Nguyen Duc Thien

Founder @

[Nguyen Duc Thien @thientweets]

Attempt to make an ASMR video but the sound doesn't work 🫤
NPC character faces design.
https://t.co/9u1bCZ2ljr

[Yanpei Cao @yanpei_cao]

Static 3D generation isn't enough. We need assets ready for animation.

Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once.

Code is fully open-sourced! Kudos to @KyrieIr31012755 and @VastAIResearch
🧵(1/4)

[AI at Meta @AIatMeta]

Today we’re excited to unveil a new generation of Segment Anything Models:

1️⃣ SAM 3 enables detecting, segmenting and tracking of objects across images and videos, now with short text phrases and exemplar prompts.

🔗 Learn more about SAM 3: https://t.co/CjMnf7fspz

2️⃣ SAM 3D brings the model collection into the 3rd dimension to enable precise reconstruction of 3D objects and people from a single 2D image.

🔗 Learn more about SAM 3D: https://t.co/yXcvts8Ogc

These models offer innovative capabilities and unique tools for developers and researchers to create, experiment and uplevel media workflows.

[Google DeepMind @GoogleDeepMind]

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐

Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

[Google Research @GoogleResearch]

Introducing Nested Learning: A new ML paradigm for continual learning that views models as nested optimization problems to enhance long context processing. Our proof-of-concept model, Hope, shows improved performance in language modeling. Learn more: https://t.co/8wvV9vyA5V

@GoogleAI

[Nguyen Duc Thien @thientweets]

Hacker Tactics Splash Art 2
Full speed drawing & painting timelapse: https://t.co/aDJTWBHuD4

[AI at Meta @AIatMeta]

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models.

Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset https://t.co/GgJEPXTH8W

[Nguyen Duc Thien @thientweets]

Check out Redbrick https://t.co/y5riQ6BTrn if you're planning to get a mortgage in SG. The consultant does everything for you and it's all free for buyers.

[Gints Zilbalodis @gintszilbalodis]

Flow was made entirely with Blender and rendered in real time with EEVEE. We didn't use a renderfarm. The final render was done on my PC. There was no compositing, all the colors were tweaked and adjusted using shaders.

[Microsoft Research @MSFTResearch]

Nature published Microsoft research detailing our WHAM, an AI model that generates video game visuals & controller actions. We're releasing the model weights, sample data & WHAM Demonstrator on Azure AI Foundry to enable researchers to build on this work. https://t.co/R3Pt8iwPBH

[alphaXiv @askalphaxiv]

1997: Deep Blue defeats Kasparov at chess
2016: AlphaGo masters the game of Go
2025: Stanford researchers crack Among Us

Trending on alphaXiv 📈

Remarkable new work trains LLMs to master strategic social deduction through multi-agent RL, doubling win rates over standard RL.

[AI at Meta @AIatMeta]

New release from Meta FAIR — Meta Motivo is a first-of-its-kind behavioral foundation model for controlling virtual physics-based humanoid agents for a wide range of complex whole-body tasks.

The model is capable of expressing human-like behaviors and achieves performance competitive with task-specific methods and outperforms state-of-the-art unsupervised RL and model-based baselines.

Try the demo ➡️ https://t.co/AbbFGJ6rqr
Get the model and code ➡️ https://t.co/TFVLxYrhIX

We’re excited about how this research could pave the way for fully embodied agents, leading to more lifelike NPCs, democratization of character animation and new types of immersive experiences.

[Google DeepMind @GoogleDeepMind]

Introducing Genie 2: our AI model that can create an endless variety of playable 3D worlds - all from a single image. 🖼️

These types of large-scale foundation world models could enable future agents to be trained and evaluated in an endless number of virtual environments. → https://t.co/1dzB2BUlWo

[The Nobel Prize @NobelPrize]

The 2024 #NobelPrize laureates in physics used tools from physics to construct methods that helped lay the foundation for today’s powerful machine learning.

John Hopfield created a structure that can store and reconstruct information. Geoffrey Hinton invented a method that can independently discover properties in data and which has become important for the large artificial neural networks now in use.

Although computers cannot think, machines can now mimic functions such as memory and learning. This year’s physics laureates have helped make this possible. Using fundamental concepts and methods from physics, they have developed technologies that use structures in networks to process information.

[Nguyen Duc Thien @thientweets]

New post with a tutorial on how to use state of the art reinforcement learning models to build an algorithmic trading agent: https://t.co/bAimDynIYR

My company AION Research’s AI and quant system development services are now open for public clients as well. Check it out!

[Nguyen Duc Thien @thientweets]

Cover art for my upcoming hobby project, a cyberspace base building battle arena.
Going for a sci-fi theme but I realized at the end it looks more like a 90s techno Harry Porter illustration😂

[Nguyen Duc Thien @thientweets]

Remake 1 of my childhood game over 20 years ago for mobile. All 225 levels are completely new and designed autonomously by an RL agent. Can you outsmart an AI levels designer?
https://t.co/MKXSrWybXQ

[Nguyen Duc Thien @thientweets]

Check out Alfie! Alfie brings together the powers of GPT, real-time data, and specialized financial models to become your personal AI investment analyst.

Available for free now on both Android and iOS:
https://t.co/QfbonZbwUS

[Nguyen Duc Thien @thientweets]

Created a financial news AI: @MarketMoodGPT. It’s an LLM fine-tuned on analyst articles and stock returns alpha to recap financial news and rate related ticker.
More exposure to lesser known companies and events compared to mainstream news front pages

[Nguyen Duc Thien @thientweets]

New post: How likely will Russian bonds default? https://t.co/hLIDV5ypb6