Papers
-
Context-Aware Sensor Modeling for Asynchronous Multi-Sensor Tracking in Stone Soup
-
Clinical Priors Guided Lung Disease Detection in 3D CT Scans
-
Accelerating Byzantine-Robust Distributed Learning with Compressed Communication via Double Momentum and Variance Reduction
-
SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation
-
TextOVSR: Text-Guided Real-World Opera Video Super-Resolution
-
Vision-Language Model Based Multi-Expert Fusion for CT Image Classification
-
Storage and selection of multiple chaotic attractors in minimal reservoir computers
-
Point-Identification of a Robust Predictor Under Latent Shift with Imperfect Proxies
-
To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
-
HindSight: Evaluating LLM-Generated Research Ideas via Future Impact
-
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
-
Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding
-
Iterative Learning Control-Informed Reinforcement Learning for Batch Process Control
-
Sequential Transport for Causal Mediation Analysis
-
Token Coherence: Adapting MESI Cache Protocols to Minimize Synchronization Overhead in Multi-Agent LLM Systems
-
CATFormer: When Continual Learning Meets Spiking Transformers With Dynamic Thresholds
-
What Matters for Scalable and Robust Learning in End-to-End Driving Planners?
-
The Hrunting of AI: Where and How to Improve English Dialectal Fairness
-
Joint Routing and Model Pruning for Decentralized Federated Learning in Bandwidth-Constrained Multi-Hop Wireless Networks
-
The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
-
PiGRAND: Physics-informed Graph Neural Diffusion for Intelligent Additive Manufacturing
-
Massive Redundancy in Gradient Transport Enables Sparse Online Learning
-
Joint Optimization of Storage and Loading for High-Performance 3D Point Cloud Data Processing
-
Geometric framework for biological evolution
-
Efficient Document Parsing via Parallel Token Prediction
-
Mamba-3: Improved Sequence Modeling using State Space Principles
-
HorizonMath: Measuring AI Progress Toward Mathematical Discovery with Automatic Verification
-
Attention Residuals
-
Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects
-
Beyond Means: Topological Causal Effects under Persistent-Homology Ignorability
-
TACTIC for Navigating the Unknown: Tabular Anomaly deteCTion via In-Context inference
-
Balancing Multimodal Domain Generalization via Gradient Modulation and Projection
-
BluRef: Unsupervised Image Deblurring with Dense-Matching References
-
Artificial intelligence-enabled single-lead ECG for non-invasive hyperkalemia detection: development, multicenter validation, and proof-of-concept deployment
-
Selective Fine-Tuning of GPT Architectures for Parameter-Efficient Clinical Text Classification
-
Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models
-
Relationship-Aware Safety Unlearning for Multimodal LLMs
-
Fair Benchmarking of Emerging One-Step Generative Models Against Multistep Diffusion and Flow Models
-
Deep Learning From Routine Histology Improves Risk Stratification for Biochemical Recurrence in Prostate Cancer
-
Joint Segmentation and Grading with Iterative Optimization for Multimodal Glaucoma Diagnosis
-
Walking Further: Semantic-aware Multimodal Gait Recognition Under Long-Range Conditions
-
Flood Risk Follows Valleys, Not Grids: Graph Neural Networks for Flash Flood Susceptibility Mapping in Himachal Pradesh with Conformal Uncertainty Quantification
-
Efficient Federated Conformal Prediction with Group-Conditional Guarantees
-
Selective Noise Suppression and Discriminative Mutual Interaction for Robust Audio-Visual Segmentation
-
DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution
-
ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
-
Vavanagi: a Community-run Platform for Documentation of the Hula Language in Papua New Guinea
-
Memory as Asset: From Agent-centric to Human-centric Memory Management
-
Cryptographic Runtime Governance for Autonomous AI Systems: The Aegis Architecture for Verifiable Policy Enforcement
-
UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation
