Mridul Khurana

CS PhD student @VT_CS | Intern @Apple | Ex- @AMD

[Mridul Khurana @mridulk97]

I'm happy to share that I have joined @Apple in Seattle for my summer internship, working on Image Editing.

Looking forward to a great summer of research and building exciting things!

[Kimi.ai @Kimi_Moonshot]

🚀 Hello, Kimi K2 Thinking!
The Open-Source Thinking Agent Model is here.

🔹 SOTA on HLE (44.9%) and BrowseComp (60.2%)
🔹 Executes up to 200 – 300 sequential tool calls without human interference
🔹 Excels in reasoning, agentic search, and coding
🔹 256K context window

Built as a thinking agent, K2 Thinking marks our latest efforts in test-time scaling — scaling both thinking tokens and tool-calling turns.

K2 Thinking is now live on https://t.co/YutVbwktG0 in chat mode, with full agentic mode coming soon. It is also accessible via API.

🔌 API is live: https://t.co/EOZkbOwCN4
🔗 Tech blog: https://t.co/n7xxaszqzF
🔗 Weights & code: https://t.co/4ukcXB0iP6

[fal @fal]

🚨FLUX.1 Kontext [dev], the open image editing model, is now available at fal with training capabilities!

✨4x faster inference (2s vs 7s)
💰 Ultra-affordable at $0.025/megapixel
🔧 Full LoRA training support
🖌️Game-changing image editing capabilities

https://t.co/yX8wxdFlD4

[Voxel51 @Voxel51]

Today’s @CVPR research is proving that precision isn’t just about better metrics—it’s about building AI that can truly understand complexity, context, and the unknown.

In part 3 of our #CVPR series, we’re highlighting 4 papers that push the boundaries of segmentation, detection, retrieval, and prediction in powerful new ways. 🧵

https://t.co/LzwK6FiNlE

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images
Main proc
@ksmehrab @sammarfy @arkadaw_ @neog_abhilashh @harishB97 @mridulk97 @anujkarpatne (all VT) and collaborators
https://t.co/gJvYzSalmQ

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation
Workshop
@MonsefiAmin @mridulk97 (VT) Rajiv Ramnath @anujkarpatne (VT) @weilunchao @chengzhang528
https://t.co/HJAwJmb7nU
TL;DR: Generates images w/high morphological and identity accuracy

[fal @fal]

🚨 BREAKING: GPT Image Killer is here. FLUX Kontext [pro] & [max] models are available on @fal day 0!

This isn't just your usual image editing model – it preserves identity AND maintains consistency with the rest of the image.

Try it today here -> https://t.co/00qzr3FZWR

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

Congrats 🎉 to @SanghaniCtrVT core faculty member @anujkarpatne, newly named Faculty Fellow @VTEngineering, an award given in "recognition of "extraordinary performance in research." With him at Dean’s Awards Celebration are @vtdeanross (L) and Christine Julien, head @VT_CS.

[Mridul Khurana @mridulk97]

@ksmehrab @LinkedIn Congratulations man ! 😀

[Mridul Khurana @mridulk97]

@CVPR

[Medha Sawhney @medha_sawhney]

🌟Thrilled to share our paper, “A Unified Framework for Forward and Inverse Problems in Subsurface Imaging using Latent Space Translations”, has been accepted at #ICLR2025 ! 🎉
Grateful to my co-authors, Naveen Gupta, @arkadaw_ , @YouzuoLin1 and @anujkarpatne, for their support.

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
Poster

@sammarfy @arkadaw_ @ksmehrab @harishB97 @neog_abhilashh @medha_sawhney @mridulk97 @anujkarpatne- all VT w/collaborators

https://t.co/kc2XZ8bYfC

[Blockade Labs @BlockadeLabs]

Introducing Blendbox: a fresh way to create with AI

No more wrestling with long prompts or random results. Blendbox Alpha brings simplicity & control to AI art, so you can shape your vision directly.

Don't just generate. Create. https://t.co/CbMvhkI2HS

[Jia-Bin Huang @jbhuang0604]

PhD then:
“We validate our method on a large-scale dataset of hundreds of images.”

PhD now:
“We validate our method on 10 different modalities, 15 domains, 20 scenarios, 25 tasks, and 200 languages, each with millions of testing examples”.

[Fernando Cao @thefernandocz]

By 2030, I guarantee we'll all be wearing Zuckerberg's new AR glasses.

Not because they're cool.

Because they're the biggest tech revolution since the iPhone: 🧵

[Ilya Sutskever @ilyasut]

Congratulations to @geoffreyhinton for winning the Nobel Prize in physics!!

[Ishan Misra @imisra_]

So, this is what we were up to for a while :)
Building SOTA foundation models for media -- text-to-video, video editing, personalized videos, video-to-audio

One of the most exciting projects I got to tech lead at my time in Meta!

[Liquid AI @liquidai]

Today we introduce Liquid Foundation Models (LFMs) to the world with the first series of our Language LFMs: A 1B, 3B, and a 40B model. (/n)

[M. Maruf @sammarfy]

Excited to share that VLM4Bio has been accepted at #NeurIPS2024 🎉🥳. Congratulations and big thanks to my Prof. @anujkarpatne, my co-authors (notably @arkadaw_, @ksmehrab, @harishB97, @neog_abhilashh), and my awesome collaborators from @imageomics!
https://t.co/mGzaFXYGrO (1/2)

[European Conference on Computer Vision #ECCV2026 @eccvconf]

.@huggingface is hosting a demo site for #ECCV2024 🤗 Authors can claim their papers and discuss the papers on dedicated pages.

Demo page: https://t.co/LqpwVsGgD5