2. Text guided interactive video expansion pic.twitter.com/nqc6tdqy5G
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 18 août 2025
2. Text guided interactive video expansion

By
–
2. Text guided interactive video expansion pic.twitter.com/nqc6tdqy5G
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 18 août 2025
2. Text guided interactive video expansion

By
–
5. Multi-modal cross domain fusion pic.twitter.com/pa8xm2uJtb
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 18 août 2025
5. Multi-modal cross domain fusion
By
–
Tencent just unveiled Yan —
China’s response to Google Genie 3. An AI that creates playable scenes and supports real-time edits from text + images at 1080p / 60fps. Here are 9 insane examples:

By
–
Qwen Image LoRA Finetuning is here! Train your own styles for portraits or art. It’s great at complex scenes and composition
Try it: https://
replicate.com/qwen/qwen-imag
e-lora/train
…

By
–
Deploying AI on the edge? Then you know the challenge: preserving accuracy while shrinking your model footprint. Some of our community members are sharing quantisation workflows that really deliver, and others, like the awesome team at @DeGirum
, are doing impressive things on
By
–
📢☑️Video-RAG: Training-Free Retrieval for Long-Video LVLMs
— Satya Mallick (@LearnOpenCV) 18 août 2025
In this week’s deep dive, we implement Video-RAG as a training-free, single-pass pipeline and integrate it with LLaVA-Video-7B (Qwen2, 32K context), without APE – to keep things reproducible on today’s stacks. We enable… pic.twitter.com/ZVNMVXr0WQ
-RAG: Training-Free Retrieval for Long-Video LVLMs In this week’s deep dive, we implement Video-RAG as a training-free, single-pass pipeline and integrate it with LLaVA-Video-7B (Qwen2, 32K context), without APE – to keep things reproducible on today’s stacks. We enable

By
–
#Students, ready to solo a data challenge? Join the Student track in #SASHackathon! Use Cortex + SAS tools to tackle a fundraising simulation—no team or experience needed. Just you, data, and your strategy. Reg closes Aug 31 | Hackathon: Sept 15–Oct 10 http://
2.sas.com/6011fYWGD
By
–
I think my original thesis on distribution + product > raise lots of capital + product is playing out now. As software has gotten cheaper to build and youtubers actually having enough free cash flow to hire a small tight team of engineers (and they will hire good ones because
By
–
LFM2-VL support with GGUF and llama.cpp 🥳
— Maxime Labonne @ ICLR (@maximelabonne) 18 août 2025
You can now run these tiny, hyper-efficient VLMs on your watch!
We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface pic.twitter.com/DfK3p1MA08
LFM2-VL support with GGUF and llama.cpp You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface
By
–
This is the biggest AI Agent challenge yet
— God of Prompt (@godofprompt) 18 août 2025
MiniMax is giving out $150K in prizes for full-stack AI agents.
→ Over 200 awards
→ Most creative, weirdest, most remixed all categories welcome
Basically, anyone with a good idea is welcome.
Submissions open now ↓ pic.twitter.com/Rgzaf66q1l
This is the biggest AI Agent challenge yet MiniMax is giving out $150K in prizes for full-stack AI agents. → Over 200 awards
→ Most creative, weirdest, most remixed all categories welcome Basically, anyone with a good idea is welcome. Submissions open now ↓