Varun

Spent the last few months building a virtual try-on tool. It’s live now. Really cool to see the AI actually handling the cloth warping correctly. check it out here: viton-repo.vercel.app #AI #StableDiffusion #Fashion #Viton #Clothing

@HeyGen AvatarV

We solved character consistency. Forever Avatar V captures you in 15 seconds and holds your identity across every video. Change the look, outfit, and setting to create unlimited versions of you. RT + comment "AvatarV" below and I'll DM 100 credits to test it out (must follow)

Hate him as much as you want, he only has love to offer. MS Dhoni is not only a great cricketer but also a great human being.

@oprydai This is about LLM and AGI

@Fintech00 😂😂

Ekdm mast moula aadmi tha Na tension leta tha Na tension deta tha

Zhilin at GTC: Introducing Attention Residuals Learning selective memory, rather than mechanically accumulating everything, is the beauty of attention. Many of you have probably read Attention Is All You Need, the 2017 Transformer paper that brought “human-like” attention into the model’s field of view. From that point on, models no longer simply read everything in a mechanical way. Instead, they began to develop a sense of what matters more and what matters less across the text, choosing to retain the more important information. Recently, Kimi applied this idea of attention to the temporal dimension, then rotated it 90 degrees into the model’s depth dimension. This allows the model to have attention not only over time, but also throughout the process of information transmission across layers—giving it a more intelligent way to understand and process information.

@manojdotdev True 😂

Bro is raising multiple pull requests but none of them are Merging

Almost 18000 students graduate from IITs every year. Around 7000 are from the top IITs, and about 1000 are from CS/EC branches. Out of those 1000, less than 5% get an international offer, while the remaining 95% stay here. They earn and pay taxes here, but we still have not built a system that supports them if they dare to do something challenging. It is not IITians alone, it is the opportunities created by US that allows IITians to grow there. Meanwhile, in India, we are busy finding new ways to distribute freebies so that we can win the next election, and these freebies are funded by the taxes paid by someone working day and night while living in a 10×15 room in Bengaluru or Gurgaon.

@Hiteshdotcom @rutturaj 😂😂

@rutturaj Screen se nikl ke type krunga😂

maine suna hai isme @Hiteshdotcom gharpe aake padhayenge 💀

@ShyamMeeraSingh Rajeev talwar😂

इस खबर को पढ़कर मुझे ग्रीक फिलोसफर- राजीव तलवार की एक बात याद आ गई- “जिस देश का विद्वान ही…

@Mantu_kumar91 @piyushgarg_dev 😂😂

Skill sikhte hi dead ho jaata hai 😑

I coded a Speech-to-Text model from scratch. 𝐇𝐞𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐛𝐥𝐨𝐠 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐬𝐚𝐦𝐞: blogs.mayankpratapsingh.in/chapters/speec… No APIs. No pre-trained models. Just PyTorch, an A100 GPU, and hours of debugging. This started months ago. I wanted to understand how machines hear. Not surface-level understanding. I wanted to build the whole thing myself. So I built it piece by piece: autoencoders, VAEs, VQ-VAEs, Residual Vector Quantization, and CTC loss. Each one took days to get right. Trained for 3 hours on 13,100 audio clips. Got complete garbage. Changed the tokenizer from BPE to character-level. Rechecked everything. Asked @neural_avb who built STT models before. His answer: these models are tricky to train and need days of compute, not hours. Cut the dataset to 200 clips. After 2 hours, actual words appeared. Overfitted? Absolutely. But watching noise turn into recognizable English was satisfying. I have made a blog about this as well so you can learn about the same and my process - Audio fundamentals and waveform representation - Why attention breaks on raw audio - Convolutional downsampling - Transformer encoder with positional encoding - Vector Quantization, straight-through estimator, and RVQ - CTC loss and greedy decoding - Full training loop with VQ loss warmup - What went wrong and what finally worked Resources: - Blog: blogs.mayankpratapsingh.in/chapters/speec… - Code: github.com/Mayankpratapsi… More Resoures CTC loss distill.pub/2017/ctc/ @neural_avb videos @avb_fj" target="_blank" rel="nofollow noopener">youtube.com/@avb_fj SoundStream Paper arxiv.org/abs/2107.03312 LJ speech dataset keithito.com/LJ-Speech-Data… wav2vec paper arxiv.org/abs/2006.11477 RVQ blog drscotthawley.github.io/blog/posts/202… Next up: I've already trained two TTS architectures from scratch. Video post about those coming soon. But first, I'm dropping a visual breakdown of Vision Transformers, covering how they work and how to fine-tune them. Follow me @Mayank_022 you're into audio deep learning. Repost so others can find this

@sachinyadav699 resume-omega-virid.vercel.app

drop your portfolio- need inspo

@TusharGoswamy Congrats 🎉

🙌🏻🙌🏻🙌🏻

@mchulet tryown-frontend.vercel.app

✋✋ Monday again!! Time to promote your product. 🚀 Share your product URL

@HarveenChadha @SarvamAI Proud moment 😀

Nice, seeing a familiar name here

@thesayannayak Making AI fashion media from scratch

Pitch your startup in 1 line

@OmriBuilds Reshaping fashion future

Pitch your startup in 3 words

@ionleu tryown-frontend.vercel.app

drop ur startup link

@IrfanPathan baat achhi and analogy usse v achhi😂

Zaruratmand insaan tak zakaat aise pahunchao, jaise joint family mein biwi ke liye burger pahunchate ho.

@Amank1412 name?

Microsoft open sourced an inference framework that runs a 100B parameter LLM on a single CPU.