Tootfinder

Scaling Agents via Continual Pre-training
Liangcai Su, Zhen Zhang, Guangyu Li, Zhuo Chen, Chenxi Wang, Maojia Song, Xinyu Wang, Kuan Li, Jialong Wu, Xuanzhong Chen, Zile Qiao, Zhongwang Zhang, Huifeng Yin, Shihao Cai, Runnan Fang, Zhengwei Tao, Wenbiao Yin, Chenxiong Qian, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou
https://arxiv.org/…

Scaling Agents via Continual Pre-training
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models consistently underperform in agentic tasks, particularly in open-source implementations. We identify the root cause: the absence of robust agentic foundation models forces models during post-training to simultaneously learn diverse agentic behaviors while aligning them…

For a president who wants to project vigor and command at all times, Donald Trump made the worst possible spectacle of himself in the Oval Office last Thursday
when a participant fainted and several officials on hand rushed over.
-- Not Trump, however, who, after turning to look at the fallen man, stood a few feet away at the Resolute Desk with his back to the action, wearing an indifferent expression.
This was pointedly reflected in news photos that instantly went viral.

Donald Trump Is a Lamer Duck Than Ever
Even though he doesn’t want you to think so

Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training
Xin Fang, Guirui Zhong, Qing Wang, Fan Chu, Lei Wang, Mengui Qian, Mingqi Cai, Jiangzhao Wu, Jianqing Gao, Jun Du
https://arxiv.org/abs/2509.12845

Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training
Anomalous Sound Detection (ASD) is often formulated as a machine attribute classification task, a strategy necessitated by the common scenario where only normal data is available for training. However, the exhaustive collection of machine attribute labels is laborious and impractical. To address the challenge of missing attribute labels, this paper proposes an agglomerative hierarchical clustering method for the assignment of pseudo-attribute labels using representations derived from a domain-a…

Laminar: A Scalable Asynchronous RL Post-Training Framework
Guangming Sheng, Yuxuan Tong, Borui Wan, Wang Zhang, Chaobo Jia, Xibin Wu, Yuqi Wu, Xiang Li, Chi Zhang, Yanghua Peng, Haibin Lin, Xin Liu, Chuan Wu
https://arxiv.org/abs/2510.12633

Laminar: A Scalable Asynchronous RL Post-Training Framework
Reinforcement learning (RL) post-training for Large Language Models (LLMs) is now scaling to large clusters and running for extended durations to enhance model reasoning performance. However, the scalability of existing RL frameworks is limited, as extreme long-tail skewness in RL trajectory generation causes severe GPU underutilization. Current asynchronous RL systems attempt to mitigate this, but they rely on global weight synchronization between the actor and all rollouts, which creates a ri…

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo
https://arxiv.org/abs/2510.12218

GOAT: A Training Framework for Goal-Oriented Agent with Tools
Large language models (LLMs) have recently been extended beyond traditional text generation to serve as interactive agents capable of using external tools based on user intent. However, current LLM agents still show limited ability to handle goal-oriented queries, which require decomposing a high-level objective into multiple interdependent API calls with correct planning and execution. Current approaches mainly rely on zero-shot evaluation due to the absence of training data. While proprietary…

Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain
Yuqi Xie, Shuhan Ye, Chong Wang, Jiazhen Xu, Le Shen, Yuanbin Qian, Jiangbo Qian
https://arxiv.org/abs/2509.12959

Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain
The integration of event cameras and spiking neural networks holds great promise for energy-efficient visual processing. However, the limited availability of event data and the sparse nature of DVS outputs pose challenges for effective training. Although some prior work has attempted to transfer semantic knowledge from RGB datasets to DVS, they often overlook the significant distribution gap between the two modalities. In this paper, we propose Time-step Mixup knowledge transfer (TMKT), a novel…

GeoPipe: a Geo-distributed LLM Training Framework with enhanced Pipeline Parallelism in a Lossless RDMA-enabled Datacenter Optical Transport Network
Jun Dai, Xiaorun Wang, Kexiong Fang, Zheng Yang, Yuefeng Ji, Jiawei Zhang
https://arxiv.org/abs/2510.12064

GeoPipe: a Geo-distributed LLM Training Framework with enhanced Pipeline Parallelism in a Lossless RDMA-enabled Datacenter Optical Transport Network
The proliferation of Large Language Models (LLMs) with exponentially growing parameters is making cross-data center (DC) training an inevitable trend. However, viable strategies for extending single-DC training frameworks to multi-DC environments remain underdeveloped. We experimentally demonstrate, for the first time, a high-performance geo-distributed LLMs training framework across multiple DCs interconnected by a lossless, remote direct memory access (RDMA) enabled Datacenter Optical Transpo…

MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillation
Minqing Huang, Shouyi Lu, Boyuan Zheng, Ziyao Li, Xiao Tang, Guirong Zhuo
https://arxiv.org/abs/2509.13149

MSDNet: Efficient 4D Radar Super-Resolution via Multi-Stage Distillation
4D radar super-resolution, which aims to reconstruct sparse and noisy point clouds into dense and geometrically consistent representations, is a foundational problem in autonomous perception. However, existing methods often suffer from high training cost or rely on complex diffusion-based sampling, resulting in high inference latency and poor generalization, making it difficult to balance accuracy and efficiency. To address these limitations, we propose MSDNet, a multi-stage distillation framew…

A Synthetic Data Pipeline for Supporting Manufacturing SMEs in Visual Assembly Control
Jonas Werheid, Shengjie He, Aymen Gannouni, Anas Abdelrazeq, Robert H. Schmitt
https://arxiv.org/abs/2509.13089

A Synthetic Data Pipeline for Supporting Manufacturing SMEs in Visual Assembly Control
Quality control of assembly processes is essential in manufacturing to ensure not only the quality of individual components but also their proper integration into the final product. To assist in this matter, automated assembly control using computer vision methods has been widely implemented. However, the costs associated with image acquisition, annotation, and training of computer vision algorithms pose challenges for integration, especially for small- and medium-sized enterprises (SMEs), whic…

End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection
Fei Wang, Xuecheng Wu, Zheng Zhang, Danlei Huang, Yuheng Huang, BoWang
https://arxiv.org/abs/2509.13214

End4: End-to-end Denoising Diffusion for Diffusion-Based Inpainting Detection
The powerful generative capabilities of diffusion models have significantly advanced the field of image synthesis, enhancing both full image generation and inpainting-based image editing. Despite their remarkable advancements, diffusion models also raise concerns about potential misuse for malicious purposes. However, existing approaches struggle to identify images generated by diffusion-based inpainting models, even when similar inpainted images are included in their training data. To address …