nielz_r
Joined 4 months ago
Karma
94
Submissions
5
Member since
Jun 8
Recent submissions
Comment · 4 days ago
Comment · 4 months ago
Thanks a lot for your comment!
"Son of PwC" sure sounds like a compliment :) Let me know if you want to get in touch to discuss a bit more in-depth, I would be curious to hear some stories from the past!
Comment · 4 months ago
Hi,
Niels here from the open-source team at Hugging Face. Like many others, I was a huge fan of paperswithcode, a website which allowed to easily find the state-of-the-art (SOTA) across any domain of AI, from computer vision to language models to time-series forecasting. Sadly, that website is no longer maintained after its acquisition by Meta.
Hence, I've been working on reviving it. I obviously use AI agents to parse papers at scale and automatically generate leaderboards (for now I'm the one verifying results). So far, I've only parsed high-impact papers for which I know they're SOTA, like Qwen 3.5 and 3.6, RF-DETR for object detection, DINOv3, SOTA embedding models from the MTEB leaderboard, the Open ASR Leaderboard for automatic speech recognition models, etc.
For now, it includes the following:
> trending papers by default based on Github star velocity
> categorization by domain, e.g., [OCR](https://paperswithcode.co/tasks/ocr)
> methods, popular techniques used across AI papers, which PwC used to have as well, like [RLVR](https://paperswithcode.co/methods/rlvr) and
> eval results for high-impact papers, see e.g., Qwen 3.5 at the bottom
> leaderboards for each domain, e.g., MMTEB or COCO val 2017
> conferences, like [CVPR 2026](https://paperswithcode.co/conferences/cvpr-2026)
> support for citation counts (you can also see the most cited papers by domain!)
> automated linked Github, project page URLs, and artifacts (+ multiple repos are supported on a paper page)
> support for external papers beyond Arxiv, see e.g., [DeepSeek v4](https://paperswithcode.co/paper/82956)
> Harness reports for coding agent benchmarks, e.g., Terminal Bench
> "Sign in with HF" and Storage Buckets are used to store humbnails, paper PDFs, and overall data backups.
I'm curious about your feedback + feature requests!
Try it at https://paperswithcode.co
Our goal here is to collaboratively make the best paper interface, as it would be silly to build this on my own.
Over the past couple of months, I've been working with my buddies Claude and Codex on creating a website that tracks trending AI research, benchmarks and state-of-the-art (SOTA), as a revival of the original Papers with Code website (which got acquired by Meta and later shut down).
The website is pretty straightforward: - Python FastAPI backend - React frontend
The app itself is hosted on a Hetzner Virtual Private Server (VPS). The code is also hosted there as a single monorepo.
The frontend mostly calls various API endpoints to visualize papers. The API itself is also publicly available, as is an accompanying MCP server.
I've been getting cool feature requests lately, so rather than just me working on it, I thought it makes a lot more sense to openly share the code base so anyone can contribute.