Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
MAviS: A Multimodal Conversational Assistant For Avian Species
-
A Cortically Inspired Architecture for Modular Perceptual AI
-
Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms
-
AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery
-
Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
-
Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions
-
StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models
-
Data-Driven Hints in Intelligent Tutoring Systems
-
Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
-
Faster-HEAL: An Efficient and Privacy-Preserving Collaborative Perception Framework for Heterogeneous Autonomous Vehicles
-
Shutdown Safety Valves for Advanced AI
-
FinSheet-Bench: From Simple Lookups to Complex Reasoning, Where LLMs Break on Financial Spreadsheets
-
ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity
-
Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts
-
The Third Ambition: Artificial Intelligence and the Science of Human Behavior
-
To Predict or Not to Predict? Towards reliable uncertainty estimation in the presence of noise
-
Self-Supervised Evolutionary Learning of Neurodynamic Progression and Identity Manifolds from EEG During Safety-Critical Decision Making
-
VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models
-
Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine
-
A Lightweight Digital-Twin-Based Framework for Edge-Assisted Vehicle Tracking and Collision Prediction
-
Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice
-
Learning Concept Bottleneck Models from Mechanistic Explanations
-
How Much Noise Can BERT Handle? Insights from Multilingual Sentence Difficulty Detection
-
Learning Clinical Representations Under Systematic Distribution Shift
-
A Distributed Gaussian Process Model for Multi-Robot Mapping
-
AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision
-
Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems
-
The Yerkes-Dodson Curve for AI Agents: Emergent Cooperation Under Environmental Pressure in Multi-Agent LLM Simulations
-
N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
-
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
-
RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts
-
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
-
Task learning increases information redundancy of neural responses in macaque visual cortex
-
Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing
-
ConfHit: Conformal Generative Design with Oracle Free Guarantees
-
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
-
Scheduling Parallel Optical Circuit Switches for AI Training
-
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
-
Learning Diverse Skills for Behavior Models with Mixture of Experts
-
Bridging Domains through Subspace-Aware Model Merging
-
Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
-
Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
-
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
-
First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints
-
PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models
-
From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories
-
Tutor Move Taxonomy: A Theory-Aligned Framework for Analyzing Instructional Moves in Tutoring
-
Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation
-
Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrieval
-
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
