ACC: Compiling Agent Trajectories for Long-Context Training
Paper β’ 2605.21850 β’ Published β’ 56
ZeroGPU Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Lin-ChenΒ
authored a
paper 1 day ago
Lin-ChenΒ
authored 3
papers 11 days ago
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph
Paper β’ 2602.12735 β’ Published β’ 8
Flow-OPD: On-Policy Distillation for Flow Matching Models
Paper β’ 2605.08063 β’ Published β’ 97
SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation
Paper β’ 2605.08043 β’ Published β’ 10
Aurelien-MorganΒ
posted an update 19 days ago
Post
1057
@retrain-pipelines v0.2.0 is out !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
I'm at Station F at My booth with GOSIM Paris 2026 today & tomorrow.
Come meet me for a live in-person demo and a chat !
- 1 reply
Post
1812
Big update to llm-datasets, my curated list of datasets and tools for post-training LLMs.
> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.
Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
> Added many new datasets
> New "thinking" column
> Refreshed recommended tools.
Thanks to everyone who told me they used it for their research at ICLR, you motivated this update!
- 2 replies
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
Aurelien-MorganΒ
posted an update about 1 month ago
Post
2748
Avatars are everywhere, but here is the reality behind full-system marketing automation. π
Many see "Madame AI" simply as an AI news presenter. She is far deeper than that. Madame AI is a Real-time Agentic AI Assistant we developed to orchestrate entire workflows for marketing and professional media. She manages UGC (User-Generated Content), understands marketing system automation intuitively, and handles complex media tasks.
We have solved the character consistency and high production cost bottlenecks that traditionally required immense training and time. By precisely orchestrating every computational step behind videos and branded designs, we have fully automated the pipeline and significantly reduced costs.
This capability is built on our extensive experience managing large-scale automation projects with complex requirement documentation (PRD).
Grabclip is our public portal and the practical result of that journey. It is the interface where "Madame AI" acts as the intelligent engine.
We have spent three years building this pipeline with a clear goal: a 100% local, end-to-end solution that operates despite external restrictions.
See the live example on YouTube (our fast-paced AI news podcast with Madame AI) and try the automation portal yourselfπ
πΊ The Playlist: https://www.youtube.com/playlist?list=PLwEbW4bdYBSCVSziFfJYq4zXop_cyHquO
π Our Portal (Grabclip) β The first practical step in our pipeline: https://grabclip.bilsimaging.com/
hashtag#AgenticAI hashtag#VirtualInfluencer hashtag#FutureOfWork hashtag#GenerativeAI hashtag#TunisiaTech hashtag#MarketingAutomation hashtag#100PercentLocal hashtag#OSMedia hashtag#Grabclip hashtag#RealTimeAssistant hashtag#UGC hashtag#ProfessionalMedia hashtag#TunisiaAI
Many see "Madame AI" simply as an AI news presenter. She is far deeper than that. Madame AI is a Real-time Agentic AI Assistant we developed to orchestrate entire workflows for marketing and professional media. She manages UGC (User-Generated Content), understands marketing system automation intuitively, and handles complex media tasks.
We have solved the character consistency and high production cost bottlenecks that traditionally required immense training and time. By precisely orchestrating every computational step behind videos and branded designs, we have fully automated the pipeline and significantly reduced costs.
This capability is built on our extensive experience managing large-scale automation projects with complex requirement documentation (PRD).
Grabclip is our public portal and the practical result of that journey. It is the interface where "Madame AI" acts as the intelligent engine.
We have spent three years building this pipeline with a clear goal: a 100% local, end-to-end solution that operates despite external restrictions.
See the live example on YouTube (our fast-paced AI news podcast with Madame AI) and try the automation portal yourselfπ
πΊ The Playlist: https://www.youtube.com/playlist?list=PLwEbW4bdYBSCVSziFfJYq4zXop_cyHquO
π Our Portal (Grabclip) β The first practical step in our pipeline: https://grabclip.bilsimaging.com/
hashtag#AgenticAI hashtag#VirtualInfluencer hashtag#FutureOfWork hashtag#GenerativeAI hashtag#TunisiaTech hashtag#MarketingAutomation hashtag#100PercentLocal hashtag#OSMedia hashtag#Grabclip hashtag#RealTimeAssistant hashtag#UGC hashtag#ProfessionalMedia hashtag#TunisiaAI
vinesmsuicΒ
authored a
paper about 2 months ago
vinesmsuicΒ
submitted a
paper to Daily Papers about 2 months ago
BestWishYshΒ
authored a
paper 3 months ago
BestWishYshΒ
posted an update 3 months ago
Post
3712
π Introducing Helios: a 14B real-time long-video generation model!
Itβs completely wildβfaster than 1.3B models and achieves this without using self-forcing. Welcome to the new era of video generation! ππ
π» Code: https://github.com/PKU-YuanGroup/Helios
π Page: https://pku-yuangroup.github.io/Helios-Page
π Paper: Helios: Real Real-Time Long Video Generation Model (2603.04379)
πΉ True Single-GPU Extreme Speed β‘οΈ
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.
πΉ Solving Long-Video "Drift" from the Core π₯
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. β¨
πΉ 3 Model Variants for Full Coverage π οΈ
With a unified architecture natively supporting T2V, I2V, and V2V, we are open-sourcing 3 flavors:
1οΈβ£ Base: Single-stage denoising for extreme high-fidelity.
2οΈβ£ Mid: Pyramid denoising + CFG-Zero for the perfect balance of quality & throughput.
3οΈβ£ Distilled: Adversarial Distillation (DMD) for ultra-fast, few-step generation.
πΉ Day-0 Ecosystem Ready π
We wanted deployment to be a breeze from the second we launched. Helios drops with comprehensive Day-0 hardware and framework support:
β Huawei Ascend-NPU
β HuggingFace Diffusers
β vLLM-Omni
β SGLang-Diffusion
Try it out and let us know what you think!
Itβs completely wildβfaster than 1.3B models and achieves this without using self-forcing. Welcome to the new era of video generation! ππ
π» Code: https://github.com/PKU-YuanGroup/Helios
π Page: https://pku-yuangroup.github.io/Helios-Page
π Paper: Helios: Real Real-Time Long Video Generation Model (2603.04379)
πΉ True Single-GPU Extreme Speed β‘οΈ
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.
πΉ Solving Long-Video "Drift" from the Core π₯
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. β¨
πΉ 3 Model Variants for Full Coverage π οΈ
With a unified architecture natively supporting T2V, I2V, and V2V, we are open-sourcing 3 flavors:
1οΈβ£ Base: Single-stage denoising for extreme high-fidelity.
2οΈβ£ Mid: Pyramid denoising + CFG-Zero for the perfect balance of quality & throughput.
3οΈβ£ Distilled: Adversarial Distillation (DMD) for ultra-fast, few-step generation.
πΉ Day-0 Ecosystem Ready π
We wanted deployment to be a breeze from the second we launched. Helios drops with comprehensive Day-0 hardware and framework support:
β Huawei Ascend-NPU
β HuggingFace Diffusers
β vLLM-Omni
β SGLang-Diffusion
Try it out and let us know what you think!
- 6 replies
mpatel57Β
authored a
paper 3 months ago
mariagranduryΒ
authored 2
papers 3 months ago
vinesmsuicΒ
authored a
paper 3 months ago
Lin-ChenΒ
authored 2
papers 4 months ago