Author name cluster

Zhao Jin

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.

9 papers

2 author rows

AAAI Conference 2026 Conference Paper

AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization

Jingyi Liao
Yongyi Su
Rong-Cheng Tu
Zhao Jin
Wenhao Sun
Yiting Li
Xun Xu
Dacheng Tao

While Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse domains, their application to specialized anomaly detection (AD) remains constrained by domain adaptation challenges. Existing Group Relative Policy Optimization (GRPO) based approaches suffer from two critical limitations: inadequate training data utilization when models produce uniform responses, and insufficient supervision over reasoning processes that encourage immediate binary decisions without deliberative analysis. We propose a comprehensive framework addressing these limitations through two synergistic innovations. First, we introduce a multi-stage deliberative reasoning process that guides models from region identification to focused examination, generating diverse response patterns essential for GRPO optimization while enabling structured supervision over analytical workflows. Second, we develop a fine-grained reward mechanism incorporating classification accuracy and localization supervision, transforming binary feedback into continuous signals that distinguish genuine analytical insight from spurious correctness. Comprehensive evaluation across multiple industrial datasets shows that our method achieves superior accuracy by enabling general-purpose MLLMs to acquire fine-grained visual discrimination for detecting subtle manufacturing defects.

PDF Details DOI

AAAI Conference 2026 Conference Paper

MCTS-SQL: Light-Weight LLMs Can Master the Text-to-SQL Through Monte Carlo Tree Search

Shuozhi Yuan
Liming Chen
Miaomiao Yuan
Zhao Jin

Text-to-SQL is a fundamental yet challenging task in the NLP area, aiming at translating natural language questions into SQL queries. While recent advances in large language models have greatly improved performance, most existing approaches depend on models with tens of billions of parameters or costly APIs, limiting their applicability in resource-constrained environments. For real world, especially on edge devices, it is crucial for Text-to-SQL to ensure cost-effectiveness. Therefore, enabling the light-weight models for Text-to-SQL is of great practical significance. However, smaller LLMs often struggle with complicated user instruction, redundant schema linking or syntax correctness. To address these challenges, we propose MCTS-SQL, a novel framework that uses Monte Carlo Tree Search to guide SQL generation through multi-step refinement. Since the light-weight models' weak performance of single-shot prediction, we generate better results through several trials with feedback. However, directly applying MCTS-based methods inevitably leads to significant time and computational overhead. Driven by this issue, we propose a token-level prefix-cache mechanism that stores prior information during iterations, effectively improved the execution speed. Experiments results on the SPIDER and BIRD benchmarks demonstrate the effectiveness of our approach. Using a small open-source Qwen2.5-Coder-1.5B, our method outperforms ChatGPT-3.5. When leveraging a more powerful model Gemini 2.5 to explore the performance upper bound, we achieved results competitive with the SOTA. Our findings demonstrate that even small models can be effectively deployed in practical Text-to-SQL systems with the right strategy.

PDF Details DOI

ICML Conference 2025 Conference Paper

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

Wenhao Sun
Rong-Cheng Tu
Jingyi Liao
Zhao Jin
Dacheng Tao

Diffusion Transformers (DiTs) have proven effective in generating high-quality videos but are hindered by high computational costs. Existing video diffusion sampling acceleration methods often rely on costly fine-tuning or exhibit limited generalization capabilities. We propose Asymmetric Reduction and Restoration ( AsymRnR ), a training-free and model-agnostic method to accelerate video DiTs. It builds on the observation that redundancies of feature tokens in DiTs vary significantly across different model blocks, denoising steps, and feature types. Our AsymRnR asymmetrically reduces redundant tokens in the attention operation, achieving acceleration with negligible degradation in output quality and, in some cases, even improving it. We also tailored a reduction schedule to distribute the reduction across components adaptively. To further accelerate this process, we introduce a matching cache for more efficient reduction. Backed by theoretical foundations and extensive experimental validation, AsymRnR integrates into state-of-the-art video DiTs and offers substantial speedup.

Details

TCS Journal 2025 Journal Article

Expressive completeness of separation logic in block-based cloud storage systems

Tianyue Cao
Zhao Jin
Bowen Zhang
Yongzhi Cao
Hanpin Wang

Block-based cloud storage systems are widely used to store big data. Although they are highly fault-tolerant, the occurrence of bugs is still inevitable. Separation logic was proposed for mutable data structures, and can be used to verify block-based cloud storage systems. Hoare-style proof system has been constructed to verify these systems, and has been implemented in Coq. However, expressiveness of the assertion language in this formal system has not been fully studied. To fill this gap, we show the expressive completeness of separation logic in block-based cloud storage system, and prove the following three main consequences: (1) this logic is strictly more expressive than first-order logic, (2) this logic is as expressive as separation logic, and (3) this logic is as expressive as weak second-order logic with sequences.

Details DOI

NeurIPS Conference 2025 Conference Paper

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Zhao Jin
Rong-Cheng Tu
Jingyi Liao
Wenhao Sun
Xiao Luo
Shunyu Liu
Dacheng Tao

3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER — a VLM-driven agent that combines both modalities in a progressive reasoning framework. It first holistically analyzes the scene and produces a 3D rendering from the optimal viewpoint. Based on this, anchor-guided candidate screening is conducted to perform a coarse-level localization of potential objects. Furthermore, leveraging retrieved relevant 2D camera images, 3D-2D joint decision-making is efficiently performed to determine the best-matching object. By bridging spatial and semantic reasoning neural streams, SPAZER achieves robust zero-shot grounding without training on 3D-labeled data. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate that SPAZER significantly outperforms previous state-of-the-art zero-shot methods, achieving notable gains of $\mathbf{9. 0\}$% and $\mathbf{10. 9\}$% in accuracy.

PDF Details

NeurIPS Conference 2025 Conference Paper

VORTA: Efficient Video Diffusion via Routing Sparse Attention

Wenhao Sun
Rong-Cheng Tu
Yifu Ding
Jingyi Liao
Zhao Jin
Shunyu Liu
Dacheng Tao

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration methods enhance the efficiency by exploiting the local sparsity of attention scores; yet they often struggle with accelerating the long-range computation. To address this problem, we propose VORTA, an acceleration framework with two novel components: 1) a sparse attention mechanism that efficiently captures long-range dependencies, and 2) a routing strategy that adaptively replaces full 3D attention with specialized sparse attention variants. VORTA achieves an end-to-end speedup $1. 76\times$ without loss of quality on VBench. Furthermore, it can seamlessly integrate with various other acceleration methods, such as model caching and step distillation, reaching up to speedup $14. 41\times$ with negligible performance degradation. VORTA demonstrates its efficiency and enhances the practicality of video diffusion transformers in real-world settings. Codes and weights are available at https: //github. com/wenhao728/VORTA.

PDF Details

ICRA Conference 2024 Conference Paper

SM 3: Self-supervised Multi-task Modeling with Multi-view 2D Images for Articulated Objects

Haowen Wang 0001
Zhen Zhao
Zhao Jin
Zhengping Che
Liang Qiao
Yakun Huang
Zhipeng Fan
Xiuquan Qiao

Reconstructing real-world objects and estimating their movable joint structures are pivotal technologies within the field of robotics. Previous research has predominantly focused on supervised approaches, relying on annotated datasets to model articulated objects within limited categories. However, these approaches fall short of effectively addressing the diversity present in the real world. To tackle this issue, we propose a self-supervised interaction perception method, referred to as SM 3, which leverages multi-view RGB images captured before and after interaction to model articulated objects, identify the movable parts, and infer the parameters of their rotating joints. By constructing 3D geometries and textures from the captured 2D images, SM 3 achieves integrated optimization of movable part and joint parameters during the reconstruction process, obviating the need for annotations. Furthermore, we introduce the MMArt dataset, an extension of PartNet-Mobility, encompassing multi-view and multi-modal data of articulated objects spanning diverse categories. Evaluations demonstrate that SM 3 surpasses existing benchmarks across various categories and objects, and its adaptability in real-world scenarios has been thoroughly validated.

Details

TCS Journal 2022 Journal Article

An adaptation-complete proof system for local reasoning about cloud storage systems

Zhao Jin
Bowen Zhang
Lei Zhang
Yongzhi Cao
Hanpin Wang

The rapid growth of data presents a significant challenge to the capability of traditional storage technologies to collect and manage data. Cloud storage systems (CSSs) have been proposed as a method to improve storage capacity. To safely and effectively manage cloud storage data and improve data service quality, it is necessary to verify the correctness of CSS management programs. However, the complexity of these systems renders program verification difficult. In this paper, we propose a Hoare-style proof system, in conjunction with two languages, to analyze and verify CSS management programs. The first is a modeling language that describes the program execution. The second is an assertion language based on Separation Logic (SL), used to describe the properties of the CSS file-block-location storage structure. The proof system supports modular local reasoning for CSS programs by a set of adaptation rules, which enable the condition of specifications to be applied to broader contexts. A key question that arises is whether the proof system can meet adaptation completeness. If so, arbitrary satisfiable specifications can be adjusted using the adaptation rules. To this end, we developed local predicate transformers and used their domain to interpret all types of commands. By finding the smallest local predicate transformer, we established adaptation completeness. In summary, this work provides a formalization of automatic modular reasoning patterns and lays a theoretical foundation for the compositional program verification of CSSs.

Details DOI

TCS Journal 2022 Journal Article

Reasoning about block-based cloud storage systems via separation logic

Zhao Jin
Bowen Zhang
Tianyue Cao
Yongzhi Cao
Hanpin Wang

Owing to the massive growth in the storage demands of big data, cloud storage systems emerge at a historic moment, among which block-based cloud storage systems (BCSSs) are typical. Compared with traditional storage systems, BCSSs have many advantages, such as higher capacity, lower cost, and better scalability. BCSSs are also much more complex and error prone than traditional systems, and therefore, their reliability is a significant concern. Correctness is the most basic requirement for reliability. Therefore, it is of great significance to study BCSS program correctness verification to establish the theoretical basis for cloud storage systems. In this paper, we propose a novel framework based on separation logic (SL) to verify the correctness of BCSS management programs. We first construct a two-tier heap structure as the formal model of the storage architecture for BCSSs and present a modelling language based on this structure to describe the program execution. We then define assertion pairs to describe the properties of the two-tier structure. The two components of an assertion pair affect each other, producing several interesting properties. Finally, we propose a Hoare-style proof system to reason about BCSS programs and establish its soundness. We also demonstrate our proof system's uniqueness, usability, and scalability by verifying several real-world BCSS sample programs. In summary, this work presents a systematic approach that can be used to effectively solve BCSS program verification problems, and provides an SL-based logical modelling strategy, specifically to build its consistency with the actual behaviour of BCSSs.

Details DOI