The paper demonstrates that improving the design of queries used for information extraction can boost performance more than scaling up extraction models. By introducing List of Questions (LoQ) and a feedback-driven optimization method called FeedQ, the authors generate document-specific question sets that, when used to fine‑tune lightweight 4B‑parameter models, match or surpass expert‑derived baselines and outperform larger untuned models. They also release a dataset of 12,820 optimized questions to encourage treating question design as a primary research focus.
By Omar Sharif, Soroush Vosoughi, Nikhil Singh
Motus2 is a self‑evolving general world model designed for dexterous manipulation. It integrates a shared‑weight model that offers three control interfaces—a policy, a simulator, and an evaluator—forming a closed decision‑and‑learning loop for policy improvement. The system scales both model size and data, progressing from large‑scale monocular egocentric data to synchronized stereo data and robot‑domain adaptation, while also incorporating tactile feedback and a biomimetic platform with dual arms and hands.
By Hongzhe Bi, Zihao Zhou, Yihang Tang, Jingrui Pang, Shuhe Huang, Haitian Liu, Runqing Wang, Shuai Huang, Yichen Wang, Yiming Cheng, Ruowen Zhao, Zhenghua Li, Hengkai Tan, Xiaolong Liu, Jinhui Wan, Jiabao Liu, Min Zhao, Fan Bao, Jun Zhu
The paper introduces SinLlama, the first decoder‑based open‑source large language model with explicit support for Sinhala. By extending Llama‑3‑8B, adding Sinhala‑specific tokenizer vocabulary, and performing continual pre‑training on a cleaned 10‑million‑token Sinhala corpus, the authors created a model that surpasses both the base and instruction‑fine‑tuned variants of Llama‑3‑8B on three text classification tasks. This work addresses the underrepresentation of low‑resource languages in open‑source LLMs.
By H. W. K. Aravinda, Rashad Sirajudeen, Samith Karunathilake, Nisansa de Silva, Surangika Ranathunga, Rishemjit Kaur
HERBIOME is a modular, end‑to‑end pipeline that automates the digitization of herbarium labels. It combines YOLOv8 for component detection, CRAFT Hezar for word‑level text localization, a fine‑tuned TrOCR model for mixed handwritten and printed text recognition, and GPT‑4o Mini for structuring metadata into standardized fields. Evaluation on 450 French specimens shows high surface similarity (MWS ≈ 0.616) and moderate semantic accuracy (SMA ≈ 0.442), with taxonomic fields identified as the main challenge.
By Hiba Abbad, Hanane Ariouat, Eva Perez Pimpare, Nicolas Turenne, Eric Chenin, Abderrazak Sebaa, Edi Prifti, Jean-Daniel Zucker, Youcef Sklab
arXiv:2608.30427v1 Announce Type: cross
Abstract: Speculative decoding speeds up generation with an efficient draft model (drafter) that proposes tokens for a target model to verify in one pass, pres...
By Ephrem Wu
arXiv:2608.28647v1 Announce Type: new
Abstract: Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before a...
By Yifei Li, Rongman Xu, Lingling Zhang, Muye Huang, Zihan Ma, Jiashuai Liu, Hang Yan, Heng Wang
arXiv:2608.28967v1 Announce Type: cross
Abstract: Electroencephalography (EEG)-based robotic control is commonly formulated as a direct classification problem, in which electrical neural signals are...
By Alexandr Plashchinsky
arXiv:2608.30908v1 Announce Type: new
Abstract: Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practi...
By Shiguang Wu, Zhouchen Lin, Quanming Yao
The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.
By Qiancheng Zhou, Ruizhe Li
arXiv:2608.28725v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used as graders, verifiers, and process auditors, but most mathematical evaluations still emphasize final...
By Fateme Mazdarani, Carlos Toxtli
arXiv:2605.28042v2 Announce Type: replace-cross
Abstract: Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but they do so as broad generalists largely tra...
By Liu O. Martin, Lucas Bandarkar, Nanyun Peng
arXiv:2608.29168v1 Announce Type: new
Abstract: The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model...
By Yiyue Qian, Shinan Zhang, Huan Song, Hannah Marlowe
arXiv:2608.29170v1 Announce Type: new
Abstract: This paper proposes the Sinitic Romanization Ecosystem, a cross-lingual Sinitic romanization design framework with supporting digital infrastructure an...
By Zijie Zhang, Tan Lee, Yong Cao, Benyou Wang
arXiv:2605.27971v2 Announce Type: replace-cross
Abstract: When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a f...
By Kerui Peng, Feifei Li, Xingyu Fan, Wenhui Que
arXiv:2512.03400v2 Announce Type: replace-cross
Abstract: We study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers, using Rubik's...
By Prakhar Gupta, Henry Conklin, Sarah-Jane Leslie, Andrew Lee
arXiv:2511.20022v3 Announce Type: replace-cross
Abstract: Recent advancements in multimodal large language models (MLLMs) have shown strong understanding of driving scenes, drawing interest in their...
By Seungjun Yu, Seonho Lee, Namho Kim, Jaeyo Shin, Junsung Park, Wonjeong Ryu, Raehyuk Jung, Hyunjung Shim
arXiv:2503.00030v3 Announce Type: replace-cross
Abstract: Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference...
By Xiaohang Tang, Sangwoong Yoon, Seongho Son, Huizhuo Yuan, Quanquan Gu, Ilija Bogunovic
arXiv:2608.30025v1 Announce Type: new
Abstract: Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distingui...
By Hao Yan, Ziyu Yao
arXiv:2604.18364v2 Announce Type: replace
Abstract: Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reas...
By Ravidu Suien Rammuni Silva, Ahmad Lotfi, Isibor Kennedy Ihianle, Golnaz Shahtahmassebi, Jordan J. Bird
arXiv:2608.30609v1 Announce Type: cross
Abstract: Large language models are increasingly capable in general, but their utility can remain modest in niche or understudied areas. One approach to addres...
By Lukas Borggren, Jenny Kunz, Marco Kuhlmann