Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
-
LooComp: Leverage Leave-One-Out Strategy to Encoder-only Transformer for Efficient Query-aware Context Compression
-
UniField: A Unified Field-Aware MRI Enhancement Framework
-
Marginals Before Conditionals
-
Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness
-
How Contrastive Decoding Enhances Large Audio Language Models?
-
Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
-
HelixTrack: Event-Based Tracking and RPM Estimation of Propeller-like Objects
-
BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off
-
RAE-NWM: Navigation World Model in Dense Visual Representation Space
-
When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
-
Towards Instance Segmentation with Polygon Detection Transformers
-
Social-R1: Towards Human-like Social Reasoning in LLMs
-
A Generative Sampler for distributions with possible discrete parameter based on Reversibility
-
Efficient Reasoning at Fixed Test-Time Cost via Length-Aware Attention Priors and Gain-Aware Training
-
Multi-model approach for autonomous driving: A comprehensive study on traffic sign-, vehicle- and lane detection and behavioral cloning
-
Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification
-
Multimodal Graph Representation Learning with Dynamic Information Pathways
-
Implicit Geometry Representations for Vision-and-Language Navigation from Web Videos
-
ForgeDreamer: Industrial Text-to-3D Generation with Multi-Expert LoRA and Cross-View Hypergraph
-
Logos: An evolvable reasoning engine for rational molecular design
-
DendroNN: Dendrocentric Neural Networks for Energy-Efficient Classification of Event-Based Data
-
On Regret Bounds of Thompson Sampling for Bayesian Optimization
-
Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists
-
From Ideal to Real: Stable Video Object Removal under Imperfect Conditions
-
Learning Convex Decomposition via Feature Fields
-
CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation
-
Exploring Modality-Aware Fusion and Decoupled Temporal Propagation for Multi-Modal Object Tracking
-
Proxy-Guided Measurement Calibration
-
TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning
-
DenoiseSplat: Feed-Forward Gaussian Splatting for Noisy 3D Scene Reconstruction
-
See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation
-
Diagnosing and Repairing Citation Failures in Generative Engine Optimization
-
TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA
-
Rescaling Confidence: What Scale Design Reveals About LLM Metacognition
-
A Gaussian Comparison Theorem for Training Dynamics in Machine Learning
-
IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework
-
Curveball Steering: The Right Direction To Steer Isn't Always Linear
-
CLoE: Expert Consistency Learning for Missing Modality Segmentation
-
NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensors
-
SpaceSense-Bench: A Large-Scale Multi-Modal Benchmark for Spacecraft Perception and Pose Estimation
-
Reading the Mood Behind Words: Integrating Prosody-Derived Emotional Context into Socially Responsive VR Agents
-
OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models
-
Reward-Zero: Language Embedding Driven Implicit Reward Mechanisms for Reinforcement Learning
-
TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control
-
Beyond Scaling: Assessing Strategic Reasoning and Rapid Decision-Making Capability of LLMs in Zero-sum Environments
-
Predictive Spectral Calibration for Source-Free Test-Time Regression
-
TaSR-RAG: Taxonomy-guided Structured Reasoning for Retrieval-Augmented Generation
-
Robust Regularized Policy Iteration under Transition Uncertainty
-
Robust Provably Secure Image Steganography via Latent Iterative Optimization
