Ziwei Liu's banner

Ziwei Liu

@liuziwei7 • 13,266 subscribers

Associate Professor @NTUsg - Vision, Learning and Embodied AI | Building @ropedia_ai

Shorts

We are presenting **SAD** (Segment Any RGBD): SAD is able to perform 3D segmentation (segment out any 3D object) with RGBD inputs (or rendered depth images only). - Code: - Demo Hugging Face:

We are presenting SAD (Segment Any RGBD): SAD is able to perform 3D segmentation (segment out any 3D object) with RGBD inputs (or rendered depth images only). - Code: - Demo Hugging Face:

195,642 görüntüleme

🚀A Simple Baseline for Streaming Video Understanding🚀 #SimpleStream reveals a simple baseline of *recent N-frame sliding window* beats SOTA memory-based methods on standard streaming video benchmarks lmms-lab - Project: - Code:

🚀A Simple Baseline for Streaming Video Understanding🚀 #SimpleStream reveals a simple baseline of recent N-frame sliding window beats SOTA memory-based methods on standard streaming video benchmarks lmms-lab - Project: - Code:

36,137 görüntüleme

🔥Egocentric Daily Life AI Assistant🔥 We present #EgoLife: a long-context, egocentric, interpersonal, multimodal AI assistant #CVPR2026 - Project: - Paper: - Code: - Demo Hugging Face :

🔥Egocentric Daily Life AI Assistant🔥 We present #EgoLife: a long-context, egocentric, interpersonal, multimodal AI assistant #CVPR2026 - Project: - Paper: - Code: - Demo Hugging Face :

45,882 görüntüleme

We also believe in the power of learning from real human experiences. And Ropedia is here to scale it.

We also believe in the power of learning from real human experiences. And Ropedia is here to scale it.

25,082 görüntüleme

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

🔥🔥We are excited to announce #Vchitect, an open-source project for video generative models Hugging Face 📽️LaVie (Text2Video Model) - Code: - 📽️SEINE (Image2Video Model) - Code: -

🔥🔥We are excited to announce #Vchitect, an open-source project for video generative models Hugging Face 📽️LaVie (Text2Video Model) - Code: - 📽️SEINE (Image2Video Model) - Code: -

356,701 görüntüleme • 2 yıl önce

🍎Thinking with Video towards Law-Grounded Physical Intelligence🍎 🥧Apple-π🥧 is the first benchmark that asks video models to reason through explicit physical laws w/ an auditable test of physical intelligence - Project: - Code:

🍎Thinking with Video towards Law-Grounded Physical Intelligence🍎 🥧Apple-π🥧 is the first benchmark that asks video models to reason through explicit physical laws w/ an auditable test of physical intelligence - Project: - Code:

22,590 görüntüleme • 1 ay önce

🦾Can Vision-Language Models Act Through a Body🦿 🤖HumanCLAW🤖 gives VLM a human body: atomic skills in, real physics out. 🤳Frontier VLM completes just 16.8%: what's missing is embodied *self-body-awareness* - Project: - Paper:

🦾Can Vision-Language Models Act Through a Body🦿 🤖HumanCLAW🤖 gives VLM a human body: atomic skills in, real physics out. 🤳Frontier VLM completes just 16.8%: what's missing is embodied self-body-awareness - Project: - Paper:

18,260 görüntüleme • 1 ay önce

🔥Ultra-Long Video World Model up to 5min🔥 ✨ We introduce #LongVie2, an end-to-end autoregressive video world model that supports continuous video generation lasting up to 5min with: 🕹️ Strong Controllability 📷 Long-term Visual Fidelity 🔒 Temporal Consistency - Project: - Code: - Paper: . Thanks to AK !

🔥Ultra-Long Video World Model up to 5min🔥 ✨ We introduce #LongVie2, an end-to-end autoregressive video world model that supports continuous video generation lasting up to 5min with: 🕹️ Strong Controllability 📷 Long-term Visual Fidelity 🔒 Temporal Consistency - Project: - Code: - Paper: . Thanks to AK !

82,700 görüntüleme • 8 ay önce

🏃Motion Tokenizer Bridging Semantic and Kinematic Conditions🏃‍♀️ #MoTok is a diffusion-based tokenizer that unifies *perception-planning-control*, combining the strengths of continuous diffusion & discrete tokens - Project: - Code:

🏃Motion Tokenizer Bridging Semantic and Kinematic Conditions🏃‍♀️ #MoTok is a diffusion-based tokenizer that unifies perception-planning-control, combining the strengths of continuous diffusion & discrete tokens - Project: - Code:

19,259 görüntüleme • 5 ay önce

🔥Time to Upgrade Your Classifier-Free Guidance🔥 🌠CFG-Zero*🌠 offers consistently better *visual quality* and *text alignment* on text-to-image/video - Project: - Code: - Demo Gradio: . Thanks AK!

🔥Time to Upgrade Your Classifier-Free Guidance🔥 🌠CFG-Zero🌠 offers consistently better visual quality* and text alignment on text-to-image/video - Project: - Code: - Demo Gradio: . Thanks AK!

43,611 görüntüleme • 1 yıl önce

🤖Simulation-Ready Human–Scene Interaction Reconstruction🤖 #HSImul3R reconstructs sim-ready 3D human-scene interactions from casual videos with *physics-in-the-loop* that can be directly deployed to humanoids. - Project: - Code:

🤖Simulation-Ready Human–Scene Interaction Reconstruction🤖 #HSImul3R reconstructs sim-ready 3D human-scene interactions from casual videos with physics-in-the-loop that can be directly deployed to humanoids. - Project: - Code:

15,621 görüntüleme • 5 ay önce

Hugging Face 🌼🌼Inspired by Pika, we use #Vchitect to generate an **AI advertisement video** - "The Feel of Serenity" Demo videos are available on - Youtube YouTube : - Bilibili bilibili : Feel free to contact us: vchitect@pjlab.org.cn

Hugging Face 🌼🌼Inspired by Pika, we use #Vchitect to generate an AI advertisement video - "The Feel of Serenity" Demo videos are available on - Youtube YouTube : - Bilibili bilibili : Feel free to contact us: [email protected]

55,353 görüntüleme • 2 yıl önce

🔥Character AI in VR Space🔥 We present #SOLAMI, a social vision-language-action (VLA) model that enables 3D autonomous characters with *speech and body language* interaction - Project: - Paper Hugging Face : . Thanks AK !

🔥Character AI in VR Space🔥 We present #SOLAMI, a social vision-language-action (VLA) model that enables 3D autonomous characters with speech and body language interaction - Project: - Paper Hugging Face : . Thanks AK !

27,957 görüntüleme • 1 yıl önce

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:

🚀High-Res 3D Text-to-Texture🚀 🎨#MVPaint delivers high-res 3D textures with minimal UV wrapping dependency and high versatility using synchronized multi-view diffusion 📑 Paper: 🏠 Project Page: 🧑‍💻 Code:

28,179 görüntüleme • 1 yıl önce

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

🚀Turn Single Image into 3D Human🚀 #GeneMAN is a generalizable single-image 3D human reconstruction framework that turns in-the-wild images into high-quality 3D humans with ease 🔗Project: 📜Paper: 🧑‍💻Code:

26,953 görüntüleme • 1 yıl önce

🔥Unbounded 4D City Generation🔥 #CityDreamer4D is a generative model of unbounded 4D cities that decouples static and dynamic scenes with realism and controllability - Project: - Code: - CityTopia Dataset:

🔥Unbounded 4D City Generation🔥 #CityDreamer4D is a generative model of unbounded 4D cities that decouples static and dynamic scenes with realism and controllability - Project: - Code: - CityTopia Dataset:

24,326 görüntüleme • 1 yıl önce

🚀Introducing Aero-1-Audio lmms-lab ⚡️Lightweight 1.5B model 💡Outperforms SOTA models like Whisper, Qwen-2-Audio & commercial services from ElevenLabs - Blog: - Code: - Demo Gradio: . Thanks to AK!

🚀Introducing Aero-1-Audio lmms-lab ⚡️Lightweight 1.5B model 💡Outperforms SOTA models like Whisper, Qwen-2-Audio & commercial services from ElevenLabs - Blog: - Code: - Demo Gradio: . Thanks to AK!

17,982 görüntüleme • 1 yıl önce

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards *long-context world model*, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK

🔥1-min Interactive Video Generation with Multimodal Control🔥 Towards long-context world model, #LongVie is an end-to-end autoregressive framework for controllable ultra-long video generation - Page: - Paper: . Thanks AK

14,201 görüntüleme • 1 yıl önce

🔥🔥We propose #VideoBooth to enable **customized video generation** with image prompts, which provide more accurate and direct content control beyond the text prompts. - Project: - Code: - Video:

🔥🔥We propose #VideoBooth to enable customized video generation with image prompts, which provide more accurate and direct content control beyond the text prompts. - Project: - Code: - Video:

26,329 görüntüleme • 2 yıl önce

Daha fazla içerik yok.