🕯️ Candle

Rust ML Framework, CUDA Bindings, Model Inference, Neural Networks

Coroutines in C
hackaday.com·23h
🧵Async
Library-based virtual match-between-runs quantification in GlyPep-Quant improves site-specific glycan identification
nature.com·22h
📇Vector Indexing
Evaluating AI language models just got more effective and efficient
news.stanford.edu·15h
🏆LLM Benchmarking
Multichannel, ASIO, Radeon, and Randomization
anukari.com·18h·
Discuss: Hacker News
🪄Prompt Engineering
Stop Saying RAG Is Dead
hamel.dev·20h·
Discuss: Hacker News
🔄LLM RAG Pipelines
Using AI to replicate human experimental results: a motion study
arxiv.org·11h
🛡️AI Safety
Soft Graph Clustering for single-cell RNA Sequencing Data
arxiv.org·11h
📇Vector Indexing
EV-STLLM: Electric vehicle charging forecasting based on spatio-temporal large language models with multi-frequency and multi-scale information fusion
arxiv.org·11h
📊Model Serving Economics
Deep Neural Network Based Accelerated Failure Time Models using Rank Loss
arxiv.org·11h
🔍AI Interpretability
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
arxiv.org·11h
🏆LLM Benchmarking
From Wardrobe to Canvas: Wardrobe Polyptych LoRA for Part-level Controllable Human Image Generation
arxiv.org·11h
🔤Font Rendering
Theory-Informed Improvements to Classifier-Free Guidance for Discrete Diffusion Models
arxiv.org·11h
🧠LLM Inference
BrainFLORA: Uncovering Brain Concept Representation via Multimodal Neural Embeddings
arxiv.org·11h
📊Embeddings
A code quality battle between 6 AI agents
sourcery.ai·5h·
Discuss: Hacker News
👨‍💻AI Coding
On The Role of Intentionality in Knowledge Representation: Analyzing Scene Context for Cognitive Agents with a Tiny Language Model
arxiv.org·11h
🎭Claude
Discrete Differential Principle for Continuous Smooth Function Representation
arxiv.org·11h
🎯Vector Quantization
Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift
arxiv.org·11h
📊Embeddings
BURN: Backdoor Unlearning via Adversarial Boundary Analysis
arxiv.org·11h
🛡️AI Safety
Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models
arxiv.org·11h
🛡️AI Safety
Continental scale habitat modelling with artificial intelligence and multimodal earth observation
arxiv.org·11h
🔍AI Interpretability