…We evaluate our model on four standard relation extraction benchmarks: CoNLL04 , DocRED , FewRel , and CrossRE , and demonstrate competitive performance against both specialized relation extraction models and large language models, while maintaining the…
…Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models Published on May 11 Submitted by Wenxuan Song on May 12 OpenHelix-Team Authors: , , , , , , , , , Abstract A novel approach decouples auxiliary…
…on May 12 Authors: , , , , , , , , , Abstract Research demonstrates that structured pruning and knowledge distillation effectively compress mixture-of-experts models at scale, with progressive pruning and combined distillation strategies improving performance. AI-generated…
…AI-generated summary Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user…
…AI-generated summary Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations . We design an end-to-end training pipeline that jointly optimizes reconstruction and generation , enabling…
…Multi-entity & Evolving Memory Evaluation Published on May 12 Submitted by Arnas Uselis on May 13 KAIST AI Authors: , , Arnas Uselis , , Abstract MEME benchmark evaluates memory systems across multiple entities and evolving…
…on May 13 Authors: , , , , Abstract AlphaGRPO enhances multimodal generation by applying Group Relative Policy Optimization to AR-Diffusion Unified Multimodal Models through self-reflective refinement and decompositional verifiable reward mechanisms. AI-generated…
There's this new "model" on Hugging Face titled Open-OSS/privacy-filter which is actually a customized infostealer virus. It's a fake version of the OpenAI privacy filter and it uses a Python-based dropper (loader.py) wh…
The Department of War dropped PURSUE Release 01 today, 161 declassified UFO/UAP files, 3.7 GB. The official release is a paginated HTML table with mostly image-only scanned PDFs. What makes this mirror different from a b…
Hi HN,My name is Matt and I've been working on a project called Manger, a mobile app used for livestock management. As a child, I grew up in a rural area with chickens, cows and other livestock around me. At the same tim…
…Adaptive Coordination of Understanding and Generation for Unified Multimodal Reasoning Published on May 12 Submitted by Jindong Wang on May 13 The College of William & Mary Authors: , , , , Abstract Unified multimodal models can…
…hf papers read 2605.12497 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite arxiv.org/abs/2605.12497 in…
…AI-generated summary Model merging combines task experts into one model and avoids joint training, retraining, or deploying many expert models, but the merged model often still underperforms task experts . We study…