Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
ProgAgent:A Continual RL Agent with Progress-Aware Rewards
-
OrdinalBench: A Benchmark Dataset for Diagnosing Generalization Limits in Ordinal Number Understanding of Vision-Language Models
-
Vision Transformers that Never Stop Learning
-
SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation
-
Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context
-
4DRC-OCC: Robust Semantic Occupancy Prediction Through Fusion of 4D Radar and Camera
-
Toward Global Intent Inference for Human Motion by Inverse Reinforcement Learning
-
MWM: Mobile World Models for Action-Conditioned Consistent Prediction
-
Neural Precoding in Complex Projective Spaces
-
Learning embeddings of non-linear PDEs: the Burgers' equation
-
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
-
Tracking Phenological Status and Ecological Interactions in a Hawaiian Cloud Forest Understory using Low-Cost Camera Traps and Visual Foundation Models
-
Fusion Complexity Inversion: Why Simpler Cross View Modules Outperform SSMs and Cross View Attention Transformers for Pasture Biomass Regression
-
Column Generation for the Micro-Transit Zoning Problem
-
Benchmarking Large Language Models for Quebec Insurance: From Closed-Book to Retrieval-Augmented Generation
-
Transferable Optimization Network for Cross-Domain Image Reconstruction
-
GazeShift: Unsupervised Gaze Estimation and Dataset for VR
-
Gradient Iterated Temporal-Difference Learning
-
AI Misuse in Education Is a Measurement Problem: Toward a Learning Visibility Framework
-
DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
-
AI Steerability 360: A Toolkit for Steering Large Language Models
-
On the Formal Limits of Alignment Verification
-
Training-free Temporal Object Tracking in Surgical Videos
-
An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data
-
Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial IntelligenceBeihang University, Fudan University, Hong Kong University of Science and Technology, Nanyang Technological University, Northwestern Polytechnical University, Peking University, Shanghai AI Lab, Shanghai Jiao Tong University, Sichuan University, The Chinese University of Hong Kong, Tsinghua University
-
ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene ReconstructionKing's College London, Mohamed bin Zayed University of Artificial Intelligence, The University of Hong Kong, The University of Sydney
-
Scalable Training of Mixture-of-Experts Models with Megatron Core
-
Intentional Deception as Controllable Capability in LLM AgentsUniversity of Idaho
-
Scalable Training of Mixture-of-Experts Models with Megatron Core
-
Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines
-
Virtual Intraoperative CT (viCT): Sequential Anatomic Updates for Modeling Tissue Resection Throughout Endoscopic Sinus Surgery
-
Post-Training with Policy Gradients: Optimality and the Base Model Barrier
-
Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards
-
Learning Quadruped Walking from Seconds of Demonstration
-
A SISA-based Machine Unlearning Framework for Power Transformer Inter-Turn Short-Circuit Fault Localization
-
Topology-Aware Reinforcement Learning over Graphs for Resilient Power Distribution Networks
-
SurgCUT3R: Surgical Scene-Aware Continuous Understanding of Temporal 3D Representation
-
Conditional Unbalanced Optimal Transport Maps: An Outlier-Robust Framework for Conditional Generative Modeling
-
T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding
-
Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues
-
A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivity
-
NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning
-
Diffusion Controller: Framework, Algorithms and Parameterization
-
Optimizing Multi-Modal Models for Image-Based Shape Retrieval: The Role of Pre-Alignment and Hard Contrastive Learning
-
Masked Unfairness: Hiding Causality within Zero ATE
-
Perception-Aware Multimodal Spatial Reasoning from Monocular Images
-
ADAS-TO: A Large-Scale Multimodal Naturalistic Dataset and Empirical Characterization of Human Takeovers during ADAS Engagement
-
Foundational World Models Accurately Detect Bimanual Manipulator Failures
-
MipSLAM: Alias-Free Gaussian Splatting SLAM
-
Combinatorial Allocation Bandits with Nonlinear Arm Utility
