MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
SGI: Structured 2D Gaussians for Efficient and Compact Large Image RepresentationLeibniz-Institut für Analytische Wissenschaften, Tohoku University, University of Notre Dame
-
Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural ContextCenter for Artificial Intelligence Research Nepal
-
4DRC-OCC: Robust Semantic Occupancy Prediction Through Fusion of 4D Radar and Camera
-
Toward Global Intent Inference for Human Motion by Inverse Reinforcement LearningArtificial and Natural Intelligence Toulouse Institute, Image and Pervasive Access Laboratory, Laboratory for Analysis and Architecture of Systems, New York University, Université Paul Sabatier
-
MWM: Mobile World Models for Action-Conditioned Consistent PredictionPeking University
-
Neural Precoding in Complex Projective SpacesKhalifa University of Science and Technology, University of Luxembourg
-
Learning embeddings of non-linear PDEs: the Burgers' equationHarvard University, Institucio Catalana de Recerca i Estudis Avancats, Institut de Ciencies del Cosmos, Universitat de Barcelona
-
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion AccelerationUniversity of California, Berkeley, University of Waterloo
-
Tracking Phenological Status and Ecological Interactions in a Hawaiian Cloud Forest Understory using Low-Cost Camera Traps and Visual Foundation ModelsBattele Ecology, McGill University, Princeton University, The Ohio State University, The University of Puerto Rico Rio Piedras
-
Fusion Complexity Inversion: Why Simpler Cross View Modules Outperform SSMs and Cross View Attention Transformers for Pasture Biomass RegressionIndian Institute of Information Technology
-
Column Generation for the Micro-Transit Zoning ProblemCornell University, The Pennsylvania State University, Vanderbilt University
-
Benchmarking Large Language Models for Quebec Insurance: From Closed-Book to Retrieval-Augmented GenerationUniversité Laval
-
Transferable Optimization Network for Cross-Domain Image ReconstructionGeorgia State University, University of Florida
-
GazeShift: Unsupervised Gaze Estimation and Dataset for VR
-
Gradient Iterated Temporal-Difference LearningAlberta Machine Intelligence Institute, German Research Center for Artificial Intelligence, Hessian.ai, Robotics Institute Germany, TU Darmstadt, University of Alberta, University of Würzburg
-
AI Misuse in Education Is a Measurement Problem: Toward a Learning Visibility FrameworkSt. Mary's University, Trinity University
-
DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
-
AI Steerability 360: A Toolkit for Steering Large Language ModelsIBM Research
-
On the Formal Limits of Alignment Verification
-
Training-free Temporal Object Tracking in Surgical Videos
-
An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled DataEdith Cowan University, Griffith University, University of Queenland
-
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial IntelligenceBeihang University, Fudan University, Hong Kong University of Science and Technology, Nanyang Technological University, Northwestern Polytechnical University, Peking University, Shanghai AI Lab, Shanghai Jiao Tong University, Sichuan University, The Chinese University of Hong Kong, Tsinghua University
-
ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene ReconstructionKing’s College London, Mohamed bin Zayed University of Artificial Intelligence, The University of Hong Kong, The University of Sydney
-
Scalable Training of Mixture-of-Experts Models with Megatron Core
-
Intentional Deception as Controllable Capability in LLM AgentsUniversity of Idaho
-
Scalable Training of Mixture-of-Experts Models with Megatron Core
-
More Than 1v1: Human-AI Alignment in Early Developmental Communities with Multimodal LLMs
-
Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN PipelinesBoston University, Chalmers University of Technology
-
Virtual Intraoperative CT (viCT): Sequential Anatomic Updates for Modeling Tissue Resection Throughout Endoscopic Sinus SurgeryUniversity of Washington
-
Post-Training with Policy Gradients: Optimality and the Base Model BarrierUniversity of Toronto
-
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
-
Learning Quadruped Walking from Seconds of DemonstrationUniversity of California
-
A SISA-based Machine Unlearning Framework for Power Transformer Inter-Turn Short-Circuit Fault LocalizationUniversity of Texas
-
Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution NetworksUniversity at Buffalo, University of Texas
-
SurgCUT3R: Surgical Scene-Aware Continuous Understanding of Temporal 3D RepresentationImperial College London, Nanyang Technological University, University of Liverpool
-
Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative ModelingSungkyunkwan University
-
T2SGrid: Temporal-to-Spatial Gridification for Video Temporal GroundingGuangdong Laboratory of Artificial Intelligence and Digital Economy, South China University of Technology
-
Elenchus: Generating Knowledge Bases from Prover-Skeptic DialoguesUniversity of Amsterdam
-
A Systematic Investigation of Document Chunking Strategies and Embedding SensitivityUniversity of Canberra
-
NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement LearningJohns Hopkins University
-
Diffusion Controller: Framework, Algorithms and ParameterizationCarnegie Mellon University, Yale University
-
Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive LearningDelft University of Technology, Fraunhofer Institute for Computer Graphics Research
-
Masked Unfairness: Hiding Causality within Zero ATEDartmouth College, Schmidt Center
-
Perception-Aware Multimodal Spatial Reasoning from Monocular ImagesAgency for Science, Technology and Research, Singapore, Massachusetts Institute of Technology, National University of Singapore
-
ADAS-TO: A Large-Scale Multimodal Naturalistic Dataset and Empirical Characterization of Human Takeovers during ADAS EngagementUniversity of South Florida
-
Foundational World Models Accurately Detect Bimanual Manipulator FailuresStanford University
-
MipSLAM: Alias-Free Gaussian Splatting SLAMHarbin Institute of Technology, National University of Singapore
-
Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classification
-
AdaGen: Learning Adaptive Policy for Image Synthesis
-
Large Language Model-Driven Full-Component Evolution of Adaptive Large Neighborhood Search
