Tootfinder

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu
https://arxiv.org/abs/2509.12603

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling strategies, notably reflective Chain-of-Thought (CoT) reasoning and increased sampling passes. However, they both introduce significant computational overhead for inference. Moreover, existing cost analyses typically regulate only the number of sampling passes, while neglecting the substantial disparities in sampling c…

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
Xu Zheng, Chenfei Liao, Ziqiao Weng, Kaiyu Lei, Zihao Dongfang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Lu Qi, Li Chen, Danda Pani Paudel, Kailun Yang, Linfeng Zhang, Luc Van Gool, Xuming Hu
https://arxiv.org/abs/2509.12989

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
Omnidirectional vision, using 360-degree vision to understand the environment, has become increasingly critical across domains like robotics, industrial inspection, and environmental monitoring. Compared to traditional pinhole vision, omnidirectional vision provides holistic environmental awareness, significantly enhancing the completeness of scene perception and the reliability of decision-making. However, foundational research in this area has historically lagged behind traditional pinhole vi…

When marine radar target detection meets pretrained large language models
Qiying Hu, Linping Zhang, Xueqian Wang, Gang Li, Yu Liu, Xiao-Ping Zhang
https://arxiv.org/abs/2509.12110

When marine radar target detection meets pretrained large language models
Deep learning (DL) methods are widely used to extract high-dimensional patterns from the sequence features of radar echo signals. However, conventional DL algorithms face challenges such as redundant feature segments, and constraints from restricted model sizes. To address these issues, we propose a framework that integrates feature preprocessing with large language models (LLMs). Our preprocessing module tokenizes radar sequence features, applies a patch selection algorithm to filter out uninf…

High-performance multiplexed readout of superconducting qubits with a tunable broadband Purcell filter
Yuzhe Xiong, Zilin Wang, Jiawei Zhang, Xuandong Sun, Zihao Zhang, Peisheng Huang, Yongqi Liang, Ji Jiang, Jiawei Qiu, Yuxuan Zhou, Xiayu Linpeng, Wenhui Huang, Jingjing Niu, Youpeng Zhong, Ji Chu, Song Liu, Dapeng Yu
https://arxiv.org/abs…

High-performance multiplexed readout of superconducting qubits with a tunable broadband Purcell filter
Fast, high-fidelity, and low back-action readout plays a crucial role in the advancement of quantum error correction (QEC). Here, we demonstrate high-performance multiplexed readout of superconducting qubits using a tunable broadband Purcell filter, effectively resolving the fundamental trade-off between measurement speed and photon-noise-induced dephasing. By dynamically tuning the filter parameters, we suppress photon-noise-induced dephasing by a factor of 7 in idle status, while enabling rap…

Learning to Generate 4D LiDAR Sequences
Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu, Linfeng Li, Lingdong Kong, Huaici Zhao, Wei Tsang Ooi
https://arxiv.org/abs/2509.11959 https:…

Learning to Generate 4D LiDAR Sequences
While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Extending generation to 4D LiDAR data introduces challenges in controllability, temporal stability, and evaluation. We present LiDARCrafter, a unified framework that converts free-form language into editable LiDAR sequences. Instructions are parsed into ego-centric scene graphs, which a tri-branch diffusion model transfor…

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
Xiangqi Jin, Yuxuan Wang, Yifeng Gao, Zichen Wen, Biqing Qi, Dongrui Liu, Linfeng Zhang
https://arxiv.org/abs/2508.10736

Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
Despite large language models (LLMs) have achieved remarkable success, their prefix-only prompting paradigm and sequential generation process offer limited flexibility for bidirectional information. Diffusion large language models (dLLMs) present new opportunities through their bidirectional attention mechanisms and iterative refinement processes, enabling more flexible in-place prompting strategies. We introduce ICE (In-Place Chain-of-Thought Prompting with Early Exit), a novel framework that …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/6]:
- Representation biases: will we achieve complete understanding by analyzing representations?
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Yuxuan Li, Katherine Hermann

Diverse high-Chern-number quantum anomalous Hall insulators in twisted rhombohedral graphene
Naitian Liu, Zhangyuan Chen, Jing Ding, Wenqiang Zhou, Hanxiao Xiang, Xinjie Fang, Linfeng Wu, Xiaowan Zhan, Le Zhang, Qianmei Chen, Kenji Watanabe, Takashi Taniguchi, Na Xin, Shuigang Xu
https://arxiv.org/abs/2507.11347

Diverse high-Chern-number quantum anomalous Hall insulators in twisted rhombohedral graphene
Quantum anomalous Hall (QAH) insulators with high Chern number (C) enables multiple dissipationless edge channels for low-power-consumption electronics. We report the realization of multiple high-C QAH insulators including C=3,5,6, and 7 in twisted monolayer-rhombohedral pentalayer graphene. In twist angles of approximately 1.40°, we observe QAH effect with C=5 at a filling of one electron per moiré unit cell, persisting up to 2 Kelvin. Furthermore, incommensurate QAH insulators with C=5,6, a…

It's less than 6 months to Xmas, you might as well vote for the Lego Idea
"National Lampoon's Christmas Vacation - Griswold House"
https://beta.ideas.lego.com/product-ideas/4e51e9fe-f325-4ae6-a835-45cac06da106
…

National Lampoon's Christmas Vacation - Griswold House | LEGO® Ideas
Are you serious Clark? - It’s the gift that keeps on giving the whole year! LEGO is the world’s most iconic toy and National Lampoon’s Christmas Vacation is on…

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
Zhixin Zheng, Xinyu Wang, Chang Zou, Shaobo Wang, Linfeng Zhang
https://arxiv.org/abs/2509.10312

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
Diffusion transformers have gained significant attention in recent years for their ability to generate high-quality images and videos, yet still suffer from a huge computational cost due to their iterative denoising process. Recently, feature caching has been introduced to accelerate diffusion transformers by caching the feature computation in previous timesteps and reusing it in the following timesteps, which leverage the temporal similarity of diffusion models while ignoring the similarity in…