MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Multi-Armed Sequential Hypothesis Testing by Betting
-
A practical artificial intelligence framework for legal age estimation using clavicle computed tomography scans
-
Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning
-
Evaluating FrameNet-Based Semantic Modeling for Gender-Based Violence Detection in Clinical Records
-
Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing
-
TransText: Alpha-as-RGB Representation for Transparent Text Animation
-
ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws
-
CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention
-
Unified Policy Value Decomposition for Rapid Adaptation
-
VideoAtlas: Navigating Long-Form Video in Logarithmic Compute
-
Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures
-
ConGA: Guidelines for Contextual Gender Annotation. A Framework for Annotating Gender in Machine Translation
-
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition
-
Robust-ComBat: Mitigating Outlier Effects in Diffusion MRI Data Harmonization
-
Specification-Aware Distribution Shaping for Robotics Foundation Models
-
Beyond Muon: MUD (MomentUm Decorrelation) for Faster Transformer Training
-
TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis
-
Toward Scalable Automated Repository-Level Datasets for Software Vulnerability Detection
-
AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors
-
AdaRadar: Rate Adaptive Spectral Compression for Radar-based Perception
-
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
-
Versatile Editing of Video Content, Actions, and Dynamics without Training
-
Final Report for the Workshop on Robotics & AI in Medicine
-
GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes
-
LoST: Level of Semantics Tokenization for 3D Shapes
-
The Unreasonable Effectiveness of Text Embedding Interpolation for Continuous Image Steering
-
AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse
-
EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding
-
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
-
Universal Skeleton Understanding via Differentiable Rendering and MLLMs
-
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
-
Towards sample-optimal learning of bosonic Gaussian quantum states
-
Learning-Augmented Algorithms for $k$-median via Online Learning
-
How LLMs Distort Our Written Language
-
Efficient Dense Crowd Trajectory Prediction Via Dynamic Clustering
-
ResNets of All Shapes and Sizes: Convergence of Training Dynamics in the Large-scale Limit
-
Modeling the human lexicon under temperature variations: linguistic factors, diversity and typicality in LLM word associations
-
GRAFITE: Generative Regression Analysis Framework for Issue Tracking and Evaluation
-
Conflict-Free Policy Languages for Probabilistic ML Predicates: A Framework and Case Study with the Semantic Router DSL
-
VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events
-
CWoMP: Morpheme Representation Learning for Interlinear Glossing
-
TeachingCoach: A Fine-Tuned Scaffolding Chatbot for Instructional Guidance to Instructors
-
Starting Off on the Wrong Foot: Pitfalls in Data Preparation
-
MicroVision: An Open Dataset and Benchmark Models for Detecting Vulnerable Road Users and Micromobility Vehicles
-
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
-
Retrieval-Augmented LLMs for Security Incident Analysis
-
Access Controlled Website Interaction for Agentic AI with Delegated Critical Tasks
-
A Computationally Efficient Learning of Artificial Intelligence System Reliability Considering Error Propagation
-
R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
-
How Psychological Learning Paradigms Shaped and Constrained Artificial Intelligence
