Sandeep Mishra

PhD Student, Research Intern @GoogleResearch | LIVE @UTAustin | Former @samsungresearch | @IITKgp '19 |

[Oindrila Saha @oindy_saha]

Excited to share the last chapter of my PhD! Presenting SIGMA-Gen: Structure and Identity Guided Multi-subject Image Generation accepted at ICLR 2026.
Paper:https://t.co/G8nYBJOyYZ
Page:https://t.co/pmfJaLnpcL
Demo:https://t.co/M6vOv7cUJS
#ICLR2026 #ComputerVision #GenerativeAI

[Oindrila Saha @oindy_saha]

Heading to #ICCV2025 to present GTA-CLIP at the AM poster session on Tuesday #120. Drop by if you’d like to chat!

https://t.co/V7807dk83h

[Litu Rout @litu_rout_]

Continuous diffusion had a good run—now it’s time for Discrete diffusion!

Introducing Anchored Posterior Sampling (APS)

APS outperforms discrete and continuous baselines in terms of performance & scaling on inverse problems, stylization, and text-guided editing.

[Sandeep Mishra @Sandy_uta]

It’s Friday, the 13th of December and we are presenting YouDream at #NeurIPS2024. Come chat with us!!

[Oindrila Saha @oindy_saha]

We are presenting YouDream today at #NeurIPS2024 at East Exhibit Hall #2706 in the morning session. Drop by and chat with both @Sandy_uta and me at the poster!

Project page: https://t.co/D8xmgnJEq1

[Sandeep Mishra @Sandy_uta]

@zhanghesprinter Hi He, I just sent you an email regarding this. Would love to chat about this opportunity.

[Zhengzhong Tu @_vztu]

🚨 Folks, please check out our new #ECCV2024 paper SPIRE, a semantic and restoration prompt-driven image restoration technique, that leverages natural language to control the restoration process.

https://t.co/JdfI9PmyJb

[Sandeep Mishra @Sandy_uta]

Thank you for sharing our work @janusch_patas

The code will be released very soon!!

[MrNeRF @janusch_patas]

That's cool. Create posed and anatomic consistent animals with text-to-3D.
"YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals"
Project: https://t.co/ErX3smIIOZ
Paper: https://t.co/rhLW01lvin

I hope we will get some code soon to try it out!

[AK @_akhaliq]

8 papers submitted to daily papers so far today

If your a author with at least one indexed paper on HF, submit your paper directly to daily papers: https://t.co/VbXh61IzHE

[Sandeep Mishra @Sandy_uta]

Thanks for featuring our work @dreamingtulpa

[Dreaming Tulpa 🥓👑 @dreamingtulpa]

YouDream can generate high-quality 3D animals from a single image and a text prompt!

The method is able to preserve anatomic consistency and is capable of generating and combining commonly found animals.

Links ⬇️

[Dreaming Tulpa 🥓👑 @dreamingtulpa]

YouDream can generate high-quality 3D animals from a single image and a text prompt!

The method is able to preserve anatomic consistency and is capable of generating and combining commonly found animals.

Links ⬇️

[The AI Timeline @TheAITimeline]

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals

Explained by author:
https://t.co/A3qhSAa9gO

Overview:
YouDream enhances 3D generation of anatomically controllable animals using a text-to-image diffusion model guided by 2D views of 3D poses.

Unlike previous methods that rely solely on text or images, YouDream expands creative possibilities by maintaining anatomic consistency in generated animals.

The fully automated pipeline adapts 3D poses from a limited library using a multi-agent LLM, eliminating the need for human intervention.

A user study confirms the superiority of YouDream's animal models over previous methods, highlighting its effectiveness in generating high-quality 3D animals.

Paper:
https://t.co/BLyB0JZmpN

Project Page:
https://t.co/38aMNZ9iAF

Code:
https://t.co/xN71dNe4V4

[Sandeep Mishra @Sandy_uta]

@SunnySanyal9 Thanks!! It was quite fun to work on this topic as well. We will be releasing the code real soon and would love to see what crazy assets you can create.

[Sandeep Mishra @Sandy_uta]

📣 It's finally out there. Our work YouDream is now on arXiv. Do check out the video results on the webpage: https://t.co/9X7uZwQ1Sc

And watch out for code release. ⭐️

Here’s a sneak peek of a few creative examples you can create using YouDream.

[Oindrila Saha @oindy_saha]

🚨 New paper
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
YouDream achieves multi-view consistency without being trained on 3D datasets and generates imaginary assets impossible to be made using prior methods.🧵 below.
page: https://t.co/6GJEVTfuE2

[AI Bites | YouTube Channel @ai_bites]

YouDream is a method to generate high quality anatomically controllable animals.
YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. It generates 3D animals which are not possible to create using previous text-to-3D generative methods.

Paper: YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
Link: https://t.co/IZBcKyZq3q
Project: https://t.co/JRiQgE55M9

#AI #AI美女 #LLMs #deeplearning #machinelearning #3D #generativeAI

[Zhengzhong Tu @_vztu]

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
Web: https://t.co/YUS0rRcZ2j
Abs: https://t.co/EFpCABLwII

Generate high-quality anatomically controllable animals capable of preserving anatomic consistency, with a multi-agent LLM for pose editing

[Oindrila Saha @oindy_saha]

We have open-sourced the code and data for "Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions" @CVPR at: https://t.co/imdgtl5nwt
Also, find the poster and video links at the GitHub repo!

[Sandeep Mishra @Sandy_uta]

@AndrewPierno Send

[Andrej Karpathy @karpathy]

There's too much happening right now, so here's just a bunch of links

GPT-4 + Medprompt -> SOTA MMLU
https://t.co/Jkp96izfec

Mixtral 8x7B @ MLX nice and clean
https://t.co/75StzY5AHe

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
https://t.co/gOCWjfY7ec

Phi-2 (2.7B), the smallest most impressive model
https://t.co/Fps8tI5QVi

LLM360: Towards Fully Transparent Open-Source LLMs
https://t.co/l6E16GfdIN

Honorable mentions
https://t.co/7GQqiCGHRH
https://t.co/3GZrYPp9KP
https://t.co/Su8iiDksMZ

[Elon Musk @elonmusk]

An American YouTuber has been imprisoned for 5 years in Ukraine, and allegedly tortured, for making videos.

This is not ok.

[Sandeep Mishra @Sandy_uta]

@venturetwins Division is a direct consequence multiplication and thus addition. Dividing a number 'y' by a certain number 'x' is equivalent to finding out how many times you need to add 'x' to get 'y'. In this case, however number of times you add 0, one can never reach the number 'y'