Yiping Wang (@ypwang61) header
Yiping Wang (@ypwang61) profile picture

Prev. @xai (coding), Ph.D. @uwcse interned @MSFTResearch, undergraduate @ZJU_China. I'm interested in mathematics, agi, and physics.

Joined February 2022
Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)Photo by Yiping Wang (@ypwang61)
Yiping Wang retweeted
Claude was trained on protein sequences, at scale. We gave 20 language models the start of little-studied bacterial proteins and asked for the next amino acids. Only the latest Claude models predict them. Not GPT, not Gemini, not seven open-weight models.
39
135
57
1,022
171,113
We breathed life into LLM system. Introducing Evolving Infra⚙️: an inference framework that adapts diverse and dynamic agent workload purely online and retires fixed PD disaggregation. vs. NVIDIA Dynamo on up to 256 GB300 GPUs: ➡️ Up to 4.1× lower latency ➡️ Up to 14× lower P95 TTFT ➡️Up to 2.36× more revenue on real agent traces(Computer Use, Coding and math agents) and opensource models. 🌐 Website: inference-rsi.com 📄 Tech report: alphaxiv.org/en/abs/2611.123… 💻 Code: github.com/mit-han-lab/Evolv… Which agent(e.g. Pi/Openhands) do you want us to accelerate next? Tell us below 👇
18
50
11
216
46,261
Yiping Wang retweeted
Back in 2023, when I was doing my PhD, I received two internship offers: one from Microsoft and the other from NVIDIA. I chose NVIDIA for my first and only internship because of the incredible things Jensen and his team had achieved. I've always admired Jensen's leadership, and I still believe he is the soul of NVIDIA. But what's happening now is deeply disappointing. Perhaps it's also bad for the open-source community.
17
29
4
655
48,577
Yiping Wang retweeted
4-bit all the way from pre-training to post-training. Pre-training done in just 68 hours. Our model factory keeps shipping. Proud of our team!
Introducing Inkling 2 Small. Scoring 31 on the AA Intelligence Index, it's a big jump over its predecessor. Inkling 2 Small is available for fine-tuning and inference on Tinker today, with full weight release planned soon. thinkingmachines.ai/news/ink…
26
33
6
734
38,044
Today we release Ripple-65B Preview, our 65B dense LLM we pretrained from scratch. Ripple sets a new state-of-the-art for U.S. open-weight models in agentic coding tasks, surpassing significantly larger models including Muse Spark Open-816B, Beam-501B, Inkling-975B, and Nemotron 3 Ultra-550B. Learn more: ricursive.com/ripple
399
544
309
4,546
787,099
Yiping Wang retweeted
Same recipe
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.…
19
48
35
444
124,290
Yiping Wang retweeted
guys astra has no magic 👀. Gemini 4 Argon and Carbon can do the same and even better. model can link the nn weight to the task.
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.…
14
13
4
285
18,902
Your Harness. You Define It. Meet Creator Mode in DeepSeek Harness. Turn ideas into plugins that you can use, from a design workspace to a sandbox game or a 3D LLM visualizer. What will you create?
765
2,125
960
25,394
2,559,613
Yiping Wang retweeted
I've always believed that intelligence should come from simple, general building blocks that learn their own abstractions directly from raw data; in other words, the bitter lesson. I think we're finally seeing a real step towards AI that can learn from all data. Language modeling on raw bytes is a microcosm of this ideal, and to me it's a central problem in AI: if we can't build LLMs that learn end-to-end from bytes, how will we handle the rest of the world's data that we understand even less? Last year we introduced hierarchical networks (H-Nets) as a first step. Our new version finds up to 3-5x efficiency gains in controlled scaling law experiments, and at larger scale matches an open-source model trained on 11T tokens with ~10x less data and compute. The posts below walk through what we found and why we think it works.
261
826
288
7,380
1,045,777
Yiping Wang retweeted
[1/n] 作为这场训练“投毒”事件最直接的受害者,2024年那几个月漫长的训练排查、对峙与质疑,对我而言是一段炼狱般的经历,也是一场对意志和技术的锤炼。 感谢好友们最艰难的时候支持陪伴。也感谢当时所有并肩作战的同事们。
92
212
57
1,388
286,789
Yiping Wang retweeted
DeepSeek V4.1 Flash 1017 runs at 1,521+ tok/s on Fireworks Ultrafast. Fast enough to ship Tetris in 11 seconds, 7x faster than Claude Opus 5.5. Join the Ultrafast waitlist: bit.ly/3UA0wKq
195
371
251
5,616
1,055,218
Yiping Wang retweeted
Open models. Open kernels. Open inference.💪
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4
33
59
4
1,719
33,802
Yiping Wang retweeted
We are releasing DeepInfer, deepseek-recipe, and other vital components for serving DeepSeek models in the hope that more companies and organizations around the world will deploy DeepSeek models and profit from doing so.
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4
124
95
27
2,597
134,009
Yiping Wang retweeted
DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license. github.com/deepseek-ai/DeepI… Supported features: - Optimized kernels, model and sampler runtime - Parallelism: Attention DP / balanced CP, MoE EP + EPLB - DSpark and confidence-scheduled verification - SWA bounded replay - Asynchronous scheduling (zero-overhead batch scheduler) - Batch-invariant inference - Deterministic sampling - Structured output
211
210
148
2,595
326,583
Yiping Wang retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4
1,768
4,938
2,352
43,869
7,123,272
为善与众行之,为巧与众能之
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4
1
2
96
3,457
Yiping Wang retweeted
Have a try!
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
3
7
97
3,017
Yiping Wang retweeted
Always improving.😄
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
18
8
1
284
24,967