Vin Agarwal

@joshua_sirota @LongJourneyVC @UseCorgi @slashapp @agentmail Excited for the journey together!

Excited to announce our $12M Seed Round led by @LongJourneyVC We’re an applied AI Lab building operational intelligence. We're thrilled to work with incredible startups like @UseCorgi , @slashapp , @agentmail , and many more. Our mission is to turn all of enterprise software into a prompt. We do this by using frontier models and post training specific models on company data. Thanks for the coverage @TimFernholz and @TechCrunch Read more about us here:

AI deep research and writing tool github.com/K-Dense-AI/cla…

We're excited to launch subscription plans in K-Dense Web! Personal plan: pay as you go for lighter or occasional usage. Plus plan: $199/month for 300 credits refreshed every month, a $300 value. Team plan: $499/month for unlimited seats and 800 credits refreshed every month, shared across the team, an $800 value. Learn more at k-dense.ai

Spent way too long fighting Illustrator for a figure that belonged in a methods section. There's a skill for that now, describe your diagram in plain English, Nano Banana 2 draws it, Gemini 3.1 Pro grades it against the right bar for your doc type, and if it misses, it critiques itself and tries again. Flowcharts, transformer architectures, biological pathways. One command, publication-ready. Open source. Try it now! github.com/K-Dense-AI/cla…

Quick tutorial on how to create a professional slide deck using K-Dense Web (@k_dense_ai) in less than 10 min (including all the research needed)

Join our Head of AI, @TimothyKassis, in this short tutorial for how to use K-Dense Web to generate stunning graphical abstracts for your manuscripts.

Claude Scientific Skills yapay zekaya "bilimsel yetenekler" kazandırarak araştırmacıların günlerce sürecek işlerini dakikalara indirmeyi hedefliyor. 140'tan fazla hazır yeteneği aşağıdaki linkte bulabilirsiniz 🔗 github.com/K-Dense-AI/cla…

@DataChaz Thanks for the shoutout! Also try out app.k-dense.ai (K-Dense Web) which is powered by these skills and more!

Here is the link to the repo: ↳ github.com/K-Dense-AI/cla…

Wow, such a great open-source drop! Put Claude on steroids with 120+ scientific skills spanning maths, biology, chemistry, medicine, engineering, & more 🤯 If you’ve ever wanted Claude to act like a research assistant, this gets very close. Free and open source. Repo in 🧵↓

Equips Claude with skills for scientific research workflows github.com/K-Dense-AI/cla…

You can now use K-Dense Web to generate compelling and accurate infographics for any use case! Try it out today for free at k-dense.ai

Love this! We have been employing a very similar methodology for figures and schematic generation for a while now at @k_dense_ai on K-Dense Web and Claude Scientific Writer using nano banana pro and opus 4.5 Check it out here - github.com/K-Dense-AI/cla… app.k-dense.ai

Dang it’s hard to keep up !!

@SebastienBubeck Best research environment? Except for the whole "don't tell anyone about your research" part. Research in secret is not research.

@hasantoxr Love this! We have been employing a very similar methodology for figures and schematic generation at @k_dense_ai on K-Dense Web and Claude Scientific Writer using nano banana pro and opus 4.5 Check it out here - github.com/K-Dense-AI/cla… app.k-dense.ai

🚨BREAKING: Google just dropped another hit! It's called PaperBanana and it generates publication-ready academic illustrations from just your methodology text. No Figma. No manual design. No illustration skills needed. Here's how it works: A team of AI agents runs behind the scenes → One finds good diagram examples → One plans the structure → One styles the layout → One generates the image → One critiques and improves it Here's the wildest part: Random reference examples work nearly as well as perfectly matched ones. What matters is showing the model what good diagrams look like, not finding the topically perfect reference. In blind evaluations, humans preferred PaperBanana outputs 75% of the time. This is the recursion we've been waiting for AI systems that can fully document themselves visually. Waitlist’s open, Link in the first comment.

@akshay_pachaar Love this work. We have been using a similar methodology for scientific schematics and illustrations in our open source repo for a while now - github.com/K-Dense-AI/cla… A more powerful version is available in our freely usable AI scientist - k-dense.ai

Google just dropped another banger! the figures in this paper were drawn by the system described in the paper. PaperBanana is an agentic framework that generates publication-ready academic illustrations from methodology descriptions. no manual design, no Figma, just your method section and a caption. here's how it works: five specialized agents collaborate in sequence: > Retriever: finds relevant reference diagrams from a curated set of NeurIPS papers. matches by visual structure, not topic. > Planner: translates your methodology text into a detailed visual description using in-context learning. > Stylist: applies aesthetic guidelines (color palettes, typography, layout) auto-summarized from hundreds of top-tier papers. > Visualizer + Critic loop: generates the image, critiques it against source text, and refines. repeats for 3 rounds. one surprising finding: randomly selected examples work nearly as well as semantically matched ones. what matters is showing the model what good diagrams look like, not finding the topically perfect reference. in blind evaluations, humans preferred PaperBanana outputs nearly 3 out of 4 times. it also extends to statistical plots using code-based generation for numerical precision. link in the next tweet.

We just crossed 10k GitHub stars!⭐ None of this happens without the open source community and the K-Dense team. Thank you. If you have starred, contributed, or are building with us, this is yours. github.com/K-Dense-AI

@dwzhu128 Love this. We have been employing a very similar methodology for figures and schematic generation at @k_dense_ai on K-Dense Web and Claude Scientific Writer using nano banana pro and opus 4.5 Check it out here - github.com/K-Dense-AI/cla… app.k-dense.ai

[1/n] Super excited to introduce PaperBanana 🍌! (PKU x Google Cloud AI) As AI researchers, we often spend way too much time crafting diagrams and plots instead of focusing on the ideas 🤯. To rescue us from this burden, we built an Agentic Framework to auto-generate NeurIPS-quality paper illustrations! 📄 Paper: huggingface.co/papers/2601.23… 🌐 Page: dwzhu-pku.github.io/PaperBanana/ Key Features: 🌟 Human-like Workflow: Retrieve 🔍 -> Plan 📝 -> Style 🎨 -> Render 🖼️ -> Critique 🔄. This ensures both academic fidelity and aesthetics. 🌟 Versatile: Supports both illustrative diagrams and statistical plots. 🌟 Polishing: Also effective for polishing existing human-drawn diagrams. Here are some example diagrams and plots generated by our PaperBanana:

Using K-Dense Web with OpenAI Prism youtu.be/pw_99W_XJhc?si… via @YouTube

@kabirhbiswas @k_dense_ai Yes, it is!

@k_dense_ai Wondering if this figure was also generated by K-Dense Web

Great work! We also used the same prompt in K-Dense Web. 1 hr later. Ready to submit manuscript. See the full analysis: app.k-dense.ai/share/session_… Link to resulting manuscript: k-dense.ai/examples/sessi… Get started with K-Dense Web for free at k-dense.ai