefficients
-
CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks
-
Distributed Real-Time Vehicle Control for Emergency Vehicle Transit: A Scalable Cooperative Method
-
Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
-
Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs
-
Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning
-
Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields
-
A Systematic Empirical Study of Grokking: Depth, Architecture, Activation, and Regularization
-
Imperative Interference: Social Register Shapes Instruction Topology in Large Language Models
-
GDPO-Listener: Expressive Interactive Head Generation via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization
-
VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
-
A Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures
-
Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy
-
Improving Infinitely Deep Bayesian Neural Networks with Nesterov's Accelerated Gradient Method
-
System-Anchored Knee Estimation for Low-Cost Context Window Selection in PDE Forecasting
-
CARE: Training-Free Controllable Restoration for Medical Images via Dual-Latent Steering
-
Optimal High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
-
From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support
-
Epistemic Compression: The Case for Deliberate Ignorance in High-Stakes AI
-
Mechanistically Interpreting Compression in Vision-Language Models
-
GeoNDC: A Queryable Neural Data Cube for Planetary-Scale Earth Observation
-
Uncertainty Quantification for Quantum Computing
-
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
-
MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes
-
MP-MoE: Matrix Profile-Guided Mixture of Experts for Precipitation Forecasting
-
Approaches to Analysing Historical Newspapers Using LLMs
-
Closing the Confidence-Faithfulness Gap in Large Language Models
-
GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator
-
Synergistic Event-SVE Imaging for Quantitative Propellant Combustion Diagnostics
-
The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
-
Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
-
SIGMA: Structure-Invariant Generative Molecular Alignment for Chemical Language Models via Autoregressive Contrastive Learning
-
TopoPilot: Reliable Conversational Workflow Automation for Topological Data Analysis and Visualization
-
Evaluating Synthetic Images as Effective Substitutes for Experimental Data in Surface Roughness Classification
-
Ultra-fast Traffic Nowcasting and Control via Differentiable Agent-based Simulation
-
An Explainable Ensemble Learning Framework for Crop Classification with Optimized Feature Pyramids and Deep Networks
MongoDB - Build AI That Scales
