MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Grounding World Simulation Models in a Real-World Metropolis
-
Physics-Informed Neural Systems for the Simulation of EUV Electromagnetic Wave Diffraction from a Lithography Mask
-
Computational Concept of the Psyche
-
Effective Distillation to Hybrid xLSTM Architectures
-
OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
-
Robust and Computationally Efficient Linear Contextual Bandits under Adversarial Corruption and Heavy-Tailed Noise
-
AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
-
SmartSearch: How Ranking Beats Structure for Conversational Memory Retrieval
-
From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
-
Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery
-
S2Act: Simple Spiking Actor
-
MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification
-
ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
-
Do Metrics for Counterfactual Explanations Align with User Perception?
-
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
-
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions
-
Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion
-
Mechanistic Origin of Moral Indifference in Language Models
-
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
-
Look Before Acting: Enhancing Vision Foundation Representations for Vision-Language-Action Models
-
Mixture-of-Depths Attention
-
Towards Generalizable Robotic Manipulation in Dynamic Environments
-
You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
-
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
-
CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning
-
Entropy-Aware Task Offloading in Mobile Edge Computing
-
CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving
-
Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs
-
Domain Adaptation Without the Compute Burden for Efficient Whole Slide Image Analysis
-
Parallelised Differentiable Straightest Geodesics for 3D Meshes
-
Learnability with Partial Labels and Adaptive Nearest Neighbors
-
OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning
-
CUBE: A Standard for Unifying Agent Benchmarks
-
Prose2Policy (P2P): A Practical LLM Pipeline for Translating Natural-Language Access Policies into Executable Rego
-
Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory
-
Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables
-
Mask Is What DLLM Needs: A Masked Data Training Paradigm for Diffusion LLMs
-
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
-
Feed-forward Gaussian Registration for Head Avatar Creation and Editing
-
ModTrack: Sensor-Agnostic Multi-View Tracking via Identity-Informed PHD Filtering with Covariance Propagation
-
Longitudinal Risk Prediction in Mammography with Privileged History Distillation
-
Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition
-
Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution
-
Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation
-
Persona-Conditioned Risk Behavior in Large Language Models: A Simulated Gambling Study with GPT-4.1
-
Spectral Hierarchy of the Cosmic Web
-
When Stability Fails: Hidden Failure Modes Of LLMS in Data-Constrained Scientific Decision-Making
-
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
-
FEEL (Force-Enhanced Egocentric Learning): A Dataset for Physical Action Understanding
-
Algorithmic Trading Strategy Development and Optimisation
