…A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction Published on May 12 Submitted by HuggingFace Zhang on May 13 Peking University Authors: , Zeyu Zhang , , , Abstract Lite3R addresses efficiency challenges in…
…AI-generated summary Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies…
Papers arxiv:2605.10468 Can Muon Fine-tune Adam-Pretrained Models? Published on May 11 Submitted by Xingyu Qu on May 12 Mohamed Bin Zayed University of Artificial Intelligence Authors: Xingyu Qu…
…hf papers read 2605.13037 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite arxiv.org/abs/2605.13037 in…
…AI-generated summary We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation…
…AI-generated summary Recent generative models can produce images that appear highly realistic, raising challenges in distinguishing real and AI-generated images. Yet existing detectors based on pre-trained feature extractors tend…
…hf papers read 2605.13481 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite arxiv.org/abs/2605.13481 in…
…Yuxiang Ji , , , , , , , , Abstract Agentic reinforcement learning for large language models leverages action data from human interactions as reference guidance to improve exploration and reduce dependence on costly supervised fine-tuning. AI-generated…
…hf papers read 2605.10921 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No model linking this paper Cite arxiv.org/abs/2605.10921 in…
Papers arxiv:2605.04330 The Scaling Properties of Implicit Deductive Reasoning in Transformers Published on May 5 Submitted by Enrico on May 8 Applied AI group of the Tallinn University of Technology…