…noose tightens further it won't be officially discussed/acknowledged ( why would we?? we have so much to share with sell to the #community like this robot! look its so cute ) Maybe…
…https://github.com/fscdc/dMoE View arXiv page View PDF Project page GitHub 37 Add to collection Community Welcome discussion! I did not expect this to be as promising as it was…
…View arXiv page View PDF Add to collection Community This paper presents UniSteer, a text-guided flow matching framework for steering LLM activations. The goal is to provide a unified interface where…
Papers arxiv:2604.23426 Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy Published on Apr 25 Submitted by Emre ARDIÇ on Apr 30 Authors…
…We discuss methodological limitations and outline directions for improving the robustness of bias measurement. View arXiv page View PDF GitHub 1 Add to collection Community Elections represent a crucial milestone in a…
…View arXiv page View PDF GitHub 35 Add to collection Community Welcome everyone to join the discussion! Made an audio walkthrough of this paper for anyone who wants to skim it on…
Papers arxiv:2606.05304 What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems Published on Jun 3 Submitted by Chen Huang on Jun 10 iNLP Lab @ SUTD Authors: , , Abstract…
…View arXiv page View PDF Project page Add to collection Community WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models We introduce WorldCraft, an interactive video world model that…
…View arXiv page View PDF GitHub 0 Add to collection Community Excited to share our latest work on visual RAG! 🚀 Existing iRAG systems linearise documents into plain text, which (1) breaks visual…
…View arXiv page View PDF Project page GitHub 1 Add to collection Community Large-scale instruction tuning hits two walls: heterogeneous tasks produce conflicting gradients (negative transfer), and joint training needs constant…