Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
SCENEBench: An Audio Understanding Benchmark Grounded in Assistive and Industrial Use Cases
-
A Graph-Based Approach to Spectrum Demand Prediction Using Hierarchical Attention Networks
-
GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection
-
Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts
-
CarbonBench: A Global Benchmark for Upscaling of Carbon Fluxes Using Zero-Shot Learning
-
N-gram-like Language Models Predict Reading Time Best
-
MissBench: Benchmarking Multimodal Affective Analysis under Imbalanced Missing Modalities
-
Do What I Say: A Spoken Prompt Dataset for Instruction-Following
-
Emerging Extrinsic Dexterity in Cluttered Scenes via Dynamics-aware Policy Learning
-
DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary
-
Benchmarking Political Persuasion Risks Across Frontier Large Language Models
-
LCA: Local Classifier Alignment for Continual Learning
-
Influencing LLM Multi-Agent Dialogue via Policy-Parameterized Prompts
-
MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
-
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports
-
MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
-
AI-Enabled Data-driven Intelligence for Spectrum Demand Estimation
-
WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition
-
OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality
-
On the Structural Failure of Chamfer Distance in 3D Shape Optimization
-
Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction
-
Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation
-
Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
-
Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective
-
Model Merging in the Era of Large Language Models: Methods, Applications, and Future Directions
-
SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG
-
Towards Flexible Spectrum Access: Data-Driven Insights into Spectrum Demand
-
PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
-
Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models
-
No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space
-
Denoising the US Census: Succinct Block Hierarchical Regression
-
The Confidence Gate Theorem: When Should Ranked Decision Systems Abstain?
-
When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
-
Leveraging whole slide difficulty in Multiple Instance Learning to improve prostate cancer grading
-
From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding
-
Think Before You Lie: How Reasoning Improves Honesty
-
TinyNav: End-to-End TinyML for Real-Time Autonomous Navigation on Microcontrollers
-
BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
-
Emotional Modulation in Swarm Decision Dynamics
-
Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People
-
CREATE: Testing LLMs for Associative Creativity
-
From Data Statistics to Feature Geometry: How Correlations Shape Superposition
-
Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
-
Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes
-
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
-
Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
-
4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
-
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
-
HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
-
The Prediction-Measurement Gap: Toward Meaning Representations as Scientific Instruments
