Base44 Superagents-AI agent that does it all
Mini toolsPapers
Filter by company
-
N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting
-
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
-
RILEC: Detection and Generation of L1 Russian Interference Errors in English Learner Texts
-
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
-
Task learning increases information redundancy of neural responses in macaque visual cortex
-
Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing
-
ConfHit: Conformal Generative Design with Oracle Free Guarantees
-
Domain-Specific Quality Estimation for Machine Translation in Low-Resource Scenarios
-
Scheduling Parallel Optical Circuit Switches for AI Training
-
SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions
-
Learning Diverse Skills for Behavior Models with Mixture of Experts
-
Bridging Domains through Subspace-Aware Model Merging
-
Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers
-
Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
-
Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
-
First-Order Softmax Weighted Switching Gradient Method for Distributed Stochastic Minimax Optimization with Stochastic Constraints
-
PVminerLLM: Structured Extraction of Patient Voice from Patient-Generated Text using Large Language Models
-
From Statistical Fidelity to Clinical Consistency: Scalable Generation and Auditing of Synthetic Patient Trajectories
-
Tutor Move Taxonomy: A Theory-Aligned Framework for Analyzing Instructional Moves in Tutoring
-
Balancing Domestic and Global Perspectives: Evaluating Dual-Calibration and LLM-Generated Nudges for Diverse News Recommendation
-
Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrieval
-
Proof-of-Guardrail in AI Agents and What (Not) to Trust from It
-
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
