Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Paper • 2604.13081 • Published
ZeroGPU Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Q-bert
authored a
paper about 1 month ago
PeterL1n
authored a
paper about 1 month ago
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened about 1 month ago
by 
Reality123b
Why doesn't anyone host llms in zerogpu spaces?
8
#172 opened about 1 month ago
by Reality123b
PeterL1n
authored a
paper about 1 month ago
PeterL1n
submitted a
paper to Daily Papers about 1 month ago
Q-bert
submitted a
paper to Daily Papers about 2 months ago
thecollabagepatch
posted an update 2 months ago
Post
220
just released v3 of gary, the ai plugin for music producers
there's 6 music models inside it now that all do different stuff...
newest models:
ace-step-1.5: get vocals overtop your instrumentals or extend tracks
RoyalCities/Foundation-1: bpm and key-aware synth loops with deep knowledge of fx/timbre
i turn my guitar into bleepy bloops
https://thepatch.gumroad.com/l/gary4juce
i self-host a backend so anyone can use, all open weight models
there's 6 music models inside it now that all do different stuff...
newest models:
ace-step-1.5: get vocals overtop your instrumentals or extend tracks
RoyalCities/Foundation-1: bpm and key-aware synth loops with deep knowledge of fx/timbre
i turn my guitar into bleepy bloops
https://thepatch.gumroad.com/l/gary4juce
i self-host a backend so anyone can use, all open weight models
mapooon
authored a
paper 2 months ago
Q-bert
authored a
paper 2 months ago
BestWishYsh
authored a
paper 3 months ago
BestWishYsh
posted an update 3 months ago
Post
3725
🚀 Introducing Helios: a 14B real-time long-video generation model!
It’s completely wild—faster than 1.3B models and achieves this without using self-forcing. Welcome to the new era of video generation! 😎👇
💻 Code: https://github.com/PKU-YuanGroup/Helios
🏠 Page: https://pku-yuangroup.github.io/Helios-Page
📄 Paper: Helios: Real Real-Time Long Video Generation Model (2603.04379)
🔹 True Single-GPU Extreme Speed ⚡️
No need to rely on traditional workarounds like KV-cache, quantization, sparse/linear attention, or TinyVAE. Helios hits an end-to-end 19.5 FPS on a single H100!
Training is also highly accessible: an 80GB VRAM can fit four 14B models.
🔹 Solving Long-Video "Drift" from the Core 🎥
Tired of visual drift and repetitive loops? We ditched traditional hacks (like error banks, self-forcing, or keyframe sampling).
Instead, our innovative training strategy simulates & eliminates drift directly, keeping minute-long videos incredibly coherent with stunning quality. ✨
🔹 3 Model Variants for Full Coverage 🛠️
With a unified architecture natively supporting T2V, I2V, and V2V, we are open-sourcing 3 flavors:
1️⃣ Base: Single-stage denoising for extreme high-fidelity.
2️⃣ Mid: Pyramid denoising + CFG-Zero for the perfect balance of quality & throughput.
3️⃣ Distilled: Adversarial Distillation (DMD) for ultra-fast, few-step generation.
🔹 Day-0 Ecosystem Ready 🌍
We wanted deployment to be a breeze from the second we launched. Helios drops with comprehensive Day-0 hardware and framework support:
✅ Huawei Ascend-NPU
✅ HuggingFace Diffusers
✅ vLLM-Omni
✅ SGLang-Diffusion
Try it out and let us know what you think!
It’s completely wild—faster than 1.3B models and achieves this without using self-forcing. Welcome to the new era of video generation! 😎👇
💻 Code: https://github.com/PKU-YuanGroup/Helios
🏠 Page: https://pku-yuangroup.github.io/Helios-Page
📄 Paper: Helios: Real Real-Time Long Video Generation Model (2603.04379)
🔹 True Single-GPU Extreme Speed ⚡️
No need to rely on traditional workarounds like KV-cache, quantization, sparse/linear attention, or TinyVAE. Helios hits an end-to-end 19.5 FPS on a single H100!
Training is also highly accessible: an 80GB VRAM can fit four 14B models.
🔹 Solving Long-Video "Drift" from the Core 🎥
Tired of visual drift and repetitive loops? We ditched traditional hacks (like error banks, self-forcing, or keyframe sampling).
Instead, our innovative training strategy simulates & eliminates drift directly, keeping minute-long videos incredibly coherent with stunning quality. ✨
🔹 3 Model Variants for Full Coverage 🛠️
With a unified architecture natively supporting T2V, I2V, and V2V, we are open-sourcing 3 flavors:
1️⃣ Base: Single-stage denoising for extreme high-fidelity.
2️⃣ Mid: Pyramid denoising + CFG-Zero for the perfect balance of quality & throughput.
3️⃣ Distilled: Adversarial Distillation (DMD) for ultra-fast, few-step generation.
🔹 Day-0 Ecosystem Ready 🌍
We wanted deployment to be a breeze from the second we launched. Helios drops with comprehensive Day-0 hardware and framework support:
✅ Huawei Ascend-NPU
✅ HuggingFace Diffusers
✅ vLLM-Omni
✅ SGLang-Diffusion
Try it out and let us know what you think!
- 6 replies
BK-Lee
authored a
paper 3 months ago
BK-Lee
submitted a
paper to Daily Papers 3 months ago
Zhengyi
authored a
paper 3 months ago
Post
5663
My USB charger has a Blackwell GPU and 128GB RAM.
What. A. Time. To. Be. Alive.
People in Sofia: “It’s freezing.”
Me: sitting next to 3kW of space AI heaters on my desk 👀
1x GLM-5, 2x MiniMax-M2.5, 1x Qwen3 Coder Next; all on single Aibrix/K8s cluster
What. A. Time. To. Be. Alive.
People in Sofia: “It’s freezing.”
Me: sitting next to 3kW of space AI heaters on my desk 👀
1x GLM-5, 2x MiniMax-M2.5, 1x Qwen3 Coder Next; all on single Aibrix/K8s cluster
- 6 replies
mariagrandury
authored 2
papers 3 months ago
Post
537
134,614 tok/sec input prefil max
1031 tokens/sec out gen max
At these local AI speeds, there is no User Interface for humans. My human UI is the Radicle distributed Git issues queue
On my GPU workstation:
- Z8 Fury G5 4x A6000
- MiniMax-M2.5
- Claude Code to localhost:8000
1031 tokens/sec out gen max
At these local AI speeds, there is no User Interface for humans. My human UI is the Radicle distributed Git issues queue
On my GPU workstation:
- Z8 Fury G5 4x A6000
- MiniMax-M2.5
- Claude Code to localhost:8000
- 1 reply
Post
4835
I just pushed Claude Code Agent Swarm with 20 coding agents on my desktop GPU workstation.
With local AI, I don’t have /fast CC switch, but I have /absurdlyfast:
- 100’499 tokens/second read, yeah 100k, not a typo | 811 tok/sec generation
- KV cache: 707’200 tokens
- Hardware: 5+ year old GPUs 4xA6K gen1; It’s not the car. It’s the driver.
Qwen3 Coder Next AWQ with cache at BF16. Scores 82.1% in C# on 29-years-in-dev codebase vs Opus 4.5 at only 57.5%. When your codebase predates Stack Overflow, you don't need the biggest model; you need the one that actually remembers Windows 95.
My current bottleneck is my 27" monitor. Can't fit all 20 Theos on screen without squinting.
With local AI, I don’t have /fast CC switch, but I have /absurdlyfast:
- 100’499 tokens/second read, yeah 100k, not a typo | 811 tok/sec generation
- KV cache: 707’200 tokens
- Hardware: 5+ year old GPUs 4xA6K gen1; It’s not the car. It’s the driver.
Qwen3 Coder Next AWQ with cache at BF16. Scores 82.1% in C# on 29-years-in-dev codebase vs Opus 4.5 at only 57.5%. When your codebase predates Stack Overflow, you don't need the biggest model; you need the one that actually remembers Windows 95.
My current bottleneck is my 27" monitor. Can't fit all 20 Theos on screen without squinting.
- 3 replies