Meta-Transfer Learning Powered Temporal Graph Networks for Cross-City Real Estate Appraisal
Meta-transfer learning with temporal graph networks for real estate valuation across cities with limited data.
Meta-transfer learning with temporal graph networks for real estate valuation across cities with limited data.
Deep operator networks for discovering hidden physics laws and system parameters from sparse observations without retraining.
Analyzes Local-SGD/FedAvg convergence for overparameterized models in distributed training with local update steps.
Investigates sample complexity cost of achieving replicable active learning algorithms across independent runs.
Probabilistic neural network with incremental learning and unlearning capabilities using automatic construction without hyperparameter tuning.
Hyperdimensional computing approach for causal effect estimation from observational data with network confounding and interference.
Simplifies RLHF for LLM alignment by reformulating as supervised learning, reducing complexity and computational cost of PPO/GRPO methods.
Implicit neural representation method for spherical data using harmonic positional encoding to handle curved domain geometry.
Multi-modal time series prediction framework combining prototype encoders with three LLMs for improved accuracy and explainability.
Applies reinforcement learning to insurance loss reserving under macroeconomic constraints using CVaR and PPO optimization.
Educational implementation of AlphaZero reinforcement learning framework addressing complexity and reproducibility challenges for broader accessibility.
Analyzes Transformers through evolutionary biology lens, examining in-weight learning vs in-context learning as complementary inference strategies.
Compares uniform loss vs specialized optimizers in multi-task learning, examining whether equal weighting can match task-specific optimization with proper hyperparameters.
SSR: Training-free framework for parallel decoding in LLMs, improving efficiency of test-time scaling reasoning.
FRIREN: Spectral method for long-term time-series forecasting using Wasserstein distance on geometric structure.
Exemplar-free continual learning approach for State Space Models addressing catastrophic forgetting.
Intuitor: LLM reasoning method using internal confidence signals for RL without external rewards or labeled data.
Framework for continual learning on data streams with concept drift and evolving label spaces.
Denoising diffusion model for predicting wildfire spread using generative AI.
Privacy-preserving graph structure learning with differential privacy guarantees for open datasets.
Empirical analysis of predictive multiplicity in ML models, examining conflicting predictions across equally valid models.
TIC-GRPO: Theoretical analysis and improvements to Group Relative Policy Optimization for LLM fine-tuning via RLHF.
Agnostics: Language-agnostic RL framework for LLMs to learn code generation across low-resource programming languages.
Weakly supervised learning method combining similarity-confidence and confidence-difference for incomplete labels.
Approximation results for deep neural networks with general activations in Sobolev spaces.
Parameter-free optimal convergence rates for nonlinear semi-norm contractions with Q-learning applications.
Method using LLMs to generate interpretable explanations for Graph Neural Networks on text-attributed graphs.
Bounds for Schrödinger potential estimation in generative modeling and unpaired data translation.
Analysis of how event log characteristics impact process mining algorithm performance.
Theoretical framework interpreting masked diffusion models as solutions to discrete optimal transport energy minimization problems.
HDC-X framework for energy-efficient medical data classification on embedded devices using high-dimensional computing.
AgentDrive provides persistent file storage API for AI agents without setup requirements, solving the problem of ephemeral file storage in agent sandboxes and VM environments.
ContextSpectre is a tool for managing Claude Code session context, helping developers review token usage, identify cleanable content, and reduce context bloat during long agent conversations.
Podcast interview with Nvidia CEO on company valuation and AI trends.
Mitata is a JavaScript benchmark tool with garbage collection support for runtimes like Bun and Node.js.
TechEmpower announces discontinuation of its long-running web framework performance benchmarks project.
Database/tracking page describing AI systems metrics and organizational data without specific findings.
Research finding that persona-based prompting instructions like 'You're an expert' may not improve LLM performance.
Developer reflects on contributing to open-source Chroma project using Claude AI, questioning learning and value.
Semantic gating approach for filtered vector search in job search using pgvector, handles mixed semantic and hard constraints.
Portfolio page for VitaOS-Libre operating system and VitaFPGA architecture projects, no content loaded.
Snow CLI: Terminal tool enabling agentic coding compatible with OpenAI, Gemini, and Claude APIs.
Research on LLM internal structure discovery using layer duplication experiments on open models like Qwen2-72B.
Overview of AppFunctions framework enabling agentic interfaces for application integration.
Brief post on changes to LLM-generated music monetization loophole.
Video about early AI supercomputer hardware history.
Case study using LLM to optimize legacy Java code performance through refactoring suggestions.
Forum post seeking tools for post-processing LLM chat history anonymization and PII removal.
Study showing that few in-context examples can negatively impact LLM reasoning and accuracy.
Open-source MCP server implementation enabling voice capabilities for AI agents.