MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Partial Policy Gradients for RL in LLMs
-
Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion
-
Spatial Colour Mixing Illusions as a Perception Stress Test for Vision-Language ModelsPolitehnica Bucuresti
-
Predictive Coding Graphs are a Superset of Feedforward Neural NetworksUtrecht University
-
Longitudinal NSCLC Treatment Progression via Multimodal Generative ModelsUmeå University, Università Campus Bio-Medico di Roma, University of Basel, University of Genoa
-
Property-driven Protein Inverse Folding With Multi-Objective Preference AlignmentHEC Montréal, Mila–Quebec AI Institute, Peking University, Université de Montréal
-
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language ModelsUniversity of Edinburgh
-
Ensemble Graph Neural Networks for Probabilistic Sea Surface Temperature Forecasting via Input PerturbationsUniversity of Illinois Urbana-Champaign
-
Efficient Vector Search in the Wild: One Model for Multi-K Queries
-
Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTORIdiap Research Institute, Mohamed bin Zayed University of Artificial Intelligence, Tallinn University of Technology
-
Reflective Flow Sampling EnhancementHong Kong Baptist University, Hong Kong University of Science and Technology, The University of Tokyo
-
FreeOcc: Training-free Panoptic Occupancy Prediction via Foundation Models
-
A Semi-Supervised Framework for Breast Ultrasound Segmentation with Training-Free Pseudo-Label Generation and Label RefinementSendai College, Southeast University, Sun Yat-sen University Cancer Center, Tohoku University, Tohoku University Graduate School of Medicine, University of Chemistry and Technology Prague, Zhejiang University
-
JOPP-3D: Joint Open Vocabulary Semantic Segmentation on Point Clouds and PanoramasRicoh / German Research Center for Artificial Intelligence, Rheinland-Pfälzische Technische Universität Kaiserslautern
-
Robotic Foundation Models for Industrial Control: A Comprehensive Survey and Readiness Assessment FrameworkUniversität Wuppertal
-
XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease ClassificationAngel College of Engineering and Technology, Bannari Amman Institute of Technology, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Vellore Institute of Technology
-
Optimizing 3D Diffusion Models for Medical Imaging via Multi-Scale Reward LearningUniversity of Sussex, University of Toronto
-
Making Training-Free Diffusion Segmentors Scale with the Generative PowerAlibaba / Chinese Academy of Sciences, Sun Yat-sen University, University of Chinese Academy of Sciences
-
Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity LearningNational Research Institute for Agriculture, Food and the Environment, University of Haute, University Paris-Saclay
-
Towards Motion Turing Test: Evaluating Human-Likeness in Humanoid Robots
-
CRIMSON: A Clinically-Grounded LLM-Based Metric for Generative Radiology Report EvaluationHarvard Medical School
-
SpaCRD: Multimodal Deep Fusion of Histology and Spatial Transcriptomics for Cancer Region DetectionWuhan University, Yunnan University, Zhongnan University of Economics and Law
-
Random Quadratic Form on a Sphere: Synchronization by Common NoiseFreie Universität Berlin, University of Amsterdam
-
Whisper-CD: Accurate Long-Form Speech Recognition using Multi-Negative Contrastive DecodingSungkyunkwan University
-
MAPO: Mixed Advantage Policy Optimization for Long-Horizon Multi-Turn Dialogue
-
Wisdom of the AI Crowd (AI-CROWD) for Ground Truth Approximation in Content Analysis: A Research Protocol & Validation Using Eleven Large Language ModelsCarlos III University of Madrid, University of Alcalá
-
LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation
-
Latent Autoencoder Ensemble Kalman Filter for Data assimilationNational University of Singapore, Southeast University
-
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
-
Adaptive Language-Aware Image Reflection Removal NetworkHuazhong University of Science and Technology, National University of Defense Technology
-
Point-Supervised Skeleton-Based Human Action SegmentationSoutheast University
-
VG3S: Visual Geometry Grounded Gaussian Splatting for Semantic Occupancy PredictionHong Kong University of Science and Technology
-
EarthBridge: A Solution for 4th Multi-modal Aerial View Image Challenge Translation TrackUniversity of Science and Technology of China, Zhejiang University
-
Topological descriptors of foot clearance gait dynamics improve differential diagnosis of ParkinsonismUniversity of Minho, University of Porto
-
Cut to the Chase: Training-free Multimodal Summarization via Chain-of-EventsHangzhou Dianzi University, Harbin Institute of Technology, University of Science and Technology of China
-
EntON: Eigenentropy-Optimized Neighborhood Densification in 3D Gaussian SplattingInstitute of Photogrammetry and Remote Sensing, Karlsruhe Institute of Technology
-
Conversational Demand Response: Bidirectional Aggregator-Prosumer Coordination through Agentic AINorwegian University of Science and Technology, Technische Universität Wien
-
Word-Anchored Temporal Forgery LocalizationNanjing University of Posts and Telecommunications, National University of Singapore, Qilu University of Technology
-
SPOT: Span-level Pause-of-Thought for Efficient and Interpretable Latent Reasoning in Large Language ModelsBeihang University, Tianjin University
-
FedSCS-XGB -- Federated Server-centric surrogate XGBoost for continual health monitoringETH Zurich, RWTH Aachen University, Swiss Paraplegic Research
-
Low-latency Event-based Object Detection with Spatially-Sparse Linear Attention
-
TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Driving
-
DC-Merge: Improving Model Merging with Directional ConsistencySoutheast University
-
Gradient Flow Polarizes Softmax Outputs towards Low-Entropy SolutionsÉcole Polytechnique Fédérale de Lausanne
-
Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression SegmentationMohamed bin Zayed University of Artificial Intelligence, The University of Melbourne, The University of Sydney
-
SPPCSO: Adaptive Penalized Estimation Method for High-Dimensional Correlated DataChongqing University
-
Synthetic Monitoring Environments for Reinforcement LearningTechnical University of Munich
-
Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation TasksIzmir Institute of Technology
-
NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous DrivingHunan University, Tongji University
-
GazeMoE: Perception of Gaze Target with Mixture-of-ExpertsAalborg University, Aston University, University of Leicester
