Papers
-
Context-Enriched Natural Language Descriptions of Vessel Trajectories
-
From Garbage to Gold: A Data-Architectural Theory of Predictive Robustness
-
Sparsity and Out-of-Distribution Generalization
-
Feed m Birds with One Scone: Accelerating Multi-task Gradient Balancing via Bi-level Optimization
-
Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval
-
Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams
-
AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
-
Interpretable Aneurysm Classification via 3D Concept Bottleneck Models: Integrating Morphological and Hemodynamic Clinical Features
-
VIVECaption: A Split Approach to Caption Quality Improvement
-
Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss
-
Prompt-Based Caption Generation for Single-Tooth Dental Images Using Vision-Language Models
-
Adaptive Capacity Allocation for Vision Language Action Fine-tuning
-
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
-
Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety
-
Machine Learning for the Internet of Underwater Things: From Fundamentals to Implementation
-
QdaVPR: A novel query-based domain-agnostic model for visual place recognition
-
Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting
-
DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
-
Dynamic Vehicle Routing Problem with Prompt Confirmation of Advance Requests
-
AutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
-
Disentangled Textual Priors for Diffusion-based Image Super-Resolution
-
OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions
-
Generalization in Online Reinforcement Learning for Mobile Agents
-
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
-
RPG-SAM: Reliability-Weighted Prototypes and Geometric Adaptive Threshold Selection for Training-Free One-Shot Polyp Segmentation
-
Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
-
Machine Learning for Stress Testing: Uncertainty Decomposition in Causal Panel Prediction
-
DogWeave: High-Fidelity 3D Canine Reconstruction from a Single Image via Normal Fusion and Conditional Inpainting
-
Med-Evo: Test-time Self-evolution for Medical Multimodal Large Language Models
-
HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery
-
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning
-
Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting
-
Dial: A Knowledge-Grounded Dialect-Specific NL2SQL System
-
Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
-
SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognition
-
Image Generation Models: A Technical History
-
"Better Ask for Forgiveness than Permission": Practices and Policies of AI Disclosure in Freelance Work
-
Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment
-
The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
-
Do Machines Fail Like Humans? A Human-Centred Out-of-Distribution Spectrum for Mapping Error Alignment
-
SIGMAE: A Spectral-Index-Guided Foundation Model for Multispectral Remote Sensing
-
Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection
-
Classifying Novel 3D-Printed Objects without Retraining: Towards Post-Production Automation in Additive Manufacturing
-
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
-
Probabilistic Inference and Learning with Stein's Method
-
FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation
-
Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments
-
Contact-Guided 3D Genome Structure Generation of E. coli via Diffusion Transformers
-
Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
-
Cross-Modal Taxonomic Generalization in (Vision-) Language Models
