🏗️ LLVM

Compiler Infrastructure, Code Generation, Optimization Passes, Backend Development

Opsqueue: Lightweight batch processing queue for heavy loads – now open-source
channable.com·3d·
Discuss: Lobsters, Hacker News
🗄️Database Internals
The Inkhaven Residency
lesswrong.com·11h
🌐WebGPU
LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models
arxiv.org·5d
🤖AI
Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
arxiv.org·4d
🔒Hardware Security
Improving annotator selection in Active Learning using a mood and fatigue-aware Recommender System
arxiv.org·2d
🤖AI
Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning
arxiv.org·3d
🗣️Language Servers
Adversarial-Guided Diffusion for Multimodal LLM Attacks
arxiv.org·2d
🕯️Candle
AISN #60: The AI Action Plan
lesswrong.com·2d
🤖AI
SigBERT: Combining Narrative Medical Reports and Rough Path Signature Theory for Survival Risk Estimation in Oncology
arxiv.org·2d
🕯️Candle
Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
arxiv.org·3d
🕯️Candle
MRGSEM-Sum: An Unsupervised Multi-document Summarization Framework based on Multi-Relational Graphs and Structural Entropy Minimization
arxiv.org·2d
📈Graph Algorithms
Comparing Cluster-Based Cross-Validation Strategies for Machine Learning Model Evaluation
arxiv.org·3d
🕯️Candle
LLM-Adapted Interpretation Framework for Machine Learning Models
arxiv.org·4d
🤖AI
See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs
arxiv.org·4d
🌐WebGPU
LLMs Will Sacrifice Their Goals to Avoid Discomfort: Experimental Evidence
lesswrong.com·3d
🤖AI
MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
arxiv.org·4d
🗣️Language Servers
An LLM Driven Agent Framework for Automated Infrared Spectral Multi Task Reasoning
arxiv.org·4d
🕯️Candle
InterfO-RAN: Real-Time In-band Cellular Uplink Interference Detection with GPU-Accelerated dApps
arxiv.org·2d
🌐WebGPU
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
arxiv.org·5d
🤖AI
Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
arxiv.org·4d
🎮Game Engines