Found a potential mistake in an ICLR 2026 blogpost [D]
I think I found a mistake in an ICLR 2026 blog post. I created an issue and have been trying to contact the author and organizers,…
Latest
Just landed a Computer Vision internship, here’s the preparation list I used [D]
Hey everyone, I recently landed a Computer Vision internship after prepping with this checklist I put together. It starts with core math and ML fundamentals, then…
Non-deterministic Vulnerability Detection Benchmark System [P]
I work in firmware adjacent to AI, so not an ML guy exactly, so that's why I've come here. For work we got a bit concerned…
Syntactically robust NLI for semantics of imperfectly generated text? [R]
Hi all, I'm looking for literature on relatively specific tooling. In autoregressive LLMs, there is substantial published work that used NLI on sub-claims produced by LLMs…
Recommendations for speech annotation tools [D]
I'm looking for human-in-the-loop platforms that allow you to automatically transcribe audio followed by manually fixing the transcriptions and fine tuning the model. Is there a…
Some new updates to Papers with Code [P]
Hi folks, Niels here from the open-source team at Hugging Face. I continue working on a revival of paperswithcode.co as we're back to the "age of…
GPU access in 2026 is still fragmented — is there a better market structure for compute? [P]
Anyone building at the model layer knows the procurement problem hasn't gone away. H100s are still allocated unevenly, spot instances get preempted at the worst times,…
[ECCV 2026] Paper Decision Appeals Discussion [D]
With the release of meta-reviews, ECCV sent out a google form for dissatisfied authors to submit an appeal for the following reasons: Policy errors, e.g., reviewers…
An Update on Matrix Recurrent Units, an Attention Alternative [R]
I recently revisited my matrix recurrent units algorithm (the MRU), a novel linear-time sequence architecture I created as an alternative to attention. I explain it in…
Data-centric debugging for teams training neural nets [P]
We just did a big revamp of WeightsLab and wanted to share it here. If you’ve ever spent hours debugging a training run only to discover…