Patel Maitreya
@patelmaitreya
Followers
358
Following
3K
Media
53
Statuses
523
Research Intern @Adobe | PhD at @ApgAsu @ASU | Vision & Language | T2I Diffusion Modeling | Prev. @SonyAI_global @Adobe
Tempe, AZ
Joined November 2012
🚀 Introducing FlowChef: "Steering Rectified Flow Models in the Vector Field for Controlled Image Generation"! 🌌✨. 💡 Key Highlights:. - Perform image editing, solve inverse problems, and more. - Achieved inversion-free, gradient-free, & training-free inference time steering!
2
4
21
RT @patelmaitreya: Thinking of kicking off a new open research project… can’t decide which direction to take. Both have some very spicy ide….
0
1
0
Thinking of kicking off a new open research project… can’t decide which direction to take. Both have some very spicy ideas I think the community will love 👀. 1️⃣ Text-to-image: runs any hardware pre-distill/quant.2️⃣ Flexible unified autoregressive model. Both prod-ready from day.
0
1
2
RT @tunahansalih: Combining multiple LoRAs is tricky. One concept often dominates, killing the composition. Our paper, CLoRA, accepted as….
0
17
0
Also this 👇.
We just discovered the 🔥 COOLEST 🔥 trick in Flow that we have to share:. Instead of wordsmithing the perfect prompt, you can just. draw it. Take the image of your scene, doodle what you'd like on it (through any editing app), and then briefly describe what needs to happen
0
0
0
Do not ask me to use your model if it cannot at least do this. It seems that video models are finally becoming truly useful. Exciting!.
Introducing Runway Aleph, a new way to edit, transform and generate video. Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing
1
0
0
First time I’m not feeling FOMO over the OpenAI agent — I’ve got early access to @yutori_ai and it’s way, way better 😁. The team has absolutely nailed the use case. Not surprised — they’re brilliant.
0
2
20
I mean, the Windsurf/ScaleAI saga was wild to watch… but honestly, it feels unfair to all the early employees who took the biggest risks. If this keeps happening, why would anyone join a startup early? 🚩 Something’s gotta change.
🚨BREAKING: GOOGLE TO PAY $2.4 BILLION FOR WINDSURF STAFF AND IP . we are so back.
0
0
5
Okay… diffusability is a real concern. 🙁 .Any post-hoc solution without equivariance training?.
0
0
2
I have been wondering about this for months now. This makes total sense. Gotta change my scripts. 🏃➡️.
0
0
3
I'm glad to see that someone finally wrote a paper on this low hanging fruit, which I shared on X back in December and also included in invited talks. (check this out)
0
0
0
Lately, so many incredible projects are being released—it’s inspiring and a little overwhelming. Some days I wake up excited to be part of this space. Other days, I wonder if what I’m building will still matter tomorrow. That back-and-forth is constant.
0
0
7
I have lost confidence in all papers only using Qwen for alignment improvements. How can we trust that these improvements are not influenced by spurious biases or methodological changes?. Interesting work though.
🤯 We cracked RLVR with. Random Rewards?!.Training Qwen2.5-Math-7B with our Spurious Rewards improved MATH-500 by:.- Random rewards: +21%.- Incorrect rewards: +25%.- (FYI) Ground-truth rewards: + 28.8%.How could this even work⁉️ Here's why: 🧵.Blogpost:
0
0
3
I agree with this. There are still many great papers that predate the recent diffusion LLM hype that are being overlooked. Hint: At least check the #ICLR2025 papers.
@arankomatsuzaki Tbh, there are many good papers coming out of academic labs too, for example diffusion LLMs, but they didn’t really get attention until Google released a paper on it. Perhaps you should also tweet a bit about academic research :).
0
0
2
RT @jasonbaldridge: Veo 3 is here, and in addition to better visuals, it makes noises and speaks! This was a massive effort made possible b….
0
34
0
Whoa… just got access to the model—and it’s phenomenal. Solves many of the classic LLM problems right out of the gate. Time to put it through its paces. Wish I knew the parameter count for fair comparison, but I’ll benchmark it soon enough.
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
0
0
3
I’m seriously getting FOMO.
We’ve developed Gemini Diffusion: our state-of-the-art text diffusion model. Instead of predicting text directly, it learns to generate outputs by refining noise, step-by-step. This helps it excel at coding and math, where it can iterate over solutions quickly. #GoogleIO
0
0
4
Just had a Final Destination-type moment on my way to the Bay Area. Life really threw a plot twist today. Luckily, I did not get hurt and just got a big logistical task on my to-do list. 😮💨.
2
0
3