MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning
-
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
-
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
-
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
-
MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
-
OccAny: Generalized Unconstrained Urban 3D Occupancy
-
LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset
-
Environment Maps: Structured Environmental Representations for Long-Horizon Agents
-
LLMORPH: Automated Metamorphic Testing of Large Language Models
-
LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops
-
M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production
-
Revisiting Real-Time Digging-In Effects: No Evidence from NP/Z Garden-Paths
-
Evaluating a Multi-Agent Voice-Enabled Smart Speaker for Care Homes: A Safety-Focused Framework
-
A Theory of LLM Information Susceptibility
-
Ukrainian Visual Word Sense Disambiguation Benchmark
-
Steering Code LLMs with Activation Directions for Language and Library Control
-
Stochastic Ray Tracing for the Reconstruction of 3D Gaussian Splatting
-
Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments
-
LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Load
-
Swiss-Bench SBP-002: A Frontier Model Comparison on Swiss Legal and Regulatory Tasks
-
λSplit: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy
-
Foundation Model Embeddings Meet Blended Emotions: A Multimodal Fusion Approach for the BLEMORE Challenge
-
Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages
-
Boost Like a (Var)Pro: Trust-Region Gradient Boosting via Variable Projection
-
Probing Ethical Framework Representations in Large Language Models: Structure, Entanglement, and Methodological Challenges
-
GTO Wizard Benchmark
-
Echoes: A semantically-aligned music deepfake detection dataset
-
Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models
-
Estimating Individual Tree Height and Species from UAV Imagery
-
Bio-Inspired Event-Based Visual Servoing for Ground Robots
-
Grounding Vision and Language to 3D Masks for Long-Horizon Box Rearrangement
-
Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection
-
PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation
-
Learning What Can Be Picked: Active Reachability Estimation for Efficient Robotic Fruit Harvesting
-
Assessment Design in the AI Era: A Method for Identifying Items Functioning Differentially for Humans and Chatbots
-
MoCHA: Denoising Caption Supervision for Motion-Text Retrieval
-
The Economics of Builder Saturation in Digital Markets
-
AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models
-
Multi-LLM Query Optimization
-
CoRe: Joint Optimization with Contrastive Learning for Medical Image Registration
-
Causal AI For AMS Circuit Design: Interpretable Parameter Effects Analysis
-
The Diminishing Returns of Early-Exit Decoding in Modern LLMs
-
An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments and Analysis]
-
Mind the Hitch: Dynamic Calibration and Articulated Perception for Autonomous Trucks
-
LLMs Do Not Grade Essays Like Humans
-
CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
-
Dual-Gated Epistemic Time-Dilation: Autonomous Compute Modulation in Asynchronous MARL
-
Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
-
Bi-CRCL: Bidirectional Conservative-Radical Complementary Learning with Pre-trained Foundation Models for Class-incremental Medical Image Analysis
-
An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Models
