MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Computer Vision-Based Vehicle Allotment System using Perspective MappingNational Institute of Technology Rourkela
-
MASEval: Extending Multi-Agent Evaluation from Models to SystemsParameter Lab / Korea Advanced Institute of Science and Technology, Mohamed bin Zayed University of Artificial Intelligence, NAVER AI Lab, TU Darmstadt, University of Oxford, University of Tübingen
-
A Lightweight Multi-Cancer Tumor Localization Framework for Deployable Digital PathologyIndiana University, University of Pittsburgh, UPMC Hillman Cancer Center
-
HECTOR: Hybrid Editable Compositional Object References for Video Generation
-
SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility EvaluationAlan Turing Institute, University of Oxford
-
LDP: An Identity-Aware Protocol for Multi-Agent LLM SystemsIndian School of Business
-
Unpacking Interpretability: Human-Centered Criteria for Optimal Combinatorial SolutionsTechnical University of Darmstadt, University of Vienna
-
Expressivity-Efficiency Tradeoffs for Hybrid Sequence ModelsUniversity of Wisconsin-Madison
-
APPLV: Adaptive Planner Parameter Learning from Vision-Language-Action ModelGeorge Mason University, Rutgers University, University of South Florida
-
Why Channel-Centric Models are not Enough to Predict End-to-End Performance in Private 5G: A Measurement Campaign and Case StudyKTH Royal Institute of Technology
-
One Language, Two Scripts: Probing Script-Invariance in LLM Concept RepresentationsColumbia University
-
Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM SearchLouisiana State University
-
MultiGraSCCo: A Multilingual Anonymization Benchmark with Annotations of Personal IdentifiersBerlin Institute for the Foundations of Learning and Data, Charité – Universitätsmedizin Berlin, German Research Center for Artificial Intelligence, Humboldt-Universität zu Berlin, Technische Universitat Berlin, University of Potsdam
-
From Word2Vec to Transformers: Text-Derived Composition Embeddings for Filtering Combinatorial ElectrocatalystsRuhr-Universität Bochum
-
Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving ArchitecturesClemson University
-
Towards Visual Query Segmentation in the WildUniversity of North Texas
-
ConFu: Contemplate the Future for Better Speculative SamplingQualcomm AI Research, University of California
-
A New Modeling to Feature Selection Based on the Fuzzy Rough Set Theory in Normal and Optimistic States on Hybrid Information SystemsIslamic Azad University
-
NetDiffuser: Deceiving DNN-Based Network Attack Detection Systems with Diffusion-Generated Adversarial TrafficNew Mexico State University, The U.S. Army Combat Capabilities Development Command, University of Hartford
-
Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center ShiftBC Cancer Research Institute, University of British Columbia
-
Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting
-
SciTaRC: Benchmarking QA on Scientific Tabular Data that Requires Language Reasoning and Complex ComputationJohns Hopkins University
-
FedLECC: Cluster- and Loss-Guided Client Selection for Federated Learning under Non-IID DataSapienza University of Rome
-
Quantifying Memorization and Privacy Risks in Genomic Language ModelsCase Western Reserve University, Rutgers University, University of Texas
-
Uncovering a Winning Lottery Ticket with Continuously Relaxed Bernoulli GatesBar-Ilan University
-
Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical ReasoningMcMaster University, Queen’s University, University of British Columbia, Vector Institute
-
Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents
-
Quantifying Uncertainty in AI Visibility: A Statistical Framework for Generative Search Measurement
-
MEGC2026: Micro-Expression Grand Challenge on Visual Question AnsweringHeriot-Watt University Malaysia, Manchester Metropolitan University, University of Chinese Academy of Sciences
-
TIDE: Text-Informed Dynamic Extrapolation with Step-Aware Temperature Control for Diffusion TransformersRice University, University of Houston
-
Using Vision Language Foundation Models to Generate Plant Simulation Configurations via In-Context LearningUniversity of California
-
Optimizing Reinforcement Learning Training over Digital Twin Enabled Multi-fidelity NetworksThe Institute of Electrical and Electronics Engineers
-
Interpretable Markov-Based Spatiotemporal Risk Surfaces for Missing-Child Search Planning with Reinforcement Learning and LLM-Based Quality AssuranceOld Dominion University
-
PathoScribe: Transforming Pathology Data into a Living Library with a Unified LLM-Driven Framework for Semantic Retrieval and Clinical Integration
-
VoxEmo: Benchmarking Speech Emotion Recognition with Speech LLMsThe University of Sheffield, University of Southern California
-
Multi-Agent Memory from a Computer Architecture Perspective: Visions and Challenges AheadGeorgia Institute of Technology, University of California
-
BiCLIP: Domain Canonicalization via Structured Geometric TransformationUniversity of Houston, University of Oklahoma
-
Kernel Debiased Plug-in Estimation based on the Universal Least Favorable SubmodelUniversity of North Carolina at Chapel Hill
-
Towards Reliable Simulation-based InferenceNational Institute for Research in Digital Science and Technology, University of Liège
-
A Consensus-Driven Multi-LLM Pipeline for Missing-Person InvestigationsOld Dominion University
-
A Survey of Reinforcement Learning For EconomicsGeorgetown University
-
Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor ComputationRice University
-
The $qs$ Inequality: Quantifying the Double Penalty of Mixture-of-Experts at Inference
-
The FABRIC Strategy for Verifying Neural Feedback SystemsStanford University
-
Semantic Level of Detail: Multi-Scale Knowledge Representation via Heat Kernel Diffusion on Hyperbolic Manifolds
-
Can You Hear, Localize, and Segment Continually? An Exemplar-Free Continual Learning Benchmark for Audio-Visual SegmentationPurdue University
-
MAcPNN: Mutual Assisted Learning on Data Streams with Temporal DependencePolitecnico di Milano
-
Data-driven robust Markov decision processes on Borel spaces: performance guarantees via an axiomatic approachRice University
-
SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware RoutingUniversity of California
-
SurgCalib: Gaussian Splatting-Based Hand-Eye Calibration for Robot-Assisted Minimally Invasive SurgeryNational University of Singapore, University of British Columbia
