Papers
-
Borderless Long Speech Synthesis
-
Offshore oil and gas platform dynamics in the North Sea, Gulf of Mexico, and Persian Gulf: Exploiting the Sentinel-1 archive
-
Evaluating Vision Foundation Models for Pixel and Object Classification in Microscopy
-
Quantifying Gate Contribution in Quantum Feature Maps for Scalable Circuit Optimization
-
Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
-
A graph neural network based chemical mechanism reduction method for combustion applications
-
Two-Time-Scale Learning Dynamics: A Population View of Neural Network Training
-
Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study
-
GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Prediction
-
Sparsely-Supervised Data Assimilation via Physics-Informed Schrödinger Bridge
-
HUGE-Bench: A Benchmark for High-Level UAV Vision-Language-Action Tasks
-
FrameNet Semantic Role Classification by Analogy
-
FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse and Prover-Effective Autoformalization
-
Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?
-
Fourier Splatting: Generalized Fourier encoded primitives for scalable radiance fields
-
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
-
Explainable cluster analysis: a bagging approach
-
Modeling subgrid scale production rates on complex meshes using graph neural networks
-
Overreliance on AI in Information-seeking from Video Content
-
Bridging the Gap Between Climate Science and Machine Learning in Climate Model Emulation
-
Hyper-Connections for Adaptive Multi-Modal MRI Brain Tumor Segmentation
-
G2DR: A Genotype-First Framework for Genetics-Informed Target Prioritization and Drug Repurposing
-
Semantic Delta: An Interpretable Signal Differentiating Human and LLMs Dialogue
-
Failure Modes for Deep Learning-Based Online Mapping: How to Measure and Address Them
-
FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts
-
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment
-
MedQ-Engine: A Closed-Loop Data Engine for Evolving MLLMs in Medical Image Quality Assessment
-
NASimJax: GPU-Accelerated Policy Learning Framework for Penetration Testing
-
On the Dynamics & Transferability of Latent Generalization during Memorization
-
SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
-
Minimax Generalized Cross-Entropy
-
Discovery of Decision Synchronization Patterns from Event Logs
-
What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time
-
From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs
-
Toward a Multi-View Brain Network Foundation Model: Cross-View Consistency Learning Across Arbitrary Atlases
-
AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations
-
Integrating Meta-Features with Knowledge Graph Embeddings for Meta-Learning
-
MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
-
A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
-
The Multiverse of Time Series Machine Learning: an Archive for Multivariate Time Series Classification
-
Utility-Guided Agent Orchestration for Efficient LLM Tool Use
-
DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
-
Revealing Domain-Spatiality Patterns for Configuration Tuning: Domain Knowledge Meets Fitness Landscapes
-
Deep Autocorrelation Modeling for Time-Series Forecasting: Progress and Prospects
-
Scene Representation using 360° Saliency Graph and its Application in Vision-based Indoor Navigation
-
Infinite-dimensional spherical-radial decomposition for probabilistic functions, with application to constrained optimal control and Gaussian process regression
-
Leum-VL Technical Report
-
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
-
PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms
-
Span-Level Machine Translation Meta-Evaluation
MongoDB - Build AI That Scales
