Author name cluster

Siyi Wang

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs

Xiang Fang
Wanlong Fang
Changshuo Wang
Keke Tang
Daizong Liu
Siyi Wang
Wei Ji

Video-Language Models (VLMs) have demonstrated impressive multi-modal reasoning capabilities across diverse computer vision applications. However, these VLMs are task-specific and assume that both video and language inputs are complete. However, real-world VLM applications might face challenges due to deactivated sensors (e.g., cameras are unavailable due to data privacy), yielding modality-incomplete data and leading to inconsistency between training and testing data. While straightforward incomplete input can boast training generalization-ability and lead to training failure, its potential risks to VLMs regarding safety and trustworthiness have been largely neglected. To this end, we make the first attempt to propose a unified incomplete video-language model to process the incomplete multi-modal inputs. Extensive experimental results show that our method can serve as a plug-and-play module for previous works to improve their performance in various multi-modal tasks.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation

hanzhuo tan
Xiaolong Tian
Hanrui Qi
Jiaming Liu
Siyi Wang
GAO Zuchen
Qi Luo
Jing Li

Recent advances in LLM-based decompilers have been shown effective to convert low-level binaries into human-readable source code. However, there still lacks a comprehensive benchmark that provides large-scale binary-source function pairs, which is critical for advancing the LLM decompilation technology. Creating accurate binary-source mappings incurs severe issues caused by complex compilation settings and widespread function inlining that obscure the correspondence between binaries and their original source code. Previous efforts have either relied on used contest‐style benchmarks, synthetic binary–source mappings that diverge significantly from the mappings in real world, or partially matched binaries with only code lines or variable names, compromising the effectiveness of analyzing the binary functionality. To alleviate these issues, we introduce Decompile-Bench, the first open-source dataset comprising two million binary-source function pairs condensed from 100 million collected function pairs, i. e. , 450GB of binaries compiled from permissively licensed GitHub projects. For the evaluation purposes, we also developed a benchmark Decompile-Bench-Eval including manually crafted binaries from the well-established HumanEval and MBPP, alongside the compiled GitHub repositories released after 2025 to mitigate data leakage issues. We further explore commonly-used evaluation metrics to provide a thorough assessment of the studied LLM decompilers and find that fine-tuning with Decompile-Bench causes a 20% improvement over previous benchmarks in terms of the re-executability rate. Our code and data has been released in HuggingFace and Github. https: //github. com/anonepo/LLM4Decompile

PDF Details

IJCAI Conference 2024 Conference Paper

A Survey on Rank Aggregation

Siyi Wang
Qi Deng
Shiwei Feng
Hong Zhang
Chao Liang

Rank aggregation (RA), the technique of combining multiple basic rankings into a consensus one, plays an important role in social choices, bioinformatics, information retrieval, metasearch, and recommendation systems. Although recent years have witnessed remarkable progress in RA, the absence of a systematic overview motivates us to conduct a comprehensive survey including both classic algorithms and the latest advances in RA study. Specifically, we first discuss the challenges of RA research, then present a systematic review with a fine-grained taxonomy to introduce representative algorithms in unsupervised RA, supervised RA, as well as the previously overlooked semi-supervised RA. Within each category, we not only summarize the common ideas of similar methods, but also discuss their strengths and weaknesses. Particularly, to investigate the performance difference of different types of RA methods, we conduct the largest scale of comparative evaluation to date of 27 RA methods on 7 public datasets from person re-identification, recommendation systems, bioinformatics and social choices. Finally, we raise two open questions in the current RA research and make our comments about future trends in the context of the latest research progress.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators

Yiyan Huang
Cheuk H. Leung
Siyi Wang
Yijun Li
Qi Wu

The growing demand for personalized decision-making has led to a surge of interest in estimating the Conditional Average Treatment Effect (CATE). Various types of CATE estimators have been developed with advancements in machine learning and causal inference. However, selecting the desirable CATE estimator through a conventional model validation procedure remains impractical due to the absence of counterfactual outcomes in observational data. Existing approaches for CATE estimator selection, such as plug-in and pseudo-outcome metrics, face two challenges. First, they must determine the metric form and the underlying machine learning models for fitting nuisance parameters (e. g. , outcome function, propensity function, and plug-in learner). Second, they lack a specific focus on selecting a robust CATE estimator. To address these challenges, this paper introduces a Distributionally Robust Metric (DRM) for CATE estimator selection. The proposed DRM is nuisance-free, eliminating the need to fit models for nuisance parameters, and it effectively prioritizes the selection of a distributionally robust CATE estimator. The experimental results validate the effectiveness of the DRM method in selecting CATE estimators that are robust to the distribution shift incurred by covariate shift and hidden confounders.

PDF Details DOI