A student of HUST,China
Wuhan,China
Joined July 2023
- Tweets125
- Following336
- Followers17
- Likes68
Yuhang Chen retweeted
“Reinforcement Learning for Real-Time Vision-Language-Action Policies”
VLA models are usually too slow for reactive robot control, so this paper lets the VLA generate actions slowly in the background, while a lightweight RL policy uses the latest observation to rapidly edit and select actions in real time.
This simple split improves real-world success from 42% to 97% with just 10 minutes of online robot data.
alphaxiv.org/abs/2609.18207
Yuhang Chen retweeted
@typesafeai Jev vs. GPT-6 Astra 🤖 on a real robotic task @AgilexRobotics : Task: “Put the red cube in the box.” 🔴 → 📦
⚡ Jev 27s vs. Astra 1m 11s
💰 Jev much cheaper
The arm was limited to just 10% speed for safety — at full speed, Jev’s advantage would be even more significant.
Yuhang Chen retweeted
check out what we do. cosmicbrain.ai/?v=4
Yuhang Chen retweeted
2/ Repo here for when code drops. Mega token burning in progress pls be patient 👨🏽🚒
github.com/dimensionalOS/dim…
Yuhang Chen retweeted
Is Jev is a game changer for robotics?
We gave Jev a robot body and handed it complex tasks across navigation, spatial reasoning, and world geometry
120 different real + simulated tasks and environments benchmarking performance against Dimcode, Astra, Fable, Opus, and 5.6
We graded against speed, cost, tokens, # collisions, path quality
Code, Data, and Paper dropping tomorrow. The results were surprising.
Yuhang Chen retweeted
tested Jev as a real-time robotics policy in MuJoCo
it struggled at first, so i split each update into two calls: decide what to do next, then decide how to move the arm and gripper
Jev doesn’t accept images, it gets simplified geometry and contacts as text here
Yuhang Chen retweeted
Check out the github link here: github.com/openroboto-ai/jev…
Yuhang Chen retweeted
ByteDance released GenLIP: Let ViT Speak
A minimalist generative pretraining framework that trains Vision Transformers to predict language tokens directly from visual tokens using a single autoregressive objective, outperforming baselines with only 8B training samples.
Yuhang Chen retweeted
Map2World
Generate 3D worlds from any segment map and text.
This framework ensures global-scale consistency across expansive environments, while a detail enhancer network preserves fine-grained details without compromising scene coherence.
Yuhang Chen retweeted
在 GitHub 上挖到一门很实用的开源课：Learn Harness Engineering，专门教你给 AI 编程助手搭一套更可靠的“工作台”。
它把 AI 协作拆成五个关键机制：指令、状态、验证、范围、会话，让每次任务都可追踪、可续接、可验证，不再靠运气出结果。
GitHub：github.com/walkinglabs/learn…
官网：walkinglabs.github.io/learn-…
课程结构很清晰：12 节理论 + 6 个实战项目，用同一个桌面应用贯穿推进，边做边演进。
从最基础的对比实验起步，逐步把整套工作环境搭起来；每个项目的产出，直接接到下一个项目继续用，越做越稳。
更贴心的是，它还提供可直接复用的模板文件：拷进自己的项目就能上手，不用完整学完，也能立刻提升 AI 的稳定性和可控性。
如果你已经在用 Claude Code 或 Codex 做真实开发，却总觉得 AI 时好时坏、难以复现，这门课很值得花时间看看。
Yuhang Chen retweeted
🌩️Introducing FlashQLA: high-performance linear attention kernels on TileLang.
⚡ 2-3× fwd, 2× bwd speedup.
💻 Purpose-built for agentic on your personal devices.
1. Gate-driven auto intra-card CP.
2. Hardware-friendly reformulation.
3. TileLang fused warp-specialized kernels.
🤖 Made with AI
Yuhang Chen retweeted
It's time to systematically teach VLMs to see with synthetic images!
We built VisionFoundry, a simple but intuitive framework that generates synthetic image datasets from only a task name.
10k synthetic data → over +10% improvement on visual perception benchmarks 👀
Yuhang Chen retweeted
Engineering PhDs (D.Eng) in China are getting wholesaled out now. Company employees take three months of classes per year and walk away with the degree straight from national policy.
The state no longer trusts universities to drive real tech progress. Tang boss built Zhipu AI and still didnt get academician status. They think enterprises do it better while unis just pump out low quality papers.
Unis are told to focus on talent cultivation and hand R&D to companies so freshmen might as well go straight to internships to learn by doing.
Yet good company labs still pump out papers and undergrads get thrown into research groups. Young profs chase papers and titles old ones chase grants and cash. Nobody gets judged on actual teaching.
Undergrad research only exists because everyone knows these profs wont teach so students chase the cutting edge themselves. Leadership wisdom at its finest write piles of equations no reviewer understands and keep managing upwards.
Yuhang Chen retweeted
NEC held a welcoming ceremony for 800 newly-hired employees today. The check-in process was completed using the company's facial recognition technology.
Yuhang Chen retweeted
LongCat-Next
An open-source native multimodal model that lexicalizes vision, audio, and text into discrete tokens, enabling a pure autoregressive approach to understanding and generation.
Yuhang Chen retweeted
The biggest reduction in KV cache memory comes not from quantization or MLA, but from latent compaction, along the sequence dimension.
More strong results coming soon with Attention Matching.
Yuhang Chen retweeted
"Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?"
Self-distillation can make LLMs look smarter by producing shorter, more confident reasoning traces, but in math it often takes out the model's uncertainty and self-correction signals.
This can potentially badly hurt out-of-domain reasoning, so this paper suggests that better reasoning is not just about compression, but preserving useful "doubt".
