Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Fibration Policy Optimization
-
SiMO: Single-Modality-Operable Multimodal Collaborative Perception
-
Sensivity of LLMs' Explanations to the Training Randomness:Context, Class & Task Dependencies
-
Optimising antibiotic switching via forecasting of patient physiology
-
Topologically Stable Hough Transform
-
Bootstrapping Audiovisual Speech Recognition in Zero-AV-Resource Scenarios with Synthetic Visual Data
-
Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement
-
FedPrism: Adaptive Personalized Federated Learning under Non-IID Data
-
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
-
FlowTouch: View-Invariant Visuo-Tactile Prediction
-
NCL-UoR at SemEval-2026 Task 5: Embedding-Based Methods, Fine-Tuning, and LLMs for Word Sense Plausibility Rating
-
Beyond ReinMax: Low-Variance Gradient Estimators for Discrete Latent Variables
-
WaDi: Weight Direction-aware Distillation for One-step Image Synthesis
-
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
-
Event-based Motion & Appearance Fusion for 6D Object Pose Tracking
-
Airborne Magnetic Anomaly Navigation with Neural-Network-Augmented Online Calibration
-
Towards a more efficient bias detection in financial language models
-
SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM
-
SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
-
Prototype-Guided Concept Erasure in Diffusion Models
-
How Much Do LLMs Hallucinate in Document Q&A Scenarios? A 172-Billion-Token Study Across Temperatures, Context Lengths, and Hardware Platforms
-
AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models
-
TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction
-
OSCAR: Occupancy-based Shape Completion via Acoustic Neural Implicit Representations
-
Evaluating LLM-Based Grant Proposal Review via Structured Perturbations
-
Using Multimodal and Language-Agnostic Sentence Embeddings for Abstractive Summarization
-
PolyFormer: learning efficient reformulations for scalable optimization under complex physical constraints
-
LAMUS: A Large-Scale Corpus for Legal Argument Mining from U.S. Caselaw using LLMs
-
Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces
-
A Blockchain-based Traceability System for AI-Driven Engine Blade Inspection
-
Novel Semantic Prompting for Zero-Shot Action Recognition
-
Minor First, Major Last: A Depth-Induced Implicit Bias of Sharpness-Aware Minimization
-
Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm
-
Graph-Instructed Neural Networks for parametric problems with varying boundary conditions
-
Retrieval-Augmented Anatomical Guidance for Text-to-CT Generation
-
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness
-
Sign Identifiability of Causal Effects in Stationary Stochastic Dynamical Systems
-
Learning Multiple Utterance-Level Attribute Representations with a Unified Speech Encoder
-
HDR-NSFF: High Dynamic Range Neural Scene Flow Fields
-
SlowBA: An efficiency backdoor attack towards VLM-based GUI agents
-
Human-AI Divergence in Ego-centric Action Recognition under Spatial and Spatiotemporal Manipulations
-
CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support
-
Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
-
EndoSERV: A Vision-based Endoluminal Robot Navigation System
-
Beyond Attention Heatmaps: How to Get Better Explanations for Multiple Instance Learning Models in Histopathology
-
SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
-
Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning Method
-
Electrocardiogram Classification with Transformers Using Koopman and Wavelet Features
-
Rethinking Attention Output Projection: Structured Hadamard Transforms for Efficient Transformers
-
Local-Global Prompt Learning via Sparse Optimal Transport
