Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction
-
ProtAlign: Contrastive learning paradigm for Sequence and structure alignment
-
The Coordination Gap: Alternation Metrics for Temporal Dynamics in Multi-Agent Battle of the Exes
-
UWPD: A General Paradigm for Invisible Watermark Detection Agnostic to Embedding Algorithms
-
Bi Directional Feedback Fusion for Activity Aware Forecasting of Indoor CO2 and PM2.5
-
StreamWise: Serving Multi-Modal Generation in Real-Time at Scale
-
Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks
-
Sparse Crosscoders for diffing MoEs and Dense models
-
MoE Lens -- An Expert Is All You Need
-
EventGeM: Global-to-Local Feature Matching for Event-Based Visual Place Recognition
-
Training-free Latent Inter-Frame Pruning with Attention Recovery
-
Margin and Consistency Supervision for Calibrated and Robust Vision Models
-
RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
-
Regression Models Meet Foundation Models: A Hybrid-AI Approach to Practical Electricity Price Forecasting
-
Self-Auditing Parameter-Efficient Fine-Tuning for Few-Shot 3D Medical Image Segmentation
-
HART: Data-Driven Hallucination Attribution and Evidence-Based Tracing for Large Language Models
-
Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
-
Lexara: A User-Centered Toolkit for Evaluating Large Language Models for Conversational Visual Analytics
-
Architectural Unification for Polarimetric Imaging Across Multiple Degradations
-
Evaluating LLM Alignment With Human Trust Models
-
Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment
-
Remote Sensing Image Classification Using Deep Ensemble Learning
-
Cog2Gen3D: Sculpturing 3D Semantic-Geometric Cognition for 3D Generation
-
Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
-
VS3R: Robust Full-frame Video Stabilization via Deep 3D Reconstruction
-
Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds
-
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
-
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
-
TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis
-
PatchCue: Enhancing Vision-Language Model Reasoning with Patch-Based Visual Cues
-
PolyBlocks: A Compiler Infrastructure for AI Chips and Programming Frameworks
-
Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation
-
Stochastic Event Prediction via Temporal Motif Transitions
-
Systematic Evaluation of Novel View Synthesis for Video Place Recognition
-
ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning
-
Confidence Before Answering: A Paradigm Shift for Efficient LLM Uncertainty Estimation
-
CylinderSplat: 3D Gaussian Splatting with Cylindrical Triplanes for Panoramic Novel View Synthesis
-
VerChol -- Grammar-First Tokenization for Agglutinative Languages
-
Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness
-
HERO: Hierarchical Embedding-Refinement for Open-Vocabulary Temporal Sentence Grounding in Videos
-
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec
-
PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
-
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
-
Building an Ensemble LLM Semantic Tagger for UN Security Council Resolutions
-
InnoAds-Composer: Efficient Condition Composition for E-Commerce Poster Generation
-
Mitigating Bias in Concept Bottleneck Models for Fair and Interpretable Image Classification
-
Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
-
Calibrated Credit Intelligence: Shift-Robust and Fair Risk Scoring with Bayesian Uncertainty and Gradient Boosting
-
LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck Analysis
-
CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection
