MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
-
Rethinking Vector Field Learning for Generative Segmentation
-
DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding
-
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
-
Online Learning and Equilibrium Computation with Ranking Feedback
-
Spectrally-Guided Diffusion Noise Schedules
-
F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
-
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
-
FinTradeBench: A Financial Reasoning Benchmark for LLMs
-
Under One Sun: Multi-Object Generative Perception of Materials and Illumination
-
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing
-
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
-
NavTrust: Benchmarking Trustworthiness for Embodied Navigation
-
MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction
-
Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens
-
Matryoshka Gaussian Splatting
-
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
-
Warm-Start Flow Matching for Guaranteed Fast Text/Image Generation
-
AURORA: Adaptive Unified Representation for Robust Ultrasound Analysis
-
Factored Levenberg-Marquardt for Diffeomorphic Image Registration: An efficient optimizer for FireANTs
-
Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents
-
Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
-
TuLaBM: Tumor-Biased Latent Bridge Matching for Contrast-Enhanced MRI Synthesis
-
VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
-
Bridging Conformal Prediction and Scenario Optimization: Discarded Constraints and Modular Risk Allocation
-
Optimizing Resource-Constrained Non-Pharmaceutical Interventions for Multi-Cluster Outbreak Control Using Hierarchical Reinforcement Learning
-
Rolling-Origin Validation Reverses Model Rankings in Multi-Step PM10 Forecasting: XGBoost, SARIMA, and Persistence
-
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
-
Investigating In-Context Privacy Learning by Integrating User-Facing Privacy Tools into Conversational Agents
-
Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs
-
The Autonomy Tax: Defense Training Breaks LLM Agents
-
Is Evaluation Awareness Just Format Sensitivity? Limitations of Probe-Based Evidence under Controlled Prompt Structure
-
Vocabulary shapes cross-lingual variation of word-order learnability in language models
-
When both Grounding and not Grounding are Bad -- A Partially Grounded Encoding of Planning into SAT (Extended Version)
-
Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphs
-
Near-Equivalent Q-learning Policies for Dynamic Treatment Regimes
-
LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray
-
TrustFlow: Topic-Aware Vector Reputation Propagation for Multi-Agent Ecosystems
-
Cooperation and Exploitation in LLM Policy Synthesis for Sequential Social Dilemmas
-
In-the-Wild Camouflage Attack on Vehicle Detectors through Controllable Image Editing
-
GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models
-
Deep Hilbert--Galerkin Methods for Infinite-Dimensional PDEs and Optimal Control
-
Global Convergence of Multiplicative Updates for the Matrix Mechanism: A Collaborative Proof with Gemini 3
-
ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models
-
A Framework for Formalizing LLM Agent Security
-
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
-
Reinforcement-guided generative protein language models enable de novo design of highly diverse AAV capsids
-
TRACE: Trajectory Recovery with State Propagation Diffusion for Urban Mobility
-
Narrative Aligned Long Form Video Question Answering
-
Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
