@mayhewsw: New paper: I know the hotness is all in 10xing compute scale, and telling things to think step by step with tool use, b…
Summary
Authors release Universal NER v2, a named-entity recognition paper presented at LREC 2026 that deliberately eschews modern scaling and tool-use trends.
Similar Articles
@dair_ai: NEW paper from Meta: Agentic Discovery of Neural Architectures. This is a hot new area of research! Keep an eye on it.
Meta's new paper presents an agentic system that autonomously discovers neural architectures outperforming Llama 3.2 at 350M, 1B, and 3B scales within a 24-hour compute budget.
@NielsRogge: Top trending paper on http://paperswithco.de is "FastContext: Training Efficient Repository Explorer for Coding Agents"…
Microsoft's FastContext is a trending paper introducing a small 4B model for efficient code retrieval paired with coding agents, rivaling closed-source systems on SWE-Bench Multilingual.
@dair_ai: https://x.com/dair_ai/status/2056018543850754283
A roundup of the top AI papers from May 11-17, covering Lighthouse Attention for long-context pretraining, a comparison of grep vs embedding retrieval for coding agents, and mechanistic interpretability work revealing a geometric calculator in LLMs.
A Mechanism and Optimization Study on the Impact of Information Density on User-Generated Content Named Entity Recognition
ArXiv preprint identifies low information density as the root cause of NER performance collapse on noisy user-generated content and introduces the Window-Aware Optimization Module (WOM) that boosts F1 by up to 4.5% on WNUT2017.
@HuggingPapers: Top AI papers on @huggingface this week (June 1-7) - On the Scaling of PEFT: Towards Million Personal Models of Trillio…
A weekly roundup of notable AI papers on Hugging Face, covering topics like PEFT scaling, multi-agent crafting, speculative decoding, and more.