AK
@_akhaliq
AI research paper tweets, ML @Gradio (acq. by @HuggingFace ๐ค) dm for promo ,submit papers here:
3.1K Following 528.3K Followers
ProgramDistill
From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
paper:
Uh oh Open Together is 90% full and we're still 3 weeks away...
50 spots left before the waitlist, get yours!
Should we bring robots?
Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face
Text-to-image and image editing in 6 steps
about 5ร faster than the 40-step Qwen-Image-2.1
model:
Show more
Training Object Permanence in World Models
paper:
The Pruna-Qwen-Image-2.1 Space is now live!
You can now test our few-step LoRA adapters for Qwen-Image-2.1 by @Alibaba_Qwen directly in your browser, no setup or code required.
- 5 steps for maximum speed
- 8 steps for the best balance of speed and quality
- Text-to-image and image editing support
Put it to the test and show us the results. B๐ฆ๐ต๐ต๐ฆ๐ณ ๐ท๐ฆ๐ณ๐ด๐ช๐ฐ๐ฏ๐ด ๐ฐ๐ฏ ๐ต๐ฉ๐ฆ ๐ธ๐ข๐บ. ๐
Test the Pruna-Qwen-Image-2.1 Space on @huggingface by @_akhaliq:
Check Pruna-Qwen-Image-2.1:
Show more
Pruna-Qwen-Image-2.1
a set of a few-step LoRA adapters that make Qwen-Image-2.1 up to 6.3ร faster for image generation and editing
Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance
HF workflow:
Show more
On the Diffusibility of High-Dimensional Latents
paper:
Weโre proud to sponsor Open Together, a free community event hosted by @huggingface on Friday, October 16, to kick off Open Source AI Week in SF.
The evening is split into two parts:
โก๏ธ 6PM โ 9PM: 36 live community demos, food, drinks, and time to connect with open-source builders
๐ชฉ 9PM โ 12AM: Full dance floor with live DJ sets
Doors open at 6 PM, and the first 500 people through the door get collectible HF swag. ๐ค
RSVP:
Show more
Qwen-Image 2.1 draws its best pictures when a 9B "prompt rewriter" expands your request first. That is 20 GB in bf16 and uses 1700 words as system prompt, and thinks for ~1,600 tokens before answering.
We shrank it to 0.8B. It fits on a laptop now. ๐งต
Show more
Transferring the Intelligence of VLMs to Robotic Control
paper:
Thanks for sharing @_akhaliq!
onPanda
Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
paper:
๐ Test the Qwen-Image-2.1 workflow on our official demo, thanks to @_akhaliq & @huggingface! ๐
๐ก Pro tip: Default steps are lowered due to free limits. Set to 40 & enable PE thinking to unleash its FULL power! โก๐ฅ
Show more
RRSI
Regularized Recursive Self-Improvement of Agent Harnesses
paper:
Tencent ARC Lab just released GameHorizon Suite
A unified data and evaluation suite measuring AAA gameplay capabilities across multiple temporal horizons for VLMs, UMMs, GUI, coding, and game agents.
Show more
DigitalOcean Managed Agents is now in public preview.
Run Claude Code, Codex, or your own LangGraph agent in a runtime environment that pauses when idle. Put its tools behind one governed endpoint, and pick from 75+ open and proprietary models. One cloud, one bill.
Prompts to get started available in the blog:
Show more
RoboDawn: Transferring the Intelligence of VLMs to Robotic Control
Tsinghua and Tencent Hunyuan show a frozen VLM can drive robots through simple move, rotate and gripper commands, reaching 73.6% one-shot success on RoboTwin 2.0 C2R.
Show more
Meet PixVerse R2, our new real-time world model.
Explore living worlds. Control and edit them with prompts. Shape the story. Meet characters that remember and respond.
WorldCrafter
Consistent Video World Model with Implicit 3D-aware Memory
paper:
Excited to welcome @reflection_ai as a co-host and sponsor of Open Together! ๐ค
Weโre already at 50% capacity! Grab your spot before registration switches to the waitlist.
๐ San Francisco ยท October 16
๐๏ธ Register:
Show more
