
CS Ph.D. Student @Cornell | a fan of @ChipotleTweets | Previous Visiting @EPFL and @ucmerced | B.Eng. @WHU_1893
Ithaca, NY
Joined April 2020
- Tweets402
- Following646
- Followers584
- Likes1.2K
Pinned Tweet
We present the SOTA feed-forward 3DGS pipeline Selfi, which was accepted by #CVPR2026
Project Page: denghilbert.github.io/selfi
youming.deng retweeted
For interactive video, FPS isn’t enough. Latency measures the actual responsiveness — from an input to an RGB output.
FastFrames-1.3B generates frames in 35ms on a B200 GPU and FastFrames-14B in 45ms on 8 B200s. We also accelerate LingBot-1.3B to 50ms for responsive camera control.
We open source all code and model weights.
huggingface.co/papers/2611.2…
apple-aiml-research.github.i…
youming.deng retweeted
We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄
To enter:
🟢 Share this post
🟢 Comment #RTXON
youming.deng retweeted
We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄
To enter:
🟢 Share this post
🟢 Comment #RTXON
Terms and Conditions: nvidia.com/en-us/geforce/con…
youming.deng retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
youming.deng retweeted
Impressionism and Post-Impressionism marked the shift from traditional painting to modern art.
Worth remembering:
🔹Cézanne → Cubism. Picasso and Braque broke forms into geometric shapes.
🔹Van Gogh → Expressionism. Colours and brushwork influenced artists such as Kirchner and Kandinsky.
🔹Monet → Abstract art. His late Water Lilies anticipated artists such as Rothko.
But the influence went much further 👇
youming.deng retweeted
Hi all, I have a new result I'm excited to share. It turns out that *all existing implementations* of softmax and cross-entropy (that's JAX, PyTorch, textbooks, etc) have a subtle bug --- two bugs, actually. A simple rewrite fixes both, and eliminates "slingshots" when grokking:
youming.deng retweeted
Now autoregressive video models can remember. 🧠
Introducing MosaiChunk: persistent visual memory for long-horizon autoregressive video generation🧩.
Instead of remembering everything, it remembers the right things. ✍️
1/6
youming.deng retweeted
We are entering a new era of discovery now:
openai.com/index/sharing-ai-…
youming.deng retweeted
Do coding agents understand the dynamics of the world well enough to reconstruct it from video?
We introduce 4DCodeBench to evaluate this ability through 4D inverse graphics.
4DCodeBench.com/
<🧵>
youming.deng retweeted
Vincent van Gogh
Wheatfield with a Reaper, September 1889
Van Gogh Museum, Amsterdam

































