Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation acceleration with semantic-aware sparse attention! 🏆Spotlight paper accepted by #NeurIPS2025 ✅ Training-free & plug-and-play ✅ Up to 2.5× faster on HunyuanVideo, 1.9× faster on Wan 2.1 ✅ SOTA quality preserved (no artifacts, no flickering, no distortion) 📚Paper: 💻Code: 🌐Website: ⚡Attention... show more

Haocheng Xi

1,621 subscribers

43,470 views • 1 year ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

NVIDIA released Sol-Attn A training-free sparse attention method accelerating video generation inference by up to 2.1× while preserving visual quality, unifying dynamic routing and approximate correction in a single online-softmax pass.

NVIDIA released Sol-Attn A training-free sparse attention method accelerating video generation inference by up to 2.1× while preserving visual quality, unifying dynamic routing and approximate correction in a single online-softmax pass.

DailyPapers

23,144 views • 2 months ago

🚀 Sol Video Inference Engine is here! An agent-native, training-free full-stack accelerator for video diffusion. It auto-tunes cache + sparse attn + token pruning + quant + kernel fusion for any model/hardware/config. >2× end-to-end speedup on 64B Cosmos3-Super, 22B LTX-2.3 and 2B SANA-Video — near-lossless VBench quality, minimal human effort. Practical acceleration for real video gen deployment. 📄 Paper: 🌐 Project: 💻 Code: Proud of the team! 🎉

🚀 Sol Video Inference Engine is here! An agent-native, training-free full-stack accelerator for video diffusion. It auto-tunes cache + sparse attn + token pruning + quant + kernel fusion for any model/hardware/config. >2× end-to-end speedup on 64B Cosmos3-Super, 22B LTX-2.3 and 2B SANA-Video — near-lossless VBench quality, minimal human effort. Practical acceleration for real video gen deployment. 📄 Paper: 🌐 Project: 💻 Code: Proud of the team! 🎉

Enze Xie

36,698 views • 3 months ago

Introducing DeepConf: Deep Think with Confidence 🚀 First method to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens. It also delivers many strong advantages for parallel thinking: 🔥 Performance boost: ~10% accuracy across models & datasets ⚡ Ultra-efficient: Up to 85% fewer tokens generated 🔧 Plug & play: Works with ANY existing model - zero training needed (no hyperparameter tuning as well!) ⭐ Easy to deploy: Just ~50 lines of code in vLLM (see PR below) 📚 Paper: 🌐 Project: joint work with: Yichao Fu , xuewei_wang, Yuandong Tian (see details in the comments below)

Introducing DeepConf: Deep Think with Confidence 🚀 First method to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens. It also delivers many strong advantages for parallel thinking: 🔥 Performance boost: ~10% accuracy across models & datasets ⚡ Ultra-efficient: Up to 85% fewer tokens generated 🔧 Plug & play: Works with ANY existing model - zero training needed (no hyperparameter tuning as well!) ⭐ Easy to deploy: Just ~50 lines of code in vLLM (see PR below) 📚 Paper: 🌐 Project: joint work with: Yichao Fu , xuewei_wang, Yuandong Tian (see details in the comments below)

Jiawei Zhao

464,995 views • 1 year ago

Wan-Animate-2 pushes character animation beyond pose-driven pipelines: reference image + driving video in, cleaner character motion out. 🚀 🤖 🌐 🏆 Blind user study: preferred over Wan-Animate in 70%+ of overall-quality comparisons, with perceived quality comparable to Dreamina and Kling-MotionControl. 🎬 Cleaner animation: directly processes driving-video motion instead of relying on pose skeletons, reducing identity drift, artifacts, and shape distortion across different characters. 🎥 Text camera control: Viewpoint LoRA lets prompts steer the output perspective while keeping the original motion consistent. ⚡ Streaming path: Wan-Animate-2-Lite reports 24fps at 400x720, with stable long-sequence generation for live avatars and interactive virtual environments. Built with dual-branch DiT, Time-Align RoPE, Sparse-Ref Attention, 100K+ video pairs, and 50K Unreal Engine multi-view samples.

Wan-Animate-2 pushes character animation beyond pose-driven pipelines: reference image + driving video in, cleaner character motion out. 🚀 🤖 🌐 🏆 Blind user study: preferred over Wan-Animate in 70%+ of overall-quality comparisons, with perceived quality comparable to Dreamina and Kling-MotionControl. 🎬 Cleaner animation: directly processes driving-video motion instead of relying on pose skeletons, reducing identity drift, artifacts, and shape distortion across different characters. 🎥 Text camera control: Viewpoint LoRA lets prompts steer the output perspective while keeping the original motion consistent. ⚡ Streaming path: Wan-Animate-2-Lite reports 24fps at 400x720, with stable long-sequence generation for live avatars and interactive virtual environments. Built with dual-branch DiT, Time-Align RoPE, Sparse-Ref Attention, 100K+ video pairs, and 50K Unreal Engine multi-view samples.

ModelScope

25,884 views • 1 month ago

pip install spectralquant ✂️ Up to 6.62x KV cache compression for LLMs and transformers. Same model. Faster outputs. Smaller KV cache. Try now (2 mins): - KV cache integration via Hugging Face's DynamicCache - Three presets: 5.95x (paper), 6.55x (validated), 6.68x (edge) - Mistral 7B / Qwen 2.5 7B / Llama 3.1 8B verified - Pure PyTorch + future CUDA kernel support - Auto-calibration from a bundled corpus 📰 Paper: 💻 Code, quickstart, and benchmarks: #LLM #Inference #PyTorch #OpenSource #MachineLearning #LLM #KVCache #Inference

pip install spectralquant ✂️ Up to 6.62x KV cache compression for LLMs and transformers. Same model. Faster outputs. Smaller KV cache. Try now (2 mins): - KV cache integration via Hugging Face's DynamicCache - Three presets: 5.95x (paper), 6.55x (validated), 6.68x (edge) - Mistral 7B / Qwen 2.5 7B / Llama 3.1 8B verified - Pure PyTorch + future CUDA kernel support - Auto-calibration from a bundled corpus 📰 Paper: 💻 Code, quickstart, and benchmarks: #LLM #Inference #PyTorch #OpenSource #MachineLearning #LLM #KVCache #Inference

ani

17,269 views • 4 months ago

🚀 Introducing CodeWarp: Jump to Definition with MicroGPT! 🚀 No more endless scrolling—CodeWarp lets you instantly navigate to function, variable, and class definitions with ease. Code faster, smarter, and more efficiently! ⚡

🚀 Introducing CodeWarp: Jump to Definition with MicroGPT! 🚀 No more endless scrolling—CodeWarp lets you instantly navigate to function, variable, and class definitions with ease. Code faster, smarter, and more efficiently! ⚡

MicroGPT

213,368 views • 1 year ago

🎥 Video generation is hitting the memory wall. As videos get longer, the KV cache quietly explodes — and long-horizon consistency starts to break. We built Quant VideoGen: a training-free KV cache compression method for auto-regressive video diffusion. Instead of storing every KV in high precision, QVG exploits video’s spatiotemporal redundancy with semantic-aware smoothing + progressive residual quantization. 🚀 Up to 7× KV memory reduction ⚡ <4% overhead ✅ Strong long-video quality 🕹️ Deploy HYWorldPlay on your own RTX 5090 locally KV compression is becoming a core scaling primitive — not just for LLMs, but for video generation too. Paper: Code: (1/5)

🎥 Video generation is hitting the memory wall. As videos get longer, the KV cache quietly explodes — and long-horizon consistency starts to break. We built Quant VideoGen: a training-free KV cache compression method for auto-regressive video diffusion. Instead of storing every KV in high precision, QVG exploits video’s spatiotemporal redundancy with semantic-aware smoothing + progressive residual quantization. 🚀 Up to 7× KV memory reduction ⚡ <4% overhead ✅ Strong long-video quality 🕹️ Deploy HYWorldPlay on your own RTX 5090 locally KV compression is becoming a core scaling primitive — not just for LLMs, but for video generation too. Paper: Code: (1/5)

Haocheng Xi 🚗 COLM

65,800 views • 5 months ago

🚀 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： Hugging Face： Project Page：

🚀 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： Hugging Face： Project Page：

Meituan LongCat

43,828 views • 11 months ago

Attention fellow YouTube creators! Launching TubeToolkit in beta 🚀 Built in ~72 hours with Claude Code. It turns your video transcript into the full supporting content package (titles, timestamps, description, hooks, thumbnail ideas) so you can publish faster and stay on-brand. ✅ Free credits to start ✅ No credit card required 💳 Paid tiers available if you want to scale Sign up today: If you’re testing + giving useful feedback and you run out of credits, DM/reply — let me know.

Branden Flasch

17,286 views • 8 months ago

We have released the code and weights for our #CVPR2023 paper "Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model"! code: abs: project: The demo is below:

We have released the code and weights for our #CVPR2023 paper "Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model"! code: abs: project: The demo is below:

Artsiom Sanakoyeu

35,715 views • 3 years ago

New freemint collection coming right up! 🛸 Locus Fleet: Special Proto Craft 🛸 ✅ No FCFS, No Public, Whitelist Only! ✅ 350 confirmed collabs and more on the way! ✅ Many opportunities to secure your whitelist spot! Mint Details: 📦 Amount: 4,500 WL 🪙 Price: FREE 🌐 Chain: Polygon 📅 Date: September 26, 2024 🚀 Launchpad: Space Mavericks Website

New freemint collection coming right up! 🛸 Locus Fleet: Special Proto Craft 🛸 ✅ No FCFS, No Public, Whitelist Only! ✅ 350 confirmed collabs and more on the way! ✅ Many opportunities to secure your whitelist spot! Mint Details: 📦 Amount: 4,500 WL 🪙 Price: FREE 🌐 Chain: Polygon 📅 Date: September 26, 2024 🚀 Launchpad: Space Mavericks Website

Gravity Blasters

42,226 views • 2 years ago

⚡ Want to help your athlete get faster? Single-Leg Pogo Hops improve: ✅ Speed ✅ Balance ✅ Explosiveness ✅ Coordination The goal: spend less time on the ground and more time moving. 3 sets of 15-20 hops per leg before training. Train smart. Get faster. ⚡ #SpeedTraining

⚡ Want to help your athlete get faster? Single-Leg Pogo Hops improve: ✅ Speed ✅ Balance ✅ Explosiveness ✅ Coordination The goal: spend less time on the ground and more time moving. 3 sets of 15-20 hops per leg before training. Train smart. Get faster. ⚡ #SpeedTraining

USG

42,841 views • 3 months ago

⚡ Video diffusion is slow. PDD changes that. 🚀 Introducing Parallel Decoding Distillation, our latest work on accelerating video diffusion models. Paper: Page: By Neta Shaul, Julius Berner, and Chao Liu. Below PDD on LTX-2.3 🔊

⚡ Video diffusion is slow. PDD changes that. 🚀 Introducing Parallel Decoding Distillation, our latest work on accelerating video diffusion models. Paper: Page: By Neta Shaul, Julius Berner, and Chao Liu. Below PDD on LTX-2.3 🔊

Arash Vahdat

21,483 views • 2 months ago

I tried Kijai's latest INT8 VAE for Minimax H3 Its 2.3x faster with no visible quality loss! Details below👇

I tried Kijai's latest INT8 VAE for Minimax H3 Its 2.3x faster with no visible quality loss! Details below👇

Kent Dhani

40,240 views • 11 days ago

Can robots learn without training❓ [𝗜𝘁'𝘀 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 ⬇ ] Teaching robots to do complex tasks WITHOUT spending hours training them. Sounds cool, right? That's exactly what DIAL-MPC does! The first training-free method for whole-body torque control using full-order dynamics: ✅ Instantly checks if a robot's moves are right or wrong ✅ Adapts quickly to new tasks without needing extra training ✅ Could work hand-in-hand with other robot learning methods Robots are getting smarter AND faster without the need for long training sessions. Website: Paper: Code: Saw this first Haoru Xue 🙏

Can robots learn without training❓ [𝗜𝘁'𝘀 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲𝗱 ⬇ ] Teaching robots to do complex tasks WITHOUT spending hours training them. Sounds cool, right? That's exactly what DIAL-MPC does! The first training-free method for whole-body torque control using full-order dynamics: ✅ Instantly checks if a robot's moves are right or wrong ✅ Adapts quickly to new tasks without needing extra training ✅ Could work hand-in-hand with other robot learning methods Robots are getting smarter AND faster without the need for long training sessions. Website: Paper: Code: Saw this first Haoru Xue 🙏

Ilir Aliu

71,540 views • 1 year ago

Can $300 RTX3060 be faster than $10,000 A100 for LLM decoding?🧐Yes Introduce EAGLE-2: - 4.26x🚀vanilla (13B) - 1.4x🚀EAGLE (13B) - No extra training than EAGLE - Maintain distribution Paper: Code: Demo:

Can $300 RTX3060 be faster than $10,000 A100 for LLM decoding?🧐Yes Introduce EAGLE-2: - 4.26x🚀vanilla (13B) - 1.4x🚀EAGLE (13B) - No extra training than EAGLE - Maintain distribution Paper: Code: Demo:

Hongyang Zhang

35,696 views • 2 years ago

If you're constantly creating video content, every second and every credit count. Dreamina Seedance 2.0 Mini helps streamline the creative process with faster generation speeds and lower costs while delivering the quality needed for professional projects. From marketing campaigns to social media content and cinematic edits, it makes high-quality video creation more efficient than ever. Key highlights: ✅ Around 30% cheaper than Seedance 2.0 ✅ 2× faster generation ✅ Comparable output quality ✅ Built for creators who want more productivity Try now 👇 #Seedance2Mini #CapCut

If you're constantly creating video content, every second and every credit count. Dreamina Seedance 2.0 Mini helps streamline the creative process with faster generation speeds and lower costs while delivering the quality needed for professional projects. From marketing campaigns to social media content and cinematic edits, it makes high-quality video creation more efficient than ever. Key highlights: ✅ Around 30% cheaper than Seedance 2.0 ✅ 2× faster generation ✅ Comparable output quality ✅ Built for creators who want more productivity Try now 👇 #Seedance2Mini #CapCut

𝐇𝐨𝐧𝐞𝐲

11,630 views • 3 months ago

✅ Rewind on mobile ✅ 2x faster ✅ Wont melt your phone Kick app 3.0 now live 🚀

✅ Rewind on mobile ✅ 2x faster ✅ Wont melt your phone Kick app 3.0 now live 🚀

KICK

510,223 views • 1 year ago