🕯️ Candle

Rust ML Framework, PyTorch Alternative, Deep Learning, Neural Networks

A Bytecode VM for Arithmetic: The Parser
abhinavsarkar.net·3d·
Discuss: Lobsters, Hacker News
🏗️LLVM
Trustworthy scientific inference for inverse problems with generative models
arxiv.org·18h
🤖AI
Simple Methods Defend RAG Systems Well Against Real-World Attacks
arxiv.org·18h
⏱️Real-time Systems
Building and Aligning Comparable Corpora
arxiv.org·18h
🗣️Language Servers
MetaExplainer: A Framework to Generate Multi-Type User-Centered Explanations for AI Systems
arxiv.org·1d
🤖AI
Solved in Unit Domain: JacobiNet for Differentiable Coordinate Transformations
arxiv.org·18h
🤖AI
Efficient Chambolle-Pock based algorithms for Convoltional sparse representation
arxiv.org·18h
🔢SIMD Programming
Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
arxiv.org·18h
🔒Hardware Security
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
arxiv.org·18h
🤖AI
S-RRG-Bench: Structured Radiology Report Generation with Fine-Grained Evaluation Framework
arxiv.org·18h
🎭Proc Macros
From Pixels to Pathology: Restoration Diffusion for Diagnostic-Consistent Virtual IHC
arxiv.org·18h
🎨Computer Graphics
Alignment Monitoring
arxiv.org·1d
🌍Distributed Systems
Accurate and Interpretable Postmenstrual Age Prediction via Multimodal Large Language Model
arxiv.org·18h
🤖AI
Constructive Disintegration and Conditional Modes
arxiv.org·1d
🤖AI
Nakamoto Consensus from Multiple Resources
arxiv.org·18h
🌍Distributed Systems
Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model
arxiv.org·18h
🎨Computer Graphics
OmniUnet: A Multimodal Network for Unstructured Terrain Segmentation on Planetary Rovers Using RGB, Depth, and Thermal Imagery
arxiv.org·1d
🎨Computer Graphics
AutoDebias: Automated Framework for Debiasing Text-to-Image Models
arxiv.org·1d
🤖AI
A Residual Guided strategy with Generative Adversarial Networks in training Physics-Informed Transformer Networks
arxiv.org·18h
🎨Computer Graphics
NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds
arxiv.org·18h
🔢SIMD Programming