Papers
-
Dynamic Dual-Granularity Skill Bank for Agentic RL
-
Meta-Harness: End-to-End Optimization of Model Harnesses
-
Falcon Perception
-
Throughput Optimization as a Strategic Lever in Large-Scale AI Systems: Evidence from Dataloader and Memory Profiling Innovations
-
JRM: Joint Reconstruction Model for Multiple Objects without Alignment
-
FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation
-
Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
-
AutoB2G: A Large Language Model-Driven Agentic Framework For Automated Building-Grid Co-Simulation
-
Longitudinal Boundary Sharpness Coefficient Slopes Predict Time to Alzheimer's Disease Conversion in Mild Cognitive Impairment: A Survival Analysis Using the ADNI Cohort
-
FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
-
Toward Culturally Grounded Natural Language Processing
-
Cone-Beam CT Image Quality Enhancement Using A Latent Diffusion Model Trained with Simulated CBCT Artifacts
-
VLAgeBench: Benchmarking Large Vision-Language Models for Zero-Shot Human Age Estimation
-
QuitoBench: A High-Quality Open Time Series Forecasting Benchmark
-
GeoReFormer: Geometry-Aware Refinement for Lane Segment Detection and Topology Reasoning
-
Unlabeled Cross-Center Automatic Analysis for TAAD: An Integrated Framework from Segmentation to Clinical Features
-
Central-to-Local Adaptive Generative Diffusion Framework for Improving Gene Expression Prediction in Data-Limited Spatial Transcriptomics
-
GLU: Global-Local-Uncertainty Fusion for Scalable Spatiotemporal Reconstruction and Forecasting
-
Identification of Bivariate Causal Directionality Based on Anticipated Asymmetric Geometries
-
Learning to Trim: End-to-End Causal Graph Pruning with Dynamic Anatomical Feature Banks for Medical VQA
-
Constitutive parameterized deep energy method for solid mechanics problems with random material parameters
-
Designing Fatigue-Aware VR Interfaces via Biomechanical Models
-
Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
-
AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
-
Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection
-
Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives
-
H-Node Attack and Defense in Large Language Models
-
Retrieval-Augmented Generation Based Nurse Observation Extraction
-
Asymptotic Optimism for Tensor Regression Models with Applications to Neural Network Compression
-
Seeing Like Radiologists: Context- and Gaze-Guided Vision-Language Pretraining for Chest X-rays
-
Bridging Pixels and Words: Mask-Aware Local Semantic Fusion for Multimodal Media Verification
-
Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs
-
Pioneering Perceptual Video Fluency Assessment: A Novel Task with Benchmark Dataset and Baseline
-
Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals
-
I Want to Believe (but the Vocabulary Changed): Measuring the Semantic Structure and Evolution of Conspiracy Theories
-
MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection
-
A Regression Framework for Understanding Prompt Component Impact on LLM Performance
-
Adversarial Bandit Optimization with Globally Bounded Perturbations to Linear Losses
-
R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting
-
PAD-Hand: Physics-Aware Diffusion for Hand Motion Recovery
-
MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality
-
Envisioning global urban development with satellite imagery and generative AI
-
Semi-Automated Knowledge Engineering and Process Mapping for Total Airport Management
-
External Benchmarking of Lung Ultrasound Models for Pneumothorax-Related Signs: A Manifest-Based Multi-Source Study
-
When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization
-
Experimental study on surveillance video-based indoor occupancy measurement with occupant-centric control
-
Hybrid Diffusion Model for Breast Ultrasound Image Augmentation
-
ANVIL: Accelerator-Native Video Interpolation via Codec Motion Vector Priors
-
Learnable Instance Attention Filtering for Adaptive Detector Distillation
-
Selective Deficits in LLM Mental Self-Modeling in a Behavior-Based Test of Theory of Mind
MongoDB - Build AI That Scales
