Jiaqi Chen

Jiaqi Chen, Xiaoye Zhu, Tianyang Liu et al.

Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Although past methods have achieved good performance on detecting pure machine-generated text, those detectors have poor performance on distinguishing machine-revised text (rewriting, expansion, and polishing), which can have only minor changes from its original human prompt. As the content of text may originate from human prompts, detecting machine-revised text often involves identifying distinctive machine styles, e.g., worded favored by LLMs. However, existing methods struggle to detect machine-style phrasing hidden within the content contributed by humans. We propose the "Imitate Before Detect" (ImBD) approach, which first imitates the machine-style token distribution, and then compares the distribution of the text to be tested with the machine-style distribution to determine whether the text has been machine-revised. To this end, we introduce style preference optimization (SPO), which aligns a scoring LLM model to the preference of text styles generated by machines. The aligned scoring model is then used to calculate the style-conditional probability curvature (Style-CPC), quantifying the log probability difference between the original and conditionally sampled texts for effective detection. We conduct extensive comparisons across various scenarios, encompassing text revisions by six LLMs, four distinct text domains, and three machine revision types. Compared to existing state-of-the-art methods, our method yields a 13% increase in AUC for detecting text revised by open-source LLMs, and improves performance by 5% and 19% for detecting GPT-3.5 and GPT-4o revised text, respectively. Notably, our method surpasses the commercially trained GPT-Zero with just $1,000$ samples and five minutes of SPO, demonstrating its efficiency and effectiveness.

Zhongqi Yang, Wenhang Ge, Yuqi Li et al.

Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often suffer from a limited scope in the generated scenes. In this work, we propose Matrix-3D, a framework that utilize panoramic representation for wide-coverage omnidirectional explorable 3D world generation that combines conditional video generation and panoramic 3D reconstruction. We first train a trajectory-guided panoramic video diffusion model that employs scene mesh renders as condition, to enable high-quality and geometrically consistent scene video generation. To lift the panorama scene video to 3D world, we propose two separate methods: (1) a feed-forward large panorama reconstruction model for rapid 3D scene reconstruction and (2) an optimization-based pipeline for accurate and detailed 3D scene reconstruction. To facilitate effective training, we also introduce the Matrix-Pano dataset, the first large-scale synthetic collection comprising 116K high-quality static panoramic video sequences with depth and trajectory annotations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance in panoramic video generation and 3D world generation. See more in https://matrix-3d.github.io.

Hui Han, Siyuan Li, Jiaqi Chen et al.

Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories: traditional benchmarks, which use metrics and embeddings to evaluate generated video quality across multiple dimensions but often lack alignment with human judgments; and large language model (LLM)-based benchmarks, though capable of human-like reasoning, are constrained by a limited understanding of video quality metrics and cross-modal consistency. To address these challenges and establish a benchmark that better aligns with human preferences, this paper introduces Video-Bench, a comprehensive benchmark featuring a rich prompt suite and extensive evaluation dimensions. This benchmark represents the first attempt to systematically leverage MLLMs across all dimensions relevant to video generation assessment in generative models. By incorporating few-shot scoring and chain-of-query techniques, Video-Bench provides a structured, scalable approach to generated video evaluation. Experiments on advanced models including Sora demonstrate that Video-Bench achieves superior alignment with human preferences across all dimensions. Moreover, in instances where our framework's assessments diverge from human evaluations, it consistently offers more objective and accurate insights, suggesting an even greater potential advantage over traditional human judgment.

Jingheng Ye, Shen Wang, Jiaqi Chen et al.

Large Language Models (LLMs) have transformed artificial intelligence, offering profound opportunities for educational applications. However, their ability to provide fine-grained educational feedback for K-12 English writing remains underexplored. In this paper, we challenge the error analysis and pedagogical skills of LLMs by introducing the problem of Fine-grained Error Analysis for English Learners and present the Fine-grained Error ANalysis for English Learners (FEANEL) Benchmark. The benchmark comprises 1,000 essays written by elementary and secondary school students, and a well-developed English writing error taxonomy. Each error is annotated by language education experts and categorized by type, severity, and explanatory feedback, using a part-of-speech-based taxonomy they co-developed. We evaluate state-of-the-art LLMs on the FEANEL Benchmark to explore their error analysis and pedagogical abilities. Experimental results reveal significant gaps in current LLMs' ability to perform fine-grained error analysis, highlighting the need for advancements in particular methods for educational applications.

Jiaqi Chen, Xiaoye Zhu, Yue Wang et al.

We propose a symbolic generative task description language and a corresponding inference engine capable of representing arbitrary multimodal tasks as structured symbolic flows. Unlike conventional generative models that rely on large-scale training and implicit neural representations to learn cross-modal mappings, often at high computational cost and with limited flexibility, our framework introduces an explicit symbolic representation comprising three core primitives: functions, parameters, and topological logic. Leveraging a pre-trained language model, our inference engine maps natural language instructions directly to symbolic workflows in a training-free manner. Our framework successfully performs over 12 diverse multimodal generative tasks, demonstrating strong performance and flexibility without the need for task-specific tuning. Experiments show that our method not only matches or outperforms existing state-of-the-art unified models in content quality, but also offers greater efficiency, editability, and interruptibility. We believe that symbolic task representations provide a cost-effective and extensible foundation for advancing the capabilities of generative AI.

Yibo Wang, Kai Li, Yuzhe Tang et al.

This paper presents iBatch, a middleware system running on top of an operational Ethereum network to enable secure batching of smart-contract invocations against an untrusted relay server off-chain. iBatch does so at a low overhead by validating the server's batched invocations in smart contracts without additional states. The iBatch mechanism supports a variety of policies, ranging from conservative to aggressive batching, and can be configured adaptively to the current workloads. iBatch automatically rewrites smart contracts to integrate with legacy applications and support large-scale deployment. For cost evaluation, we develop a platform with fast and cost-accurate transaction replaying, build real transaction benchmarks on popular Ethereum applications, and build a functional prototype of iBatch on Ethereum. The evaluation results show that iBatch saves 14.6%-59.1% Gas cost per invocation with a moderate 2-minute delay and 19.06%-31.52% Ether cost per invocation with a delay of 0.26-1.66 blocks.

Kai Li, Yuzhe Tang, Jiaqi Chen et al.

Feeding external data to a blockchain, a.k.a. data feed, is an essential task to enable blockchain interoperability and support emerging cross-domain applications, notably stablecoins. Given the data-intensive feeds in real life (e.g., high-frequency price updates) and the high cost in using blockchain, namely Gas, it is imperative to reduce the Gas cost of data feeds. Motivated by the constant-changing workloads in finance and other applications, this work focuses on designing a dynamic, workload-aware approach for cost effectiveness in Gas. This design space is understudied in the existing blockchain research which has so far focused on static data placement. This work presents GRuB, a cost-effective data feed that dynamically replicates data between the blockchain and an off-chain cloud storage. GRuB's data replication is workload-adaptive by monitoring the current workload and making online decisions w.r.t. data replication. A series of online algorithms are proposed that achieve the bounded worst-case cost in blockchain's Gas. GRuB runs the decision-making components on the untrusted cloud off-chain for lower Gas costs, and employs a security protocol to authenticate the data transferred between the blockchain and cloud. The overall GRuB system can autonomously achieve low Gas costs with changing workloads. We built a GRuB prototype functional with Ethereum and Google LevelDB, and supported real applications in stablecoins. Under real workloads collected from the Ethereum contract-call history and mixed workloads of YCSB, we systematically evaluate GRuB's cost which shows a saving of Gas by 10% ~ 74%, with comparison to the baselines of static data-placement.