Author name cluster

Haoze Sun

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.

6 papers

2 author rows

ICLR Conference 2025 Conference Paper

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

Mingyang Chen 0002
Haoze Sun
Tianpeng Li
Fan Yang 0132
Hao Liang 0017
Keer Lu
Bin Cui 0001
Wentao Zhang 0001

Large Language Models (LLMs) have exhibited significant potential in performing diverse tasks, including the ability to call functions or use external tools to enhance their performance. While current research on function calling by LLMs primarily focuses on single-turn interactions, this paper addresses the overlooked necessity for LLMs to engage in multi-turn function calling—critical for handling compositional, real-world queries that require planning with functions but not only use functions. To facilitate this, we introduce an approach, BUTTON, which generates synthetic compositional instruction tuning data via bottom-up instruction construction and top-down trajectory generation. In the bottom-up phase, we generate simple atomic tasks based on real-world scenarios and build compositional tasks using heuristic strategies based on atomic tasks. Corresponding function definitions are then synthesized for these compositional tasks. The top-down phase features a multi-agent environment where interactions among simulated humans, assistants, and tools are utilized to gather multi-turn function calling trajectories. This approach ensures task compositionality and allows for effective function and trajectory generation by examining atomic tasks within compositional tasks. We produce a dataset BUTTONInstruct comprising 8k data points and demonstrate its effectiveness through extensive experiments across various LLMs.

Details

NeurIPS Conference 2025 Conference Paper

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

Haoze Sun
Linfeng Jiang
Fan Li
Renjing Pei
Zhixin Wang
Yong Guo
Jiaqi Xu
Haoyu Chen

Real-world image super-resolution (RealSR) aims to enhance the visual quality of in-the-wild images, such as those captured by mobile phones. While existing methods leveraging large generative models demonstrate impressive results, the high computational cost and latency make them impractical for edge deployment. In this paper, we introduce PocketSR, an ultra-lightweight, single-step model that brings generative modeling capabilities to RealSR while maintaining high fidelity. To achieve this, we design LiteED, a highly efficient alternative to the original computationally intensive VAE in SD, reducing parameters by 97. 5\% while preserving high-quality encoding and decoding. Additionally, we propose online annealing pruning for the U-Net, which progressively shifts generative priors from heavy modules to lightweight counterparts, ensuring effective knowledge transfer and further optimizing efficiency. To mitigate the loss of prior knowledge during pruning, we incorporate a multi-layer feature distillation loss. Through an in-depth analysis of each design component, we provide valuable insights for future research. PocketSR, with a model size of 146M parameters, processes 4K images in just 0. 8 seconds, achieving a remarkable speedup over previous methods. Notably, it delivers performance on par with state-of-the-art single-step and even multi-step RealSR models, making it a highly practical solution for edge-device applications.

PDF Details

NeurIPS Conference 2025 Conference Paper

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Mingyang Chen
Linzhuang Sun
Tianpeng Li
Haoze Sun
Chenzheng Zhu
Haofen Wang
Jeff Pan
Wen Zhang

Large Language Models (LLMs) have shown remarkable capabilities in reasoning, exemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating reasoning with external search processes remains challenging, especially for complex multi-hop questions requiring multiple retrieval steps. We propose ReSearch, a novel framework that trains LLMs to Reason with Search via reinforcement learning without using any supervised data on reasoning steps. Our approach treats search operations as integral components of the reasoning chain, where when and how to perform searches is guided by text-based thinking, and search results subsequently influence further reasoning. We train ReSearch on Qwen2. 5-7B(-Instruct) and Qwen2. 5-32B(-Instruct) models and conduct extensive experiments. Despite being trained on only one dataset, our models demonstrate strong generalizability across various benchmarks. Analysis reveals that ReSearch naturally elicits advanced reasoning capabilities such as reflection and self-correction during the reinforcement learning process.

PDF Details

ICLR Conference 2025 Conference Paper

SysBench: Can LLMs Follow System Message?

Yanzhao Qin
Tao Zhang 0194
Yanjun Shen
Wenjing Luo
Haoze Sun
Yan Zhang 0109
Yujing Qiao
Weipeng Chen

Large Language Models (LLMs) have become instrumental across various applications, with the customization of these models to specific scenarios becoming increasingly critical. System message, a fundamental component of LLMs, is consist of carefully crafted instructions that guide the behavior of model to meet intended goals. Despite the recognized potential of system messages to optimize AI-driven solutions, there is a notable absence of a comprehensive benchmark for evaluating how well LLMs follow system messages. To fill this gap, we introduce SysBench, a benchmark that systematically analyzes system message following ability in terms of three limitations of existing LLMs: constraint violation, instruction misjudgement and multi-turn instability. Specifically, we manually construct evaluation dataset based on six prevalent types of constraints, including 500 tailor-designed system messages and multi-turn user conversations covering various interaction relationships. Additionally, we develop a comprehensive evaluation protocol to measure model performance. Finally, we conduct extensive evaluation across various existing LLMs, measuring their ability to follow specified constraints given in system messages. The results highlight both the strengths and weaknesses of existing models, offering key insights and directions for future research.

Details

IJCAI Conference 2024 Conference Paper

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

Gongye Liu
Haoze Sun
Jiayi Li
Fei Yin
Yujiu Yang

Diffusion models have recently demonstrated an impressive ability to address inverse problems in an unsupervised manner. While existing methods primarily focus on modifying the posterior sampling process, the potential of the forward process remains largely unexplored. In this work, we propose Shortcut Sampling for Diffusion(SSD), a novel approach for solving inverse problems in a zero-shot manner. Instead of initiating from random noise, the core concept of SSD is to find a specific transitional state that bridges the measurement image y and the restored image x. By utilizing the shortcut path of "input - transitional state - output", SSD can achieve precise restoration with fewer steps. To derive the transitional state during the forward process, we introduce Distortion Adaptive Inversion. Moreover, we apply back projection as additional consistency constraints during the generation process. Experimentally, we demonstrate SSD's effectiveness on multiple representative IR tasks. Our method achieves competitive results with only 30 NFEs compared to state-of-the-art zero-shot methods(100 NFEs) and outperforms them with 100 NFEs in certain tasks. Code is available at https: //github. com/GongyeLiu/SSD.

PDF Details DOI

AAAI Conference 2017 Conference Paper

Variational Autoencoder for Semi-Supervised Text Classification

Weidi Xu
Haoze Sun
Chao Deng
Ying Tan

Although semi-supervised variational autoencoder (SemiVAE) works in image classiﬁcation task, it fails in text classiﬁcation task if using vanilla LSTM as its decoder. From a perspective of reinforcement learning, it is veriﬁed that the decoder’s capability to distinguish between different categorical labels is essential. Therefore, Semi-supervised Sequential Variational Autoencoder (SSVAE) is proposed, which increases the capability by feeding label into its decoder RNN at each time-step. Two speciﬁc decoder structures are investigated and both of them are veriﬁed to be effective. Besides, in order to reduce the computational complexity in training, a novel optimization method is proposed, which estimates the gradient of the unlabeled objective function by sampling, along with two variance reduction techniques. Experimental results on Large Movie Review Dataset (IMDB) and AG’s News corpus show that the proposed approach signiﬁcantly improves the classiﬁcation accuracy compared with pure-supervised classiﬁers, and achieves competitive performance against previous advanced methods. State-of-the-art results can be obtained by integrating other pretraining-based methods.

PDF Details