Papers
-
An Agentic Approach to Generating XAI-Narratives
-
ReViSQL: Achieving Human-Level Text-to-SQL
-
NEC-Diff: Noise-Robust Event-RAW Complementary Diffusion for Seeing Motion in Extreme Darkness
-
Physics-Informed Long-Range Coulomb Correction for Machine-learning Hamiltonians
-
A Super Fast K-means for Indexing Vector Embeddings
-
Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features
-
AgenticRS-EnsNAS: Ensemble-Decoupled Self-Evolving Architecture Search
-
CFCML: A Coarse-to-Fine Crossmodal Learning Framework For Disease Diagnosis Using Multimodal Images and Tabular Data
-
RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering
-
Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
-
ODySSeI: An Open-Source End-to-End Framework for Automated Detection, Segmentation, and Severity Estimation of Lesions in Invasive Coronary Angiography Images
-
Layered Quantum Architecture Search for 3D Point Cloud Classification
-
Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergences
-
Orchestrating Human-AI Software Delivery: A Retrospective Longitudinal Field Study of Three Software Modernization Programs
-
CoverageBench: Evaluating Information Coverage across Tasks and Domains
-
Continual Learning as Shared-Manifold Continuation Under Compatible Shift
-
Federated Hyperdimensional Computing for Resource-Constrained Industrial IoT
-
LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families
-
Investigating a Policy-Based Formulation for Endoscopic Camera Pose Recovery
-
Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs
-
Structured Latent Dynamics in Wireless CSI via Homomorphic World Models
-
DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment
-
The End of Rented Discovery: How AI Search Redistributes Power Between Hotels and Intermediaries
-
Fine-tuning Timeseries Predictors Using Reinforcement Learning
-
Antenna Array Beamforming Based on a Hybrid Quantum Optimization Framework
-
MFil-Mamba: Multi-Filter Scanning for Spatial Redundancy-Aware Visual State Space Models
-
Agentic Harness for Real-World Compilers
-
A Unified Platform and Quality Assurance Framework for 3D Ultrasound Reconstruction with Robotic, Optical, and Electromagnetic Tracking
-
A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance
-
Predicting States of Understanding in Explanatory Interactions Using Cognitive Load-Related Linguistic Cues
-
Operator Learning for Smoothing and Forecasting
-
Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
-
How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
-
LLM-Enhanced Semantic Data Integration of Electronic Component Qualifications in the Aerospace Domain
-
An Empirical Study of SFT-DPO Interaction and Parameterization in Small Language Models
-
Pitfalls in Evaluating Interpretability Agents
-
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
-
The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
-
Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition
-
GO-GenZip: Goal-Oriented Generative Sampling and Hybrid Compression
-
Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture -- Bridging Predictive and Generative Self-Supervised Learning
-
Demonstration of Adapt4Me: An Uncertainty-Aware Authoring Environment for Personalizing Automatic Speech Recognition to Non-normative Speech
-
Current LLMs still cannot 'talk much' about grammar modules: Evidence from syntax
-
Conditioning Protein Generation via Hopfield Pattern Multiplicity
-
Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning
-
Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models
-
Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives
-
An Agentic Multi-Agent Architecture for Cybersecurity Risk Management
-
Revisiting Gene Ontology Knowledge Discovery with Hierarchical Feature Selection and Virtual Study Group of AI Agents
-
Reasoning Gets Harder for LLMs Inside A Dialogue
MongoDB - Build AI That Scales
