Sebastian J Zhao

on the atlas — 46

• Explore | Listen on NTS1 savers
• KALX 90.7FM Berkeley – Ordinary people making extraordinary radio.1 savers
• KALX 90.7FM Berkeley – Ordinary people making extraordinary radio.1 savers
• linkedin/Liger-Kernel: Efficient Triton Kernels for LLM Training ·1 savers
• [2310.07831] Optimal Linear Decay Learning Rate Schedules and Further Refinements1 savers
• ESOTERIC Definition & Meaning - Merriam-Webster1 savers
• MAI-Thinking-1 | Microsoft AI1 savers
• [2605.19269] CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs1 savers
• What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware1 savers
• How I Use Git Worktrees1 savers
• [2603.18090] MOSS-TTS Technical Report1 savers
• torch.unravel_index — PyTorch 2.11 documentation1 savers
• Introducing Muse Spark: Scaling Towards Personal Superintelligence2 savers
• [2404.16710] LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding1 savers
• 454345238_3797399530471890_7024663226213786587_n.pdf1 savers
• [2508.16201] SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning1 savers
• [2603.23516] MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens1 savers
• [2510.11696] QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs1 savers
• [2602.17616] Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs1 savers
• [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?1 savers
• tinker-nomics1 savers
• [2506.06105] Text-to-LoRA: Instant Transformer Adaption1 savers
• Examining the Phenomenon of Quarter-Life Crisis Through Artificial Intelligence and the Language of Twitter - PMC1 savers
• Watching the World Burn | Burning (2018) - Bright Wall/Dark Room1 savers
• 2502.110893 savers
• [2211.17192] Fast Inference from Transformers via Speculative Decoding2 savers
• 1810.048051 savers
• 2305.143141 savers
• the friendship theory of everything68 savers
• The First Fully General Computer Action Model | blog35 savers
• LoRA Without Regret - Thinking Machines Lab32 savers
• Making Deep Learning Go Faster25 savers
• Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Lab18 savers
• Transformer Inference Arithmetic | kipply's blog17 savers
• Ilya 30u3012 savers
• 10 Types of Odd Friendships You're Probably Part Of — Wait But Why10 savers
• why time felt slower when we were kids (and how to get it back)8 savers
• Generative modelling in latent space – Sander Dieleman6 savers
• Step-by-Step Diffusion: An Elementary Tutorial5 savers
• it's time to start bullying young Palantir employees4 savers
• The Bitter Lesson is coming for Tokenization | ⛰️ lucalp4 savers
• Large Language Diffusion Models3 savers
• 2409.029083 savers
• Kimi K2.5 Tech Blog: Visual Agentic Intelligence3 savers
• Ben Kamens / Claw, reflect on our work and express your feelings as animated ASCII art2 savers
• Overleaf Example2 savers