Ling-Hao CHEN (on job market)

Ph.D. candidate @Tsinghua_Uni

[Ling-Hao CHEN (on job market) @Evan_THU]

@SIGGRAPHAsia 2025, we introduce a lightweight motion retargeting (transfer) system, Motion2Motion.

🔥Beyond deep learning, Motion2Motion is a motion-matching-based system, which runs on CPU-only devices in REAL time.
See more at https://t.co/8ONOhywta5
#SIGGRAPH

[Weiyu Li @weiyuli99072112]

🚀 MeshFlow(https://t.co/501mnkvFyL) | CVPR 2026 Highlight
✅ ~1s artist mesh generation
✅ powered by MeshVAE + flow diffusion
✅ 18x faster than AR-style methods

🎮 Gradio demo(https://t.co/44KaNmeXR5)

#3DAI #CVPR2026 #GenerativeAI #OpenSource #3DAIGC

[Sadao Tokuyama @tokufxug]

Meta AIらが開発した3Dメッシュ生成技術「MeshFlow」。

従来の1面ずつ順番に作成する遅い方式を覆し、全データを同時に並列処理。

画質の劣化（量子化誤差）を完全に無くしたことで、わずか1秒でプロ仕様の滑らかな3Dデータを生成します。（詳細はリプ欄）

[Ling-Hao CHEN (on job market) @Evan_THU]

拿小本记下来📝

[Yiran @yiran2037840]

https://t.co/pX9afv5tNt

[Zhiyang (Frank) Dou @frankzydou]

Introducing ✨RigidFormer: Learning Rigid Dynamics with Transformers - our attempt to scale learning-based physical dynamics with Transformers.

RigidFormer learns rigid dynamics with Transformers. It is a mesh-free, object-centric Transformer for multi-object rigid-body contact dynamics from point clouds.

Learning physics with purely neural simulators, without relying on traditional physics engines, is an important and widely studied problem. Prior SOTA methods often use graph neural networks for accuracy and generalization, but still struggle with efficient, high-fidelity simulation at scale.

RigidFormer uses only point inputs, matches or outperforms mesh-based baselines on standard benchmarks, runs much faster, generalizes across point resolutions and datasets, and scales to 200+ objects. We also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.

RigidFormer is mesh-free: it does not require mesh connectivity, SDFs, or vertex-level message passing, making it well-suited for point-cloud observations and scalable simulation.

This architecture can also be adapted to learn soft-body dynamics by replacing the rigid-body module (differentiable Kabsch alignment).

🎬See our video for more details.

Many thanks to my amazing collaborators: Minghao Guo @GuoMh14, Haixu Wu @Haixu_Wu_1998, Doug Roble, Tuur Stuyck @TuurStuyck, and Wojciech Matusik @wojmatusik.

Project page: https://t.co/6TBaRPVEYo
Paper: https://t.co/3OQUSJSND3

[Zhiyang (Frank) Dou @frankzydou]

Excited to share that our work NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception has been accepted to #RSS2026!

Your robot — even a low-cost one — can feel external forces without torque or tactile sensors.

TL;DR: NeuralActuator is a neural actuator model that jointly predicts 1️⃣torque to capture the nonlinear and time-varying current–to–torque relationship of low-cost servos, 2️⃣external contact forces (and force detection gates) for sensorless force perception, 3️⃣and motor conditions that indicate each motor’s operating regime.

Here is a fast-forward video clip ⬇️ We are also covering more robots like LeRobot-S101 and Franka Panda.

More details coming soon.

[Ling-Hao CHEN (on job market) @Evan_THU]

Read the survey about how the world simulator evolves over the decades!

[Yuqi Hu @YuqiHuIsGreat]

Huge thanks to our amazing authors who made this work possible! Throughout one year, our survey “Simulating the Real World: A Unified Survey of Multimodal Generative Models” has been accepted by IEEE TPAMI 2026!🎉

Arxiv: https://t.co/mLaad3xIwx
Repo: https://t.co/S6u6n02OoR

[Ling-Hao CHEN (on job market) @Evan_THU]

NO HUMAN LIMITS!

[qinbafrank @qinbafrank]

人类历史首次全马破2，塞巴斯蒂安·萨维在2026伦敦马拉松用时1小时59分30秒夺冠，把世界纪录提高了接近1分钟，这是真的创造了人类记录。只能说人类在探索极限的道路上永不停歇

[Zac Yin @zixin_yin_]

I’m excited to share my three ICLR works: ColorCtrl, LazyDrag, and SpeakerVid-5M! 🚀🚀🚀

✨ High-precision, user-friendly image editing
🎥 A large-scale, high-quality audio-visual dialogue dataset
#ICLR2026 #ICLR

[Jingbo Wang @Alex_wangjingbo]

In this work, we establish an alignment between the motion space and the deep phase space, enabling modifications of motion rhythm, amplitude, and speed by adjusting the phase, amplitude, and frequency within the phase space.

[Ling-Hao CHEN (on job market) @Evan_THU]

@_TobiasLee 👍看上去任务就恁难

[Zhiyang (Frank) Dou @frankzydou]

We have seen many works unlock the power of pretrained models for images and videos🏞️. But what about human motion🕺💃?
Can we leverage a pretrained motion prior for a wide range of downstream tasks?
Yes!! UMO is a simple yet effective framework that, for the first time, unlocks the priors of a motion foundation model (i.e., HY-Motion) for 10+ tasks, including editing, reaction generation, stylization, trajectory control, obstacle avoidance, keyframe infilling, and more. Amazing work! @xiaoyan_cong and @kunkun0w0.

🏠Webpage: https://t.co/AhRCOzPxhG
📄 Paper: https://t.co/x2Zt8faTum

With the growing number of tools for transferring SMPL motion to humanoids, we hope it could also become a source of skills for humanoid robot learning.

#Graphics #Motion #Animation #AIGC #GenerativeAI #Vision #3DV #Robotics #Robot #Humanoid #Learning #GenAI #Animation

[Ling-Hao CHEN (on job market) @Evan_THU]

@_TobiasLee 恭喜学长！19年3月你给我们的经验分享受益至今！

[Ying Shan @yshan2u]

Welcome to Tencent @ SIGGRAPH Asia 2025! 🌟
Join us at Booth C01, our Dec 16 Workshop, and the Dec 17 Qingyun Starit Tech Gala as we showcase the latest in world models, 3D/4D generation & AIGC with experts from Hunyuan, ARC Lab, Tencent Video, Games & WeChat.
📌 Dec 16 – Tencent Workshop:
Frontier graphics & AIGC: 3D video world models, multimodal gen, real-time rendering, character animation + insights from Tencent tech leads.

🌃 Dec 17 – Qingyun Starit Tech Gala:
An immersive night by Victoria Harbour—connect with Tencent AI teams, rising researchers & industry leaders.
See you in Hong Kong!
🔗 https://t.co/h4HuWTPCXu

[Ling-Hao CHEN (on job market) @Evan_THU]

Congrats to Osaka. As a COROS user, I didn’t believe its predicted PB, until I break its half marathon prediction over 10 mins. This Sunday I plan to break it over 3 mins. Good luck. 🍀

[suguru osako (大迫傑) @sugurusako]

そういえば、coros のマラソンPace predictor(レースで走れる予想ペース)
がレース前2時間4分54秒になっていたのは本大会1番の驚き。

[Zhiyang (Frank) Dou @frankzydou]

Please check out paper #CoDA “Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects” at #NeurIPS2025! 🎉
(Big congrats and thanks to our amazing collaborators: @HuaijinPi (1st author), Zhi Cen, Taku Komura)

💡The paper tackles the challenge of full-body manipulation of articulated objects, generating long, physically plausible interaction sequences of a human body, both hands, and an object from an initial pose and a text instruction.
💡Its key idea is a framework that splits the body, left hand, and right hand into three diffusion models and jointly optimizes their input noise so that gradients from hand–object objectives flow through the kinematic chain and coordinate the whole body.
💡Using a unified Basis Point Set (BPS) representation to encode both object geometry and end-effector trajectories, CoDA enables precise hand–object contact and object pose control, achieves SOTA results on ARCTIC and GRAB, and supports capabilities like walking while manipulating and filling in full-body motion from hand-only data.

Btw, if you work on full-body humanoid control (either real-world robots or simulated characters), this can be a good skill learning source.

Please come meet Huaijin @HuaijinPi at our #NeurIPS2025 San Diego poster!
📍 Exhibit Hall C,D,E — #5207
🕚 Wed, Dec 3 | 11 a.m.–2 p.m. PST

Paper: https://t.co/KcAYJgxSjK
Project Page: https://t.co/z1Yt8zTOp8
Code: https://t.co/VewME6TA6M

#NeurIPS #NeurIPS2025 #motion #Animation #Robotics #Robot #AI #Deeplearning #GenerativeAI #AIGC

[Ling-Hao CHEN (on job market) @Evan_THU]

I just use @Google 's Gemini 3 to generate a BVH-viewer for animation files, which is similar to that produced by @anorangeduck . You can try it at: https://t.co/hDMpsuOXOe.

[Ling-Hao CHEN (on job market) @Evan_THU]

ConsistEdit shows a VERY VERY consistent image/video editing result!

[Zac Yin @zixin_yin_]

🚀introducing ConsistEdit @SIGGRAPHAsia 2025, a training-free attention control method for MM-DiT that enables precise, structure-aware image and video editing. It supports multi-round edits with strong consistency and achieves state-of-the-art performance without manual tuning.

[Zac Yin @zixin_yin_]

🚀introducing ConsistEdit @SIGGRAPHAsia 2025, a training-free attention control method for MM-DiT that enables precise, structure-aware image and video editing. It supports multi-round edits with strong consistency and achieves state-of-the-art performance without manual tuning.

[SIGGRAPH Asia ➡️ Kuala Lumpur, Malaysia @SIGGRAPHAsia]

We’re honored to welcome Dr. Harry Shum—Council Chairman of HKUST and former EVP of Microsoft AI & Research—to the #SIGGRAPHAsia2025 keynote stage! 🎤

Join us in Hong Kong, 15–18 Dec 2025 🎟️ https://t.co/dNEUQNhYFQ

#AI #Keynote #FutureTech