Souvenir
deprogrammaticaipsum.comΒ·1d
πŸ”—Weak References
A beginner's guide to deploying LLMs with AMD on Windows using PyTorch
gpuopen.comΒ·17hΒ·
Discuss: Hacker News
πŸš€PyPy JIT
Beyond Von Neumann: Toward a unified deterministic architecture
venturebeat.comΒ·2d
🀝Cooperative Threading
A gentle introduction to GEMM using MMA tensor cores
am17an.bearblog.devΒ·4dΒ·
Discuss: Hacker News
πŸ“Linear Memory
Teaching Models to Decide When to Retrieve: Adaptive RAG, Part 4
blog.reachsumit.comΒ·22hΒ·
Discuss: Hacker News
πŸͺœRecursive Descent
AI Under the Hood Part I: Understanding the Machine
kennethwolters.comΒ·3dΒ·
Discuss: Hacker News
πŸ–₯️Lisp Machines
Predicting Brain Spikes with Quantum Weirdness: A New Era for Neural Modeling
dev.toΒ·1dΒ·
Discuss: DEV
✨Effect Inference
Paper2Video: Automatic Video Generation from Scientific Papers
arxiv.orgΒ·2h
🌳Parser Visualization
AI Development Interview Questions : Mock Interviews
dev.toΒ·5hΒ·
Discuss: DEV
🎭Program Synthesis
Llmswap: Avoid LLM vendor lock-in – 10 providers with top LMArena models
github.comΒ·2dΒ·
Discuss: Hacker News
πŸ’¬Smalltalk VMs
Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
arxiv.orgΒ·2h
πŸͺœRecursive Descent
Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents
arxiv.orgΒ·2h
πŸͺœRecursive Descent
Learning to Predict Chaos: Curriculum-Driven Training for Robust Forecasting of Chaotic Dynamics
arxiv.orgΒ·2h
🌱Minimal ML
Multimodal Function Vectors for Spatial Relations
arxiv.orgΒ·1d
🧩Persistent Vectors
Adaptively Sampling-Reusing-Mixing Decomposed Gradients to Speed Up Sharpness Aware Minimization
arxiv.orgΒ·2h
πŸ”„Loop Optimization
Efficient Quantum Hermite Transform
arxiv.orgΒ·2h
⚑Partial Evaluation
Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
arxiv.orgΒ·1d
πŸ“‹Souffle Datalog
C2|Q>: A Robust Framework for Bridging Classical and Quantum Software Development
arxiv.orgΒ·1d
πŸ”¬Nanopasses