Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Geometry-Guided Camera Motion Understanding in VideoLLMs
-
FDeID-Toolbox: Face De-Identification Toolbox
-
Scalable Machines with Intrinsic Higher Mental-State Dynamics
-
Developing the PsyCogMetrics AI Lab to Evaluate Large Language Models and Advance Cognitive Science -- A Three-Cycle Action Design Science Study
-
Steve-Evolving: Open-World Embodied Self-Evolution via Fine-Grained Diagnosis and Dual-Track Knowledge Distillation
-
When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO
-
ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation
-
DiT-IC: Aligned Diffusion Transformer for Efficient Image Compression
-
Towards Faithful Multimodal Concept Bottleneck Models
-
Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding
-
Developing and evaluating a chatbot to support maternal health care
-
Semantic Invariance in Agentic AI
-
Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
-
Perceive What Matters: Relevance-Driven Scheduling for Multimodal Streaming Perception
-
Clustering Astronomical Orbital Synthetic Data Using Advanced Feature Extraction and Dimensionality Reduction Techniques
-
MXNorm: Reusing MXFP block scales for efficient tensor normalisation
-
Diffusion-Based Feature Denoising and Using NNMF for Robust Brain Tumor Classification
-
Towards Spatio-Temporal World Scene Graph Generation from Monocular Videos
-
Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
-
LLM Constitutional Multi-Agent Governance
-
From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research
-
Neuron-Aware Data Selection In Instruction Tuning For Large Language Models
-
Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning
-
Open World MRI Reconstruction with Bias-Calibrated Adaptation
-
Leveraging Large Vision Model for Multi-UAV Co-perception in Low-Altitude Wireless Networks
-
Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models
-
Visual-ERM: Reward Modeling for Visual Equivalence
-
Resolving Interference (RI): Disentangling Models for Improved Model Merging
-
PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
-
Equivalence of approximation by networks of single- and multi-spike neurons
-
Deep Invertible Autoencoders for Dimensionality Reduction of Dynamical Systems
-
Synthetic Melanoma Image Generation and Evaluation Using Generative Adversarial Networks
-
ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning
-
Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization
-
LibraGen: Playing a Balance Game in Subject-Driven Video Generation
-
MIRAGE: Model-agnostic Industrial Realistic Anomaly Generation and Evaluation for Visual Anomaly Detection
-
Executable Archaeology: Reanimating the Logic Theorist from its IPL-V Source
-
The AI Fiction Paradox
-
Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization
-
NumColor: Precise Numeric Color Control in Text-to-Image Generation
-
Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy
-
Semantic Aware Feature Extraction for Enhanced 3D Reconstruction
-
Performance evaluation of deep learning models for image analysis: considerations for visual control and statistical metrics
-
Holographic Invariant Storage: Design-Time Safety Contracts via Vector Symbolic Architectures
-
Robust Automatic Differentiation of Square-Root Kalman Filters via Gramian Differentials
-
Task-Oriented Wireless Transmission of 3D Point Clouds: Geometric Versus Semantic Robustness
-
Scalable Classification of Course Information Sheets Using Large Language Models: A Reusable Institutional Method for Academic Quality Assurance
-
MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction
-
EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection
-
Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
