MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
The Efficiency Attenuation Phenomenon: A Computational Challenge to the Language of Thought Hypothesis
-
dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3
-
Hyperagents
-
LLM Nepotism in Organizational Governance
-
Embedding World Knowledge into Tabular Models: Towards Best Practices for Embedding Pipeline Design
-
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
-
Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
-
Towards Infinitely Long Neural Simulations: Self-Refining Neural Surrogate Models for Dynamical Systems
-
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
-
Harm or Humor: A Multimodal, Multilingual Benchmark for Overt and Covert Harmful Humor
-
Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs
-
Grounded Multimodal Retrieval-Augmented Drafting of Radiology Impressions Using Case-Based Similarity Search
-
Facial Movement Dynamics Reveal Workload During Complex Multitasking
-
Modeling Overlapped Speech with Shuffles
-
Attention Sinks Induce Gradient Sinks
-
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
-
CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image
-
Remote Sensing Image Dehazing: A Systematic Review of Progress, Challenges, and Prospects
-
Facts as First Class Objects: Knowledge Objects for Persistent LLM Memory
-
Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime
-
ResNet-50 with Class Reweighting and Anatomy-Guided Temporal Decoding for Gastrointestinal Video Analysis
-
A Dual Certificate Approach to Sparsity in Infinite-Width Shallow Neural Networks
-
Transfer Learning for Contextual Joint Assortment-Pricing under Cross-Market Heterogeneity
-
Governed Memory: A Production Architecture for Multi-Agent Workflows
-
The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing for Next-Generation Drug Discovery
-
RangeAD: Fast On-Model Anomaly Detection
-
Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassembly
-
LLM-Augmented Computational Phenotyping of Long Covid
-
EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards
-
Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
-
Dropout Robustness and Cognitive Profiling of Transformer Models via Stochastic Inference
-
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
-
M2P: Improving Visual Foundation Models with Mask-to-Point Weakly-Supervised Learning for Dense Point Tracking
-
Process Supervision for Chain-of-Thought Reasoning via Monte Carlo Net Information Gain
-
Federated Distributional Reinforcement Learning with Distributional Critic Regularization
-
Multi-Source Evidence Fusion for Audio Question Answering
-
Discovering Decoupled Functional Modules in Large Language Models
-
Intellectual Stewardship: Re-adapting Human Minds for Creative Knowledge Work in the Age of AI
-
Symmetry-Reduced Physics-Informed Learning of Tensegrity Dynamics
-
Steering Video Diffusion Transformers with Massive Activations
-
FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
-
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
-
CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
-
RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy
-
Text-to-Stage: Spatial Layouts from Long-form Narratives
-
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
-
Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models
-
Verification and Validation of Physics-Informed Surrogate Component Models for Dynamic Power-System Simulation
-
The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning
-
Event-Centric Human Value Understanding in News-Domain Texts: An Actor-Conditioned, Multi-Granularity Benchmark
