Yong Norris Zhang

[Yong Norris Zhang @Norris29973102]

We opensource OPSD-V, a method for long video generation.

🚀 We propose on-policy self-distillation for few-step AR video generators, using real long-video context to reduce long-horizon degradation while preserving fast inference.

https://t.co/JIHAPLNLAE

[Hongyu LIU @Kumapower1]

Excited to share OPSD-V! 🚀

We propose on-policy self-distillation for few-step AR video generators, using real long-video context to reduce long-horizon degradation while preserving fast inference.

Project: https://t.co/sOMQJTL5MV
Code: https://t.co/KeldaSA2gW

[Meituan LongCat @Meituan_LongCat]

Introducing LongCat-2.0 🐱
1.6T parameters · MoE with ~48B active · 1M context
The full model behind Owl Alpha on @OpenRouter — now available.

Built for agentic coding from the ground up:
◆ LongCat Sparse Attention (LSA) — scales efficiently for 1M-context tokens
◆ Zero-Compute Experts — dynamic activation 33B–56B per token, zero wasted compute
◆ MOPD — three specialized expert groups (Agent / Reasoning / Interaction), gate-routed per task

How it stacks up:
→ Terminal-Bench 2.1: 70.8
→ SWE-bench Pro: 59.5 (GPT-5.5: 58.6)
→ SWE-bench Multilingual: 77.3
→ FORTE: 73.2 · RWSearch: 78.8 · BrowseComp: 79.9

📖 Tech Blog: https://t.co/4KrjyKiDBn
Try it across different scenarios 🧵👇

[Yong Norris Zhang @Norris29973102]

@Artyom17285124 @Meituan_LongCat the backbone is LongCat-Video

[Meituan LongCat @Meituan_LongCat]

Meet LongCat-Video-Avatar 1.5🐱—our upgraded, open-source digital human framework.

Built for real production, not just short demos.

What's New:
🔹 Upgraded Audio Encoder: Replaces Wav2Vec2 with Whisper-Large, yielding significantly smoother and more natural lip dynamics.
🔹 Production-Ready Stability: Achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency.
🔹 Stylized Domain Generalization: Robustly generalizes to anime, animals, and complex real-world conditions such as multi-person interactions and object handling.
🔹 Efficient 8-Step Inference: Advanced step distillation accelerates inference to 8 NFE, balancing cost-effective serving with exceptional visual fidelity.

📊 LongCat-Video-Avatar 1.5 performs strongly in realism, naturalness, and stability, outperforming leading open-source models and closed systems.
🐱 Avatar 1.5 framework is now open source:

🔗 Weights & Code:https://t.co/b9fVxTLaPs
🔗 HuggingFace: https://t.co/s4GjqxuAA2
🔗 Tech Report: https://t.co/noSnB7aFCh
🔗 Project Page: https://t.co/CCeRcWgRpl

[AYi @AYi_AInotes]

有条件一定要用最好的AI大模型Claude，用opus 4.6！
这个印度开发老哥把Claude代码功能讲的太细了，
中文字幕版已做好，兄弟们请查收！
每个程序员和AI玩家都应该知道的12个Claude代码功能：
- CLAUDE.md
- Permissions
- Plan Mode
- Checkpoints
- Skills
- Hooks
- MCP
- Plugins
- Context
- Slash Commands
- Compaction
- Subagents

[Yong Norris Zhang @Norris29973102]

🚀 News: Infinite-World – interactive world model w/ 1,000+ frame coherent sim in complex real envs!

🔑 Key Innovations:
✅ Hierarchical Pose-free Memory Compressor
✅ Uncertainty-aware Action Labeling
✅ Revisit-Dense Finetuning
https://t.co/2NuL9Z3jiM

[ModelScope @ModelScope2022]

🔥 New on ModelScope: LongCat-Video-Avatar!
We are thrilled to welcome this unified model for expressive, audio-driven character animation to our community. 🚀

Why you should try it:
✨ Versatile: Handles AT2V, Image-to-Video, & Video Continuation.
✨ Natural Dynamics: Decouples speech from motion for realistic results.
✨ High Quality: Uses "Reference Skip Attention" to preserve identity.
✨ Long Sequences: Minimal pixel degradation via innovative stitching.

👉 Download & Try it here: https://t.co/xFPBFuAZM8

[Meituan LongCat @Meituan_LongCat]

Meet LongCat-Video-Avatar: a robust audio-driven avatar model that pushes the boundaries of long-form video generation.

Compared with the previous InfiniteTalk, LongCat-Video-Avatar delivers far better long-sequence stability and realism.

New highlights：
⚙ Built on the LongCat-Video architecture, now supporting Audio-Text-to-Video (AT2V), Audio-Text-Image-to-Video (ATI2V), and Video Continuation modes.
🎭 Open-source SOTA Realism: Ranked 1st in overall anthropomorphism scores for both single and multi-subject scenarios in EvalTalker evaluations (492 participants, 3 independent raters per video).
♾ High-quality long videos: Cross-Chunk Latent Stitching prevents pixel degradation and error accumulation over time, ensuring seamless stitching quality.
🔒 Long-term consistency: Reference Skip Attention maintains ID consistency while eliminating rigid copy-paste artifacts.
🪄 Supports multi-person and infinite-length video generation.

🔗Open-sourced
Code: https://t.co/b9fVxTLaPs
Hugging Face: https://t.co/TI7miIswgI
Project: https://t.co/tkUpZKSKhU
Paper: https://t.co/SO8YBXcNzm

[LTX @ltx_model]

AI video isn’t a clip anymore. It’s a scene.

LTX-2 now generates 20-second continuous, synchronized audio and video. One cinematic take from a single prompt.

Available now on LTX API Playground!

Examples with prompts + a link to try it now in the thread >>

[Hasan Toor @hasantoxr]

Say goodbye to 8 second AI videos.

LTX-2 can create full 20-second movies from just one sentence, with matching sound, clear faces, and movie-like timing.

I tried it and felt like I was watching a real movie.

Here are 10 most impressive examples:

[Md Riyazuddin @riyazmd774]

🚨 RIP ElevenLabs

Sonic 3's AI voice so natural, even Elon Musk noticed.

-40ms response (ElevenLabs: 130ms)
-Native accents, 42 languages
-Real-time speed + volume control
First voice AI that works on enterprise scale.

What makes it insane:👇

[Meituan LongCat @Meituan_LongCat]

🚀 LongCat-Video Now Open-Source: Text/Image-to-Video + Video Continuation in One Model
🏆 Text/Image-to-Video Performance Hits Open-Source SOTA
🎬 Minutes-Long High-Quality Videos: No Color Drift/Quality Loss (Industry-Standout)
⚙ 13.6B Params | Strong Open-Source DiT-Based Unified Multitask Video Base Model
⚡ C2F Pipeline + Block Sparse Attention: 720p/30fps Video in Minutes
🤗 Open-Source Links:
GitHub：https://t.co/b9fVxTLaPs
Hugging Face：https://t.co/TX1k7hmcZg
Project Page：https://t.co/aRrGjchQAh

[Vaibhav (VB) Srivastav @reach_vb]

Chinese doordash dropping MIT license foundation video models???

“We introduce LongCat-Video, a foundational video generation model with 13.6B parameters, delivering strong performance across Text-to-Video, Image-to-Video, and Video-Continuation generation tasks.”

https://t.co/jPTY2Uac1S

[WaveSpeedAI @wavespeed_ai]

🚀 Models BATTLE!
🎬 Infinitetalk vs. Kling-v1 vs. Omnihuman, who is the BEST AI Avatar model?
I tested Infinitetalk, Kling-v1, and Omnihuman using the same video. Here's how they compare:
✨ Infinitetalk shines with crystal-clear, natural-sounding voices.
💥 Kling-v1 impresses with avatar creation.
⚡ Omnihuman excels in avatar design.
👉 https://t.co/TeUW6tjPCE
👉 https://t.co/v4M9AWSDzN
👉 https://t.co/76riZxkSP8
#AIAvatars #VoiceGeneration #Infinitetalk #AItools #KlingV1 #Omnihuman #AIrevolution

[Yong Norris Zhang @Norris29973102]

@crapthings @wavespeed_ai Yes, quite strange.

[Yong Norris Zhang @Norris29973102]

@willowion I leaved a comment on this issue. Please check whether it is the same problem.

[Rourke Heath @rourke_heath]

How to AI lip sync on top of videos 🤯 this is INSANE!!

Here are the links: https://t.co/qqGVvNy3Pa

Creative AI Education With Rourke:

https://t.co/vGem7Yj24O

#InfiniteTalk #AIVideoGenerator #AILipSync #AIVoiceToVideo #GenerativeAI #CreativeAI #AIForCreators #AIForMarketers

[LUTA＠AI @luta_ai]

🔥ローカル生成＋nanobananaで3分20秒の長尺MVを3日で完成！🔊🎵
1枚の画像から差分を量産し、InfiniteTalkでリップシンク。
曲を仕上げてから実質2日でフルバージョンに到達🎉

正直、普通に動画を繋ぐだけなら長尺も作れる。
でも――「歌詞に合わせた意図的な演出」を入れようとすると、これまでは生成可能なレベルを探しつつ運要素も強く、せいぜい1分ぐらいが演出の限界だった💦

nanobananaは実写だと揺らぎが大きく差分に違和感も出やすいが、何度も調整してある程度まで形にできた。NGカットも“意図的に外す”段階に入れた結果、演出意図を通したままフル尺に到達。
なおリップ以外のカットはwan2.2で生成。

運任せではなく「狙って作る」段階に踏み込めたのは大きな前進です💡

これならNDAリスクも大幅に緩和できそう。
ただしアップデートで壊れやすいので、環境は必ず分けて管理した方がいいかも😊

#nanobanana #ComfyUI

[とっしい@じぞまえ @jizomae]

「はいこんにちはー！」
InfiniteTalk Multiで３人は予想した通り左も右も関係なくなりました。
つまり使えない。
そこで、KLINGを使って改めて３人分（15秒以内ごとにクリップ）のLipSyncを行ないカタチにしました。