🦾 Rust ML

Candle Integration, tch, SmartCore, Linfa, High-performance Computing

My tiny (1000 lines), fastish, embeddable scripting language can be AOT compiled
wareya.wordpress.com·6d·
Discuss: Lobsters, Hacker News
🎭Proc Macros
A Robust Pipeline for Differentially Private Federated Learning on Imbalanced Clinical Data using SMOTETomek and FedProx
arxiv.org·4d
🕯️Candle
Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discovery
arxiv.org·1d
🕯️Candle
AI That Helps Us Help Each Other: A Proactive System for Scaffolding Mentor-Novice Collaboration in Entrepreneurship Coaching
arxiv.org·1d
🤖AI
Model Interpretability and Rationale Extraction by Input Mask Optimization
arxiv.org·1d
🤖AI
Controlling Multimodal LLMs via Reward-guided Decoding
arxiv.org·1d
🤖AI
SPHENIC: Topology-Informed Multi-View Clustering for Spatial Transcriptomics
arxiv.org·4d
🔢SIMD Programming
Risk-Based Prognostics and Health Management
arxiv.org·1d
⏱️Real-time Systems
TEN: Table Explicitization, Neurosymbolically
arxiv.org·5d
🕯️Candle
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
arxiv.org·5d
🕯️Candle
Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
arxiv.org·1d
🕯️Candle
Wild2Avatar: Rendering Humans Behind Occlusions
arxiv.org·1d
🎨Computer Graphics
LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval
arxiv.org·4d
🕯️Candle
Data-Driven Abdominal Phenotypes of Type 2 Diabetes in Lean, Overweight, and Obese Cohorts
arxiv.org·1d
🕯️Candle
SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
arxiv.org·1d
💾Database Engines
Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models
arxiv.org·1d
🎨Computer Graphics
Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis
arxiv.org·1d
🎮Game Engines
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
arxiv.org·1d
🤖AI
Efficiently Verifiable Proofs of Data Attribution
arxiv.org·4d
🌍Distributed Systems
Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
arxiv.org·1d
🕯️Candle