MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Towards Batch-to-Streaming Deep Reinforcement Learning for Continuous ControlUniversity of Padova
-
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image EditingHong Kong University of Science and Technology
-
PRISM: Streaming Human Motion Generation with Per-Joint Latent DecompositionZhejiang Lab, Zhejiang University
-
Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene RepresentationsZillow Group
-
Don't Look Back in Anger: MAGIC Net for Streaming Continual Learning with Temporal DependencePolitecnico di Milano
-
Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland SegmentationThe Ohio State University
-
FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection
-
Micro-Diffusion Compression - Binary Tree Tweedie Denoising for Online Probability Estimation
-
StreamReady: Learning What to Answer and When in Long Streaming VideosMicrosoft Research, University of Central Florida
-
Integral Formulas for Vector Spherical Tensor Products
-
UNBOX: Unveiling Black-box visual models with Natural-languageHelmholtz Munich, Technical University of Munich, University of Catania
-
OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot PoliciesUniversity of Pennsylvania
-
Retrieval-Augmented Gaussian Avatars: Improving Expression GeneralizationNVIDIA / Bar-Ilan University, OriginAI, Technion – Israel Institute of Technology, The Hebrew University of Jerusalem
-
Grow, Don't Overwrite: Fine-tuning Without Forgetting
-
CAST: Modeling Visual State Transitions for Consistent Video Retrieval
-
Divide and Predict: An Architecture for Input Space Partitioning and Enhanced AccuracyUniversity of Virginia
-
Group Entropies and Mirror Duality: A Class of Flexible Mirror Descent Updates for Machine LearningUniversidad Complutense de Madrid, Warsaw University of Technology
-
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept GenerationStepFun / Chinese Academy of Sciences, Nanyang Technological University, South China University of Technology, The Chinese University of Hong Kong
-
Cluster-Aware Attention-Based Deep Reinforcement Learning for Pickup and Delivery ProblemsDalian University of Technology
-
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
-
Context-free Self-Conditioned GAN for Trajectory ForecastingOrebro University
-
CODA: Difficulty-Aware Compute Allocation for Adaptive ReasoningFudan University
-
ImprovedGS+: A High-Performance C++/CUDA Re-Implementation Strategy for 3D Gaussian SplattingUniversidad de Murcia
-
Characterization and upgrade of a quantum graph neural network for charged particle trackingIstituto Nazionale di Fisica Nucleare, University of Ferrara
-
Quantization of Ricci Curvature in Information GeometryUniversity at Albany
-
Talking Together: Synthesizing Co-Located 3D Conversations from Audio
-
Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood EstimationEcole Normale Supérieure Paris-Saclay, Imperial College London
-
A New Lower Bound for the Random Offerer Mechanism in Bilateral Trade using AI-Guided Evolutionary Search
-
ER-Pose: Rethinking Keypoint-Driven Representation Learning for Real-Time Human Pose EstimationNanjing University of Posts and Telecommunications
-
Structural Causal Bottleneck ModelsGerman Research Center for Artificial Intelligence, Technische Universitat Berlin, University of Potsdam
-
Benchmarking Language Modeling for Lossless Compression of Full-Fidelity AudioUniversity of California San Diego
-
Split Federated Learning Architectures for High-Accuracy and Low-Delay Model Training
-
A Multi-Objective Optimization Approach for Sustainable AI-Driven Entrepreneurship in Resilient EconomiesSouthern Illinois University Carbondale, Yarmouk University
-
HiAR: Efficient Autoregressive Long Video Generation via Hierarchical DenoisingAnhui Province Key Laboratory of Digital Security, Tencent Hunyuan, The Chinese University of Hong Kong, Tongji University, University of Science and Technology of China
-
Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM EnginesThe Future University
-
Impermanent: A Live Benchmark for Temporal Generalization in Time Series ForecastingTimeCopilot, Amazon Web Services / ELLIS Institute Tübingen, Mila–Quebec AI Institute, Université de Montréal
-
FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language ModelsShanghaiTech University, University of Technology Sydney
-
Multi-level meta-reinforcement learning with skill-based curriculumJohns Hopkins University
-
Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLMNanyang Technological University, National University of Singapore
-
Large Language Model-Assisted Superconducting Qubit ExperimentsAalto University, Rensselaer Polytechnic Institute, University of Chicago
-
The Temporal Markov Transition Field
-
Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral SpecificationsFiverrLabs
-
Where, What, Why: Toward Explainable 3D-GS WatermarkingNanyang Technological University, Southeast University, Waseda University
-
VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic ModelHong Kong University of Science and Technology, Tencent Hunyuan
-
Scale-Plan: Scalable Language-Enabled Task Planning for Heterogeneous Multi-Robot TeamsHonda Research Institute, University of California, Riverside
-
Training Language Models via Neural Cellular AutomataImprobable AI Lab, Massachusetts Institute of Technology
-
Beyond Relevance: On the Relationship Between Retrieval and RAG Information CoverageJohns Hopkins University, National Institute of Standards and Technology, University of New Hampshire
-
Fish Audio S2 Technical Report
-
SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative GradientsMasaryk University, Max Planck Institute for Biogeochemistry, Max Planck Institute for Intelligent Systems, University of Tübingen
-
Are Expressive Encoders Necessary for Discrete Graph Generation?Michigan State University, University of Texas at Arlington
