Chien Nguyen (@chiennv2000) profile picture

Ph.D. Student @uoregon | Prev:@AWSCloud, @GoogleDeepMind and @Adobe.

Joined April 2020
Training with fewer bits is faster, but quantization error can interfere with learning. Today on Connectionism, we detail how we trained Inkling 2 Small with a native 4-bit forward pass from the first step of pretraining through the final RL rollout. thinkingmachines.ai/blog/end…
69
295
101
2,562
549,460
Chien Nguyen retweeted
🚀 Excited to introduce StreamRender-H3 — bringing real-time interactive worlds to life with diffusion models! Built on Sol-Engine, we post-trained @MiniMax_AI H3 Ref2VA into a real-time streaming neural renderer. 🎮 Code drives the world. A game engine handles physics, object states, and player interactions, while H3 generates the visuals. ⚡ Real-time streaming: 2 denoising steps, 24 FPS, and ~273 ms per chunk on 8×GB200 GPUs. 🎨 One world, endless appearances: Change the reference image and prompt to render the same interactive world in entirely different styles. 🔥 Powered by streaming post-training, distillation, a fast causal H3 VAE, and full-stack inference acceleration. Check out our demo and code! 👇 demo: nvlabs.github.io/Sana/Sol-En… code: github.com/NVlabs/Sana/tree/…
37
118
32
906
72,814
Chien Nguyen retweeted
Announcing d1 with vision. 👁️👁️ Our first decision model now supports images, text or both as inputs. We tested d1 against GPT-6.1 Sol and Claude Opus 5.5 on six real applications, from filtering support tickets to inspecting circuit boards. d1 matches or beats GPT-6.1 Sol on four of them. It costs 19x to 200x less than both models and answers significantly faster on every task. > probabilities for yes/no, choice, or score questions > one forward pass, without generating tokens > text decisions in 200 to 300 ms > Liquid API: console.liquid.ai 🧵
96
188
66
1,726
143,715
Chien Nguyen retweeted
Introducing jevgrep - a research agent CLI powered by jev from @typesafeai that reduces your coding agent cost by 40% (verified on SWE-bench) Make sure to use the built in skill so your coding agent knows to use jg for context collection github.com/dzhng/jevgrep
193
325
56
4,867
457,705
Chien Nguyen retweeted
I wrote about the state of AI, why I’m concerned about the next few years, and the choices we need to make to keep the future in humanity’s hands. An Alien Mind: openai.com/index/an-alien-mi…
953
2,505
1,092
15,239
7,701,196
Chien Nguyen retweeted
⚡️ We are excited to share updates from KDA-v0.5 (kernel design agents). Our latest Cute-DSL kernels can beat the human winners at FlashInfer Kernel Contest by 16%~69%! An amazing progress in just 3 months! - GDN prefill: 1.69x Speedup over Kachua - DSA attention: 1.41x Speedup over Dogacel - FP8 MoE: 1.17x Speedup over Team Wombat Humanize2 Flame Chase: docs.humanfia.ai/humanize2/f… Results and Reproduction: github.com/mit-han-lab/mlsys… MLSys 2026 Contest: mlsys26.flashinfer.ai/ KDA-v0.5 achieved this by integrating the Cute-DSL primitive, better workflows (humanize1 -> humanize2), updated kernel-wiki (self-evolved), and better profiling skills (IKET). The results are achieved by the flame chase flow from humanize2 – using gpt-5.6-sol and fable-5 to iteratively optimize . We have released the kernels for validation and more details will come soon! By the KDA Team: Dongyun Zou, Yixin Dong, Junxian Guo, Changye Li, Yahui Cui, Zihao Ye, Junru Shao, Zijian Zhang, Sihao Liu, Song Bian and Ligeng Zhu.
2
36
4
219
27,174
Chien Nguyen retweeted
I am excited to share some of the progress we are making towards using Gemini to accelerate scientific discovery in the real-world. We present an extension of Co-Scientist that transitions from pure in silico ideation to execution-grounded research partner, adapting to multiple levels of autonomy across different scientific domains.
8
30
7
207
35,376
Chien Nguyen retweeted
arxiv.org/abs/2608.17981 Recurrent transformer that injects activations from the top layers to the bottom layers at the next step (arxiv.org/abs/2608.08888). Why does this work without training?
31
103
32
1,058
236,988
Chien Nguyen retweeted
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14x the speed. Launching first in the OpenAI API to a select group of customers with expanded access to more businesses as capacity grows.
789
934
793
14,851
4,161,978
Chien Nguyen retweeted
Explore KDA (Kernel Design Agents): github.com/mit-han-lab/kerne…
Databricks ranks #1 on NVIDIA’s SOL-ExecBench kernel leaderboard, in the L1 single operation track, powered by KDA (Kernel Design Agents) 🎉 What’s crazy is: we 100% leveraged AI agents to beat the competition. This is a sneak peek at recursive self-improvement. The core frameworks we used were KDA, Humanize, and Omnigent: Claude writes code, Codex reviews. Together, they enabled agents to run autonomously for as long as possible. The key is setting up the right framework to let the agents cook. This work was driven by @leshenj15 at Databricks, in collaboration with NVIDIA and MIT HAN Lab’s @LigengZhu and @DongyunZou03 . Databricks AI is like a neolab. Join us if you’re cracked!
4
2
77
10,411
T2I systems look complex only because we keep adding components. How about removing them? Introducing our latest work MiniT2I 🪄: purely flow matching objective on pixels, no auxiliary losses, all open-source data and academia-affordable compute. Everything is just designed so simple and minimal. ✨
2
50
11
353
54,218
Chien Nguyen retweeted
For too long, users have lived under the software lottery tyranny of fused attention implementations. No longer. Introducing FlexAttention, a new PyTorch API allowing for many attention variants to enjoy fused kernels in a few lines of PyTorch. pytorch.org/blog/flexattenti… 1/10
24
272
39
1,521
288,446
Chien Nguyen retweeted
research.colfax-intl.com/tut… A tutorial to help your kernels run faster on the H100s. The H100 SXM GPU has the memory bandwidth of 3.35 TB/s (read: very fast), but writing CUDA kernels that can actually utilize this bandwidth is no easy business. H100 GPUs have a feature called TMA (Tensor Memory Accelerator). It is quite essential to use TMA if we want to utilize these GPUs' full bandwidth. But using TMA is not easy either. TMA has a lot of nuts and bolts. At a quick glance, it has a totally different way to invoke, compared to vanilla GPU memory copy operations. At a deeper dive, it has many nuance that programmers need to get right to achieve good speedups. Debugging it is painful if we don't understand how it works. You can find many of these nuts and bolts and nuance in our newest tutorial on TMA! We hope it's helpful. This is a collaboration with friends at @colfaxintl, whom I am really, really fortunate to have found.
3
64
3
379
34,442
the most valuable skill in the world is systems engineering: the ability to debug, understand, and improve a complex system with limited/poor measurement THIS is what makes great scientists, engineers, PMs, operators, doctors & investors not truly taught in school outside STEM
102
390
46
3,069
442,526
Chien Nguyen retweeted
I'll be at #ICML2023 hanging out at a few poster sessions, and helping organize a workshop on efficient systems for foundation models (ES-FoMo). Pls reach out if you want to chat about ML & systems. es-fomo.com/
1
11
128
27,847