PapersWithCode retweeted
The tech report for ZONOS3-Mini is out and I think we have some interesting stuff so let me do a paper thread.
PapersWithCode retweeted
Congrats @liquidai: LFM3-1.7B is SOTA on Multi-IF! 🏆
The 1.7B open model beats Baidu's closed ERNIE 5.0 on multi-turn, multilingual instruction following, 89.1 to 85.56.
Qwen3-VL 235B-A22B Thinking, over 100x its size, scores 79.1.
How small can a good assistant get?
PapersWithCode retweeted
Introducing the Papers with Code MCP server!
To celebrate its release, I've asked Claude Code to research the architecture of Jev by @typesafeai using the `search_papers` tool.
Here's what it came up with:
"If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."
PapersWithCode retweeted
This extraordinary paper is now also available on Papers with Code!
Find it here: paperswithcode.co/paper/1317…
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
PapersWithCode retweeted
EmbeddingGemma2 has been trending on @paperswithcodee for a few days now :)
Congrats on this amazing report!
Find it here paperswithcode.co/pdf/2610.3…
PapersWithCode retweeted
Unlimited OCR 2 is currently the top trending paper on paperswithcode.co!
Chat with it here: paperswithcode.co/pdf/131424
Unlimited OCR 2 is here, and it's open source. 📖 ✨
Longer documents can mean a lot more attention computation. Our new SR-SWA mechanism keeps that in check by condensing text-visual attention interactions into a fixed-size set of working references.
Here's what it delivers:
- Document parsing at virtually any length, within a finite context window
- Nearly constant per-step decoding latency and memory footprint as documents grow longer
- State-of-the-art performance on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages
Check out the model here ↓
PapersWithCode retweeted
OmniParseBench is now a native benchmark on Papers with Code!
Find all papers here: paperswithcode.co/benchmark/…
PapersWithCode retweeted
I've made some big improvements to the PDF reader on Papers with Code!
> The AI assistant now cites its sources, full RAG-style
> This is powered by Chandra-OCR 2 by @datalabto which is openly available on @huggingface
> This model returns bounding boxes besides markdown
> Allows you to click on citations and highlight sections
Try it out on any PDF, like paperswithcode.co/pdf/2610.1…
PapersWithCode retweeted
Introducing the Following feed 🔥
Follow your favorite AI tasks, methods, benchmarks, authors, and organizations on Papers with Code.
Stay up-to-date with a dedicated feed of new papers, SOTA results, and releases from everything you follow.
Video made with Opus 5.5
PapersWithCode retweeted
Curious to keep up to date with auto-research papers?
Just added a category for it on Papers with Code!
Find it here: paperswithcode.co/tasks/auto…
Replying to @NielsRogge
@NielsRogge an idea for paperswithcode, can you add category of auto-research papers ?
I see them a lot more these days, especially on X and I think that would be awesome 😊




















