Siyuan Wang

AAAI Conference 2026 Conference Paper

OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion

• Xian Guo
• Ben Chen
• Siyuan Wang
• Ying Yang
• Mingyue Cheng
• Chenyi Lei
• Yuqing Ding
• Han Li

Query suggestion plays a crucial role in enhancing user experience in e-commerce search systems by providing relevant query recommendations that align with users' initial input. This module helps users navigate towards personalized preference needs and reduces typing effort, thereby improving search experience. Traditional query suggestion modules usually adopt multi-stage cascading architectures, for making a well trade-off between system response time and business conversion. But they often suffer from inefficiencies and suboptimal performance due to inconsistent optimization objectives across stages. To address these, we propose OneSug, the first end-to-end generative framework for e-commerce query suggestion. OneSug incorporates a prefix2query representation enhancement module to enrich prefixes using semantically and interactively related queries to bridge content and business characteristics, an encoder-decoder generative model that unifies the query suggestion process, and a reward-weighted ranking strategy with behavior-level weights to capture fine-grained user preferences. Extensive evaluations on large-scale industry datasets demonstrate OneSug's ability for effective and efficient query suggestion. Furthermore, OneSug has been successfully deployed for the entire traffic on the e-commerce search engine in TEST platform for over 1 month, with statistically significant improvements in user top click position (-9.33%), CTR (+2.01%), Order (+2.04%), and Revenue (+1.69%) over the online multi-stage strategy, showing great potential in e-commercial conversion.

ICML Conference 2025 Conference Paper

LongRoPE2: Near-Lossless LLM Context Window Scaling

• Ning Shang
• Li Lyna Zhang
• Siyuan Wang
• Gaokai Zhang
• Gilsinia Lopez
• Fan Yang 0024
• Weizhu Chen
• Mao Yang 0004

LongRoPE2 is a novel approach that extends the effective context window of pre-trained large language models (LLMs) to the target length, while preserving the performance on the original shorter context window. This is achieved by three contributions: (1) a hypothesis that insufficient training in higher RoPE dimensions contributes to the persistent out-of-distribution (OOD) issues observed in existing methods; (2) an effective RoPE rescaling algorithm that adopts evolutionary search guided by "needle-driven" perplexity to address the insufficient training problem; (3) a mixed context window training approach that fine-tunes model weights to adopt rescaled RoPE for long-context sequences while preserving the short-context performance with the original RoPE. Extensive experiments on LLaMA3-8B and Phi3-mini-3. 8B across various benchmarks validate the hypothesis and demonstrate the effectiveness of LongRoPE2. Remarkably, LongRoPE2 extends LLaMA3-8B to achieve a 128K effective context length while retaining over 98. 5% of short-context performance, using only 10B tokens – 80x fewer than Meta’s approach, which fails to reach the target effective context length.

AIIM Journal 2025 Journal Article

Medical multimodal foundation models in clinical diagnosis and treatment: Applications, challenges, and future directions

• Kai Sun
• Siyan Xue
• Fuchun Sun
• Haoran Sun
• Yu Luo
• Ling Wang
• Siyuan Wang
• Na Guo

NeurIPS Conference 2025 Conference Paper

Prompt-guided Disentangled Representation for Action Recognition

• Tianci Wu
• Guangming Zhu
• Lu Jiang
• Siyuan Wang
• Ning Wang
• Nuoye Xiong
• Liang Zhang

Action recognition is a fundamental task in video understanding. Existing methods typically extract unified features to process all actions in one video, which makes it challenging to model the interactions between different objects in multi-action scenarios. To alleviate this issue, we explore disentangling any specified actions from complex scenes as an effective solution. In this paper, we propose Prompt-guided Disentangled Representation for Action Recognition (ProDA), a novel framework that disentangles any specified actions from a multi-action scene. ProDA leverages Spatio-temporal Scene Graphs (SSGs) and introduces Dynamic Prompt Module (DPM) to guide a Graph Parsing Neural Network (GPNN) in generating action-specific representations. Furthermore, we design a video-adapted GPNN that aggregates information using dynamic weights. Extensive experiments on two complex video action datasets, Charades and SportsHHI, demonstrate the effectiveness of our approach against state-of-the-art methods. Our code can be found in https: //github. com/iamsnaping/ProDA. git.

AAAI Conference 2025 Conference Paper

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

• Shengbin Yue
• Siyuan Wang
• Wei Chen
• Xuanjing Huang
• Zhongyu Wei

Recent advancements in Large Language Models (LLMs) have led to significant breakthroughs in various natural language processing tasks. However, generating factually consistent responses in knowledge-intensive scenarios remains a challenge due to issues such as hallucination, difficulty in acquiring long-tailed knowledge, and limited memory expansion. This paper introduces SMART, a novel multi-agent framework that leverages external knowledge to enhance the interpretability and factual consistency of LLM-generated responses. SMART comprises four specialized agents, each performing a specific sub-trajectory action to navigate complex knowledge-intensive tasks. We propose a multi-agent co-training paradigm, Long-Short Trajectory Learning, which ensures synergistic collaboration among agents while maintaining fine-grained execution by each agent. Extensive experiments on five knowledge-intensive tasks demonstrate SMART's superior performance compared to widely adopted knowledge internalization and knowledge enhancement methods. Our framework can extend beyond knowledge-intensive tasks to more complex scenarios.

AAAI Conference 2024 Conference Paper

Enhance Sketch Recognition’s Explainability via Semantic Component-Level Parsing

• Guangming Zhu
• Siyuan Wang
• Tianci Wu
• Liang Zhang

Free-hand sketches are appealing for humans as a universal tool to depict the visual world. Humans can recognize varied sketches of a category easily by identifying the concurrence and layout of the intrinsic semantic components of the category, since humans draw free-hand sketches based a common consensus that which types of semantic components constitute each sketch category. For example, an airplane should at least have a fuselage and wings. Based on this analysis, a semantic component-level memory module is constructed and embedded in the proposed structured sketch recognition network in this paper. The memory keys representing semantic components of each sketch category can be self-learned and enhance the recognition network's explainability. Our proposed networks can deal with different situations of sketch recognition, i.e., with or without semantic components labels of strokes. Experiments on the SPG and SketchIME datasets demonstrate the memory module's flexibility and the recognition network's explainability. The code and data are available at https://github.com/GuangmingZhu/SketchESC.

IJCAI Conference 2021 Conference Paper

TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning

• Zhihao Fan
• Zhongyu Wei
• Siyuan Wang
• Ruize Wang
• Zejun Li
• Haijun Shan
• Xuanjing Huang

Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image Captioning (TCIC) framework that incorporates theme concepts to represent high-level cross-modality semantics. In practice, we model theme concepts as memory vectors and propose Transformer with Theme Nodes (TTN) to incorporate those vectors for image captioning. Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN. On the vision side, TTN is configured to take both scene graph based features and theme concepts as input for visual representation learning. On the language side, TTN is configured to take both captions and theme concepts as input for text representation re-construction. Both settings aim to generate target captions with the same transformer-based decoder. During the training, we further align representations of theme concepts learned from images and corresponding captions to enforce the cross-modality learning. Experimental results on MS COCO show the effectiveness of our approach compared to some state-of-the-art models.

ICRA Conference 2020 Conference Paper

On Generalized Homogenization of Linear Quadrotor Controller

• Siyuan Wang
• Andrey E. Polyakov
• Gang Zheng 0002

A novel scheme for an "upgrade" of a linear control algorithm to a non-linear one is developed based on the concepts of a generalized homogeneity and an implicit homogeneous feedback design. Some tuning rules for a guaranteed improvement of a regulation quality are proposed. Theoretical results are confirmed by real experiments with the quadrotor QDrone of Quanser™.

AAAI Conference 2019 Conference Paper

A Multi-Agent Communication Framework for Question-Worthy Phrase Extraction and Question Generation

• Siyuan Wang
• Zhongyu Wei
• Zhihao Fan
• Yang Liu
• Xuanjing Huang

Question generation aims to produce questions automatically given a piece of text as input. Existing research follows a sequence-to-sequence fashion that constructs a single question based on the input. Considering each question usually focuses on a specific fragment of the input, especially in the scenario of reading comprehension, it is reasonable to identify the corresponding focus before constructing the question. In this paper, we propose to identify question-worthy phrases first and generate questions with the assistance of these phrases. We introduce a multi-agent communication framework, taking phrase extraction and question generation as two agents, and learn these two tasks simultaneously via message passing mechanism. The results of experiments show the effectiveness of our framework: we can extract question-worthy phrases, which are able to improve the performance of question generation. Besides, our system is able to extract more than one question worthy phrases and generate multiple questions accordingly.