Hugging Face's logo
Zixi "Oz" Li's picture
🏗️ Building on HF

Zixi "Oz" Li PRO

OzTianlu
9 32 44
Ujjwal-Tyagi's profile picture j14i's profile picture kkish's profile picture
·
https://github.com/lizixi-0x2F

AI & ML interests

My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.

Recent Activity

updated a model 11 days ago
OzTianlu/Qwen3.5-2B-OBLITERATED
published a model 11 days ago
OzTianlu/Qwen3.5-2B-OBLITERATED
reacted to theirpost with 🔥 19 days ago
ResNet is Explicit Euler. GPT is Implicit Euler. What Else is Hiding in Plain Sight? Read online: https://datawhalechina.github.io/learning-terrain/ I wrote an open-source monograph on learning dynamics — The Terrain of Learning. Bilingual (Chinese/English), 4 volumes, 12 chapters, 30+ print-grade figures. Completely free (CC BY-NC-SA 4.0). The core argument: gradient descent is not optimization. It's terrain motion. The loss function is a landscape. The gradient is the direction of slope. The optimizer is how you choose each step. Once you see it this way, everything clicks: ResNet = explicit Euler integration on a vector field. The residual branch is the vector field. Each layer takes one Euler step. GPT autoregression = implicit-state Euler iteration. Stable where explicit Euler explodes. That's why transformers handle long-range dependencies. DEQ = the Banach fixed-point theorem in production. The forward pass is root-finding. There are no layers to backprop through. KL divergence = a Bregman divergence on the entropy landscape. Your belief space is curved, not flat. Chain-of-thought reasoning = hidden states flowing along a reasoning field toward an attractor basin. Correct answers have wide basins. The number of reasoning steps is determined by the terrain, not by the problem. Diffusion models = systems flowing downhill along a score vector field, from noise to structure, from high energy to low energy. The book traces one idea across 337 years — from F=ma (Newton, 1687) to H=T+V (Hamilton, 1833) to loss landscape + gradient field (2020s). Hamilton replaced a catalog of forces with one geometric object. This book does the same for deep learning. GitHub: https://github.com/datawhalechina/learning-terrain Discussion: https://github.com/datawhalechina/learning-terrain/discussions/2 Convergence is not hope. Convergence is geometry. You see.
View all activity

Organizations

LocalLLaMA's profile picture Hugging Face Discord Community's profile picture NoesisLab's profile picture Unsloth Jobs Explorers's profile picture Reasoning Kingdom's profile picture