Geometric approach to post-hoc debiasing in vision-language models by treating bias as subspace rather than individual coordinates.
Self-supervised learning framework using masked autoencoders to learn view-invariant representations from multi-view radiology data.
Deterministic world models for verification of vision-based control systems avoiding stochastic latent variable overapproximation.
Reinforcement learning approach to control stylized motion of animated character robot using animation references.
Lightweight transformer model for joint AP clustering and power allocation in cell-free massive MIMO networks.
Benchmark studying preprocessing and generative models (StyleGAN2, Diffusion) for synthetic dermoscopic image augmentation in melanoma diagnosis.
Framework using LLMs to refine semantic information in graph representations for improved learning across diverse graph domains.
Framework for contextual distributionally robust optimization using causal Wasserstein distance for decision-making under uncertainty.
Novel video re-rendering method using 4D reconstruction models to generate new camera trajectories from monocular video.
Theoretical ML research on density estimation using KL divergence with finite dictionaries and mixture models.
GR4AD production-oriented generative recommender system for large-scale advertising with custom architecture and serving.
PC-LLM applies pre-trained LLMs as relational reasoning backbone for wireless power control optimization.
SEAnet deep learning architecture using embedding approximation for similarity search on large data series.
Hybrid Hidden Markov framework for synthetic financial time series generation preserving statistical properties.
Multimodal AI system for automated museum audiovisual metadata curation using catalogue grounding.
Balanced thinking method addressing overthinking and underthinking in Large Reasoning Models for efficient deployment.
NCCL EP library for unified Expert Parallelism communication in Mixture-of-Experts LLM training and inference.
Resource-aware RL framework for embodied robotic agents to optimize when LLM reasoning is invoked during task execution.
NeuroNarrator foundation model for EEG-to-text clinical interpretation using spectro-spatial grounding.
Integration of HPC, ML, and quantum computing for drug discovery applications to improve molecular simulation.
Theoretical analysis of adversarial learning with graph-structured target distributions using interpolative divergences.
Theoretical framework for data-driven smoothing and forecasting algorithms in dynamical systems.
Benchmark study comparing deep learning efficiency across models and discussing GPU resource accessibility trends.
Bytecode virtual machine approach for efficient dynamic tensor computation with flexible shape and control flow handling.
Analysis of linguistic shifts in arXiv papers attributable to LLM usage patterns and limitations in model classification.
D-SPEAR algorithm improves reinforcement learning stability in robotic manipulation through prioritized experience replay.
MemRerank framework distills user purchase history into preference signals for personalized product reranking in LLM shopping agents.
Adaptive reasoning approach for LLM code generation that allocates thinking throughout implementation rather than upfront.
Energy-based models for stable system identification in physical dynamics using Lyapunov functions.
MyPhoneBench framework for evaluating privacy behavior of mobile phone-use AI agents during task execution.
arXiv abstract about reasoning order in LLM decision-making processes.
Framecraft: tool enabling LLMs to generate demo videos via HTML Canvas, MCP servers, and automated rendering from prompts.
Ubik Studio: local file analysis tool combining notebook-style interaction with multi-hop reasoning and approval workflows for knowledge workers.
Supply-chain security tool detecting and surfacing diffs for Claude Code plugin auto-updates. Security analysis for plugin ecosystems.
Newsletter discussing vertical integration pattern in AI application companies.
MCP server for structured NPC dialogue generation with emotion tags. Works with Ollama locally. Game dev tool for LLM agents.
any-gpu tensor engine running on AMD/Intel/Apple GPUs using WGSL compute shaders. Cross-vendor GPU ML framework.
Production-grade ML pipeline for fine-tuning LLMs using SkyPilot and DVC for resource management and experiment tracking.
Guide to running local LLMs on personal hardware for cost reduction and privacy, covering unpredictability challenges.
Nvidia IGX Thor processor for industrial, medical, and robotics edge AI applications. Supports complex generative AI models.
Tool that converts ideas and existing codebases into architecture diagrams using MCP protocol and Claude/LLM integration.
Profile of Catholic priest involved in Anthropic's ethics work, now using Claude to write novel about monk and AI companion.
Simulation of Brook Farm utopian commune using AI agents with historical personas, exploring cooperation and resource management.
Open-source authentication and access-control gateway for self-hosted LLM backends like Ollama. Adds identity, authz, rate limiting.
Claudebar wraps Claude Code in tmux with status bar, task management, and agent team panels. Developer tool enhancement.
Open-source runtime security toolkit for autonomous AI agents, covering OWASP Top security frameworks for agent governance and safety.
DIY SMS gateway using $20 Android phone and open source SMS Gateway app as Twilio alternative. Cost optimization.
Trytet: Embeddable WebAssembly substrate for stateful AI agents with zero-trust execution, sub-millisecond latency, and state persistence.
Critique of isolated AI benchmarks proposing human-centered, context-specific evaluation methods for measuring real-world AI impact.
LISA Core browser extension providing semantic compression for AI conversations across platforms with local processing (80:1 ratio).