Tootfinder

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models
Haotian Wu, Bo Xu, Yao Shu, Menglin Yang, Chengwei Qin
https://arxiv.org/abs/2508.03363

Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models
Reasoning large language models (RLLMs) have recently demonstrated remarkable capabilities through structured and multi-step reasoning. While prior research has primarily focused on improving their training and inference strategies, their potential for in-context learning (ICL) remains largely underexplored. To fill this gap, we propose Thinking with Nothinking Calibration (JointThinking), a new ICL paradigm that leverages the structured difference between two reasoning modes, i.e., Thinking an…

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Text-to-Image Generation
Lianwei Yang, Haokun Lin, Tianchen Zhao, Yichen Wu, Hongyu Zhu, Ruiqi Xie, Zhenan Sun, Yu Wang, Qingyi Gu
https://arxiv.org/abs/2508.03485

LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Text-to-Image Generation
Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image generation. However, their high computational cost and large parameter sizes pose significant challenges for usage in resource-constrained scenarios. Post-training quantization (PTQ) is a promising solution to reduce memory usage and accelerate inference, but existing PTQ methods suffer from severe performance degradation under extreme low-bit settings. We identify two key obstacles to low-bit post-training quan…

Alibaba releases its Qwen3-235B-A22B-Thinking-2507 reasoning LLM on Hugging Face, topping several benchmarks, as Alibaba moves away from hybrid reasoning models (Carl Franzen/VentureBeat)
https://venturebeat.com/ai/its-qwens-s…

HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
Yibin Liu, Zhixuan Liang, Zanxin Chen, Tianxing Chen, Mengkang Hu, Wanxi Dong, Congsheng Xu, Zhaoming Han, Yusen Qin, Yao Mu
https://arxiv.org/abs/2508.02629

HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents
Recent advances in multimodal large language models (MLLMs) have enabled richer perceptual grounding for code policy generation in embodied agents. However, most existing systems lack effective mechanisms to adaptively monitor policy execution and repair codes during task completion. In this work, we introduce HyCodePolicy, a hybrid language-based control framework that systematically integrates code synthesis, geometric grounding, perceptual monitoring, and iterative repair into a closed-loop …

Rethinking Thinking Tokens: LLMs as Improvement Operators
Lovish Madaan, Aniket Didolkar, Suchin Gururangan, John Quan, Ruan Silva, Ruslan Salakhutdinov, Manzil Zaheer, Sanjeev Arora, Anirudh Goyal
https://arxiv.org/abs/2510.01123

Rethinking Thinking Tokens: LLMs as Improvement Operators
Reasoning training incentivizes LLMs to produce long chains of thought (long CoT), which among other things, allows them to explore solution strategies with self-checking. This results in higher accuracy, but inflates context length, token/compute cost, and answer latency. We ask: Can current models leverage their metacognition to provide other combinations on this Pareto frontier, e.g., better accuracy with lower context length and/or latency? Abstractly, we view the model as an improvement op…

Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation
Zikai Huang, Yihan Zhou, Xuemiao Xu, Cheng Xu, Xiaofen Xing, Jing Qin, Shengfeng He
https://arxiv.org/abs/2509.02278

Think2Sing: Orchestrating Structured Motion Subtitles for Singing-Driven 3D Head Animation
Singing-driven 3D head animation is a challenging yet promising task with applications in virtual avatars, entertainment, and education. Unlike speech, singing involves richer emotional nuance, dynamic prosody, and lyric-based semantics, requiring the synthesis of fine-grained, temporally coherent facial motion. Existing speech-driven approaches often produce oversimplified, emotionally flat, and semantically inconsistent results, which are insufficient for singing animation. To address this, w…

Fabrication and Characterization of the Moir\'e surface state on a topological insulator
Yi Zhang, Dang Liu, Qiaoyan Yu, Ruijun Xi, Xingsen Chen, Shasha Xue, Jice Sun, Xian Du, Xuhui Ning, Tingwen Miao, Pengyu Hu, Hao Yang, Dandan Guan, Xiaoxue Liu, Liang Liu, Yaoyi Li, Shiyong Wang, Canhua Liu, Haijiao Ji, Noah F. Q. Yuan, Hao Zheng, Jinfeng Jia
https://…

Fabrication and Characterization of the Moiré surface state on a topological insulator
A Moire superlattice on the topological insulator surface is predicted to exhibit many novel properties but has not been experimentally realized. Here, we developed a two-step growth method to successfully fabricate a topological insulator Sb2Te3 thin film with a Moire superlattice, which is generated by a twist of the topmost layer via molecular beam epitaxy. The established Moire topological surface state is characterized by scanning tunneling microscopy and spectroscopy. By application of a …

Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications in AI-assisted Data Analysis
Qianou Ma, Kenneth Koedinger, Tongshuang Wu
https://arxiv.org/abs/2509.21890

Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications in AI-assisted Data Analysis
LLMs promise to democratize technical work in complex domains like programmatic data analysis, but not everyone benefits equally. We study how students with varied expertise use LLMs to complete Python-based data analysis in computational notebooks in a non-major course. Drawing on homework logs, recordings, and surveys from 36 students, we ask: Which expertise matters most, and how does it shape AI use? Our mixed-methods analysis shows that technical expertise -- not AI familiarity or communic…

Mi primer intento de churros en casa SIN, quizšs lo mšs importante, manga churrera. Estaban ricos a trozos. Las partes finas se hacen demasiado y son demasiado crujientes (no estšn mal pero no son churros). Las partes mšs gruesas quedaban un poco crudas por dentro (igual, no estšn mal, pero no son churros). Es muy importante la manga churrera para que tengan el tamaño ideal y que se frían correctamente. Quien dijo "te ha salido un churro" seguramente quería decir "hecho sin m…

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Tianjian Liu, Fanqi Wan, Jiajian Guo, Xiaojun Quan
https://arxiv.org/abs/2508.20973 https://

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents
Proactive dialogue has emerged as a critical and challenging research problem in advancing large language models (LLMs). Existing works predominantly focus on domain-specific or task-oriented scenarios, which leads to fragmented evaluations and limits the comprehensive exploration of models' proactive conversation abilities. In this work, we propose ProactiveEval, a unified framework designed for evaluating proactive dialogue capabilities of LLMs. This framework decomposes proactive dialogue in…