Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Do Language Models Know Theo Has a Wife? Investigating the Proviso Problem
-
Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors
-
$Δ$VLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation
-
Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
-
M$^3$-ACE: Rectifying Visual Perception in Multimodal Math Reasoning via Multi-Agentic Context Engineering
-
Unifying On- and Off-Policy Variance Reduction Methods
-
Leaderboard Incentives: Model Rankings under Strategic Post-Training
-
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse
-
Beyond the Markovian Assumption: Robust Optimization via Fractional Weyl Integrals in Imbalanced Data
-
Structure from Rank: Rank-Order Coding as a Bridge from Sequence to Structure
-
InFusionLayer: a CFA-based ensemble tool to generate new classifiers for learning and modeling
-
Rectified flow-based prediction of post-treatment brain MRI from pre-radiotherapy priors for patients with glioma
-
Real-Time Drone Detection in Event Cameras via Per-Pixel Frequency Analysis
-
AULLM++: Structural Reasoning with Large Language Models for Micro-Expression Recognition
-
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
-
StructBiHOI: Structured Articulation Modeling for Long--Horizon Bimanual Hand--Object Interaction Generation
-
Adaptive Loops and Memory in Transformers: Think Harder or Know More?
-
COACH meets QUORUM: A Framework and Pipeline for Aligning User, Expert and Developer Perspectives in LLM-generated Health Counselling
-
Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
-
A Recipe for Stable Offline Multi-agent Reinforcement Learning
-
SPIRAL: A Closed-Loop Framework for Self-Improving Action World Models via Reflective Planning Agents
-
Sandpiper: Orchestrated AI-Annotation for Educational Discourse at Scale
-
Aligning to Illusions: Choice Blindness in Human and AI Feedback
-
Geometrically Constrained Outlier Synthesis
-
Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems
-
Human-Aware Robot Behaviour in Self-Driving Labs
-
SYNAPSE: Framework for Neuron Analysis and Perturbation in Sequence Encoding
-
IronEngine: Towards General AI Assistant
-
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
-
One Model Is Enough: Native Retrieval Embeddings from LLM Agent Hidden States
-
Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
-
Can Vision-Language Models Solve the Shell Game?
-
Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation
-
Efficient Policy Learning with Hybrid Evaluation-Based Genetic Programming for Uncertain Agile Earth Observation Satellite Scheduling
-
A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic
-
A Dataset for Probing Translationese Preferences in English-to-Swedish Translation
-
LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
-
The Boiling Frog Threshold: Criticality and Blindness in World Model-Based Anomaly Detection Under Gradual Drift
-
Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking
-
Data-Driven Priors for Uncertainty-Aware Deterioration Risk Prediction with Multimodal Data
-
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
-
Evolving Symbiosis, from Barricelli's Legacy to Collective Intelligence: a simulated and conceptual approach
-
MUSA-PINN: Multi-scale Weak-form Physics-Informed Neural Networks for Fluid Flow in Complex Geometries
-
Integrating Lagrangian Neural Networks into the Dyna Framework for Reinforcement Learning
-
R2F: Repurposing Ray Frontiers for LLM-free Object Navigation
-
STRIDE: Structured Lagrangian and Stochastic Residual Dynamics via Flow Matching
-
Where Do Flow Semantics Reside? A Protocol-Native Tabular Pretraining Paradigm for Encrypted Traffic Classification
-
X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection
-
Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images
-
NN-OpInf: an operator inference approach using structure-preserving composable neural networks
