Derek Wang

Day's js started 😴
Comp Eng @ UWaterloo

[Arjun Virk @virkvarjun]

I just spent months handwriting a 200 page guide on the entirety of ML foundations and math from scratch.

The guide features:
- Neural Nets (Backprop, Adam, SGD, Batch Norm)
- ML Algorithms (SVM, Grad Boosting, K-means, PCA)
- Hardware (Tensor Cores, Systolic Arrays, CUDA)
- Transformers (Multi-Head Attn, KV Cache, LoRA)
- Vision (ViT, Convolutions, MAE, IoU, NMS, VLM)
- Agents (OpenClaw, ReAct, Memory, Orchestration)

Everything I wish I had years ago, for free.

[Nengjia Li @nengjiali]

I spent 4 brutal months building a full Stereo Visual SLAM system from scratch in C++17 + CUDA.

NO pre-made libraries. NO black-box magic.

I just wanted to understand the underlying mechanics behind SLAM.

Here’s the intuitive breakdown
(the full SLAM pipeline, the math that almost broke me, and the real KITTI footage)👇

cc @aelluswamy your work in this space is a massive inspiration for tackling this from absolute scratch

[ani @anirudhbv_ce]

I implemented @GoogleResearch's TurboQuant as a CUDA-native compression engine on Blackwell B200.

5x KV cache compression on Qwen 2.5-1.5B, near-loseless attention scores, generating live from compressed memory.

5 custom cuTile CUDA kernels ft:
- fused attention (with QJL corrections)
- online softmax
-on-chip cache decompression
- pipelined TMA loads

Try it out: https://t.co/m5vkJxWIY6

s/o @blelbach and the cuTile team at @nvidia for lending me Blackwell GPU access :)

cc @sundeep @GavinSherry

[Matthew Wu @Matthew_Wu_]

My 6-axis robotic arm controller PCB that I designed back in high school.

The v2 specs:
- 4-layer board, 12A max current
- Dual ESP32 + STM32 integration
- Custom op-amp servo feedback
- Optimized for thermals & signal integrity
- Fully validated

But getting to this point wasn't easy. I learned a lot the hard way.

v1 had major signal integrity issues that forced me to cut traces, add bodge wires, and do a ton of messy rework just to get basic functionality.

But that board forced me to learn:
power distribution, spacing, layout discipline, and hot loop control.

Now that exact stuff is the foundation for the RF + power electronics boards I design at UWaterloo.

[ani @anirudhbv_ce]

🎬Floaty BTS

@float_financial

[Derek Wang @4derekwang]

@parsaxa @float_financial @anirudhbv_ce @gtskeg @shaheersan GitHub: https://t.co/uIMT5Se0xn

[Parsa Ahmadnezhad @parsaxa]

🛟 Introducing Floaty for @float_financial

> me and @4derekwang went to the Susa x KP event
> thought about panel talk on: Execution > Idea
> decided to execute in 24 hrs
> researched and built an MCP over Float API with 60+ tools

shoutout @anirudhbv_ce

@gtskeg @shaheersan

[Derek Wang @4derekwang]

@parsa_ahhh @cursor_ai @YTExo1k @dishes_io 🔥

[Parsa Ahmadnezhad @parsaxa]

🤵 we built @cursor_ai for fashion

> made it in 24hrs @ nexhacks (cmu)
> got noticed by vcs and businesss
> now we’re building it for production as an ai stylist

@4derekwang @YTExo1k @dishes_io

[Parsa Ahmadnezhad @parsaxa]

📍 E7 —> CMU

6 hour drive, exited to be building at NexHacks for the nex 24hrs

@4derekwang @YTExo1k @dishes_io

[Parsa Ahmadnezhad @parsaxa]

cannot fathom how Waterloo students are this locked in. just organized a project building event in uw cs club.

damn these waterloo students are cracked. 👩‍💻