Author name cluster

Ziyu Lu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

Shaoxiong Zhan
Yanlin Lai
Ziyu Lu
Dahua Lin
Ziqing Yang
Fei Tan

Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming human-written templates, limiting both diversity and scalability. We propose MathSmith, a novel framework for synthesizing challenging mathematical problems to enhance LLM reasoning. Rather than modifying existing problems, MathSmith constructs new ones from scratch by randomly sampling concept–explanation pairs from PlanetMath, ensuring data independence and avoiding contamination. To increase difficulty, we design nine predefined strategies as soft constraints during rationales. We further adopts reinforcement learning to jointly optimize structural validity, reasoning complexity, and answer consistency. The length of the reasoning trace generated under autoregressive prompting is used to reflect cognitive complexity, encouraging the creation of more demanding problems aligned with long-chain-of-thought reasoning. Experiments across five benchmarks, categorized as easy & medium (GSM8K, MATH-500) and hard (AIME2024, AIME2025, OlympiadBench), show that MathSmith consistently outperforms existing baselines under both short and long CoT settings. Additionally, a weakness-focused variant generation module enables targeted improvement on specific concepts. Overall, MathSmith exhibits strong scalability, generalization, and transferability, highlighting the promise of high-difficulty synthetic data in advancing LLM reasoning capabilities.

PDF Details DOI

IROS Conference 2025 Conference Paper

AnyTSR: Any-Scale Thermal Super-Resolution for UAV

Mengyuan Li
Changhong Fu 0001
Ziyu Lu
Zijie Zhang 0006
Haobo Zuo
Liangliang Yao

Thermal imaging can greatly enhance the application of intelligent unmanned aerial vehicles (UAV) in challenging environments. However, the inherent low resolution of thermal sensors leads to insufficient details and blurred boundaries. Super-resolution (SR) offers a promising solution to address this issue, while most existing SR methods are designed for fixed-scale SR. They are computationally expensive and inflexible in practical applications. To address above issues, this work proposes a novel any-scale thermal SR method (AnyTSR) for UAV within a single model. Specifically, a new image encoder is proposed to explicitly assign specific feature code to enable more accurate and flexible representation. Additionally, by effectively embedding coordinate offset information into the local feature ensemble, an innovative any-scale upsampler is proposed to better understand spatial relationships and reduce artifacts. Moreover, a novel dataset (UAV-TSR), covering both land and water scenes, is constructed for thermal SR tasks. Experimental results demonstrate that the proposed method consistently outperforms state-of-the-art methods across all scaling factors as well as generates more accurate and detailed high-resolution images. The code is located at https://github.com/vision4robotics/AnyTSR.

Details

IROS Conference 2025 Conference Paper

EdgeSR: Reparameterization-Driven Fast Thermal Super-Resolution for Edge Electro-Optical Device

Changhong Fu 0001
Ziyu Lu
Mengyuan Li
Zijie Zhang 0006
Haobo Zuo

Super-resolution (SR) can greatly promote the development of edge electro-optical (EO) devices. However, most existing SR models struggle to simultaneously achieve effective thermal reconstruction and real-time inference on edge EO devices with limited computing resources. To address these issues, this work proposes a novel fast thermal SR model (EdgeSR) for edge EO devices. Specifically, reparameterized scale-integrated convolutions (RepSConv) are proposed to deeply explore high-frequency features, incorporating multi-scale information and enhancing the scale-awareness of the backbone during the training phase. Furthermore, an inter-active reparameterization module (IRM), combining historical high-frequency with low-frequency information, is introduced to guide the extraction of high-frequency features, ultimately boosting the high-quality reconstruction of thermal images. Edge EO deployment-oriented reparameterization (EEDR) is designed to reparameterize all modules into standard convolutions that are hardware-friendly for edge EO devices and onboard real-time inference. Additionally, a new benchmark for thermal SR on cityscapes (CS-TSR) is built. The experimental results on this benchmark show that, compared to state-of-the-art lightweight SR networks, EdgeSR delivers superior reconstruction quality and faster inference speed on edge EO devices. In real-world applications, EdgeSR exhibits robust performance on edge EO devices, making it suitable for real-world deployment. The code and demo is available at https://github.com/vision4robotics/EdgeSR.

Details

ICLR Conference 2025 Conference Paper

NetFormer: An interpretable model for recovering dynamical connectivity in neuronal population dynamics

Ziyu Lu
Wuwei Zhang
Trung Le 0002
Hao Wang 0014
Uygar Sümbül
Eric Todd Shea-Brown
Lu Mi

Neuronal dynamics are highly nonlinear and nonstationary. Traditional methods for extracting the underlying network structure from neuronal activity recordings mainly concentrate on modeling static connectivity, without accounting for key nonstationary aspects of biological neural systems, such as ongoing synaptic plasticity and neuronal modulation. To bridge this gap, we introduce the NetFormer model, an interpretable approach applicable to such systems. In NetFormer, the activity of each neuron across a series of historical time steps is defined as a token. These tokens are then linearly mapped through a query and key mechanism to generate a state- (and hence time-) dependent attention matrix that directly encodes nonstationary connectivity structures. We analyze our formulation from the perspective of nonstationary and nonlinear networked dynamical systems, and show both via an analytical expansion and targeted simulations how it can approximate the underlying ground truth. Next, we demonstrate NetFormer's ability to model a key feature of biological networks, spike-timing-dependent plasticity, whereby connection strengths continually change in response to local activity patterns. We further demonstrate that NetFormer can capture task-induced connectivity patterns on activity generated by task-trained recurrent neural networks. Thus informed, we apply NetFormer to a multi-modal dataset of real neural recordings, which contains neural activity, cell type, and behavioral state information. We show that the NetFormer effectively predicts neural dynamics and identifies cell-type specific, state-dependent dynamic connectivity that matches patterns measured in separate ground-truth physiology experiments, demonstrating its ability to help decode complex neural interactions based on population activity observations alone.

Details

AAAI Conference 2017 Short Paper

Detecting Review Spammer Groups

Min Yang
Ziyu Lu
Xiaojun Chen
Fei Xu

With an increasing number of paid writers posting fake reviews to promote or demote some target entities through Internet, review spammer detection has become a crucial and challenging task. In this paper, we propose a three-phase method to address the problem of identifying review spammer groups and individual spammers, who get paid for posting fake comments. We evaluate the effectiveness and performance of the approach on a real-life online shopping review dataset from amazon. com. The experimental result shows that our model achieved comparable or better performance than previous work on spammer detection.

PDF Details