arXiv subjects

Zhihan Zhang

Publications and source records attributed to Zhihan Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Efficient self-consistent learning of gate set Pauli noise

Understanding quantum noise is an essential step towards building practical quantum information processing systems. Pauli noise is a useful model that has been widely applied in quantum benchmarking, error mitigation, and error correction. Despite intensive study, most existing works focus on learning Pauli noise channels associated with some specific gates rather than treating the gate set as a whole. A learning algorithm that is self-consistent, complete, and efficient at the same time is yet to be established. In this work, we study the task of gate set Pauli noise learning, where a set of quantum gates, state preparation, and measurements all suffer from unknown Pauli noise channels with a customized noise ansatz. Using tools from algebraic graph theory, we analytically characterize the self-consistently learnable degrees of freedom for Pauli noise models with arbitrary linear ansatz, and design experiments to efficiently learn all the learnable information. Specifically, we show that all learnable information about the gate noise can be learned to relative precision, under mild assumptions on the noise ansatz. We then demonstrate the flexibility of our theory by applying it to concrete physically motivated ansatzs (such as spatially local or quasi-local noise) and experimentally relevant gate sets (such as parallel CZ gates). These results not only enhance the theoretical understanding of quantum noise learning, but also provide a feasible recipe for characterizing existing and near-future quantum information processing devices.

quant-ph↗

arXiv2025

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability

Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capability. Specifically, we adopt a set of interleaved Spatio-Temporal Aware Queries to capture temporal perception and dynamic spatial information. Moreover, we propose a Query-Guided Space Decoder to establish a corresponding connection between the queries and spatial coordinates. Additionally, due to the lack of spatio-temporal datasets, we construct the Unified Spatio-Temporal Grounding (Uni-STG) dataset, comprising 480K instances across three tasks. This dataset fully exploits the potential of MLLM to simultaneously facilitate localization in both temporal and spatial dimensions. Extensive experiments demonstrate that SpaceVLLM achieves the state-of-the-art performance across 11 benchmarks covering temporal, spatial, spatio-temporal and video understanding tasks, highlighting the effectiveness of our approach. Our code, datasets and model will be released at https://github.com/Jayce1kk/SpaceVLLM.

cs.CV↗

arXiv2025

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

cs.SE↗

arXiv2025

IHEval: Evaluating Language Models on Following the Instruction Hierarchy

The instruction hierarchy, which establishes a priority order from system messages to user messages, conversation history, and tool outputs, is essential for ensuring consistent and safe behavior in language models (LMs). Despite its importance, this topic receives limited attention, and there is a lack of comprehensive benchmarks for evaluating models' ability to follow the instruction hierarchy. We bridge this gap by introducing IHEval, a novel benchmark comprising 3,538 examples across nine tasks, covering cases where instructions in different priorities either align or conflict. Our evaluation of popular LMs highlights their struggle to recognize instruction priorities. All evaluated models experience a sharp performance decline when facing conflicting instructions, compared to their original instruction-following performance. Moreover, the most competitive open-source model only achieves 48% accuracy in resolving such conflicts. Our results underscore the need for targeted optimization in the future development of LMs.

cs.CL↗

arXiv2025

Incorporating Sustainability in Electronics Design: Obstacles and Opportunities

Life cycle assessment (LCA) is a methodology for holistically measuring the environmental impact of a product from initial manufacturing to end-of-life disposal. However, the extent to which LCA informs the design of computing devices remains unclear. To understand how this information is collected and applied, we interviewed 17 industry professionals with experience in LCA or electronics design, systematically coded the interviews, and investigated common themes. These themes highlight the challenge of LCA data collection and reveal distributed decision-making processes where responsibility for sustainable design choices, and their associated costs, is often ambiguous. Our analysis identifies opportunities for HCI technologies to support LCA computation and its integration into the design process to facilitate sustainability-oriented decision-making. While this work provides a nuanced discussion about sustainable design in the information and communication technologies (ICT) hardware industry, we hope our insights will also be valuable to other sectors.

cs.HC↗

arXiv2025

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with code repositories. However, existing methods often overlook the need for repository-level code understanding, which is crucial for accurately grasping the broader context and developing effective solutions. On this basis, we present RepoGraph, a plug-in module that manages a repository-level structure for modern AI software engineering solutions. RepoGraph offers the desired guidance and serves as a repository-wide navigation for AI software engineers. We evaluate RepoGraph on the SWE-bench by plugging it into four different methods of two lines of approaches, where RepoGraph substantially boosts the performance of all systems, leading to a new state-of-the-art among open-source frameworks. Our analyses also demonstrate the extensibility and flexibility of RepoGraph by testing on another repo-level coding benchmark, CrossCodeEval. Our code is available at https://github.com/ozyyshr/RepoGraph.

cs.SE↗

arXiv2025

Remote Sensing Semantic Segmentation Quality Assessment based on Vision Language Model

The complexity of scenes and variations in image quality result in significant variability in the performance of semantic segmentation methods of remote sensing imagery (RSI) in supervised real-world scenarios. This makes the evaluation of semantic segmentation quality in such scenarios an issue to be resolved. However, most of the existing evaluation metrics are developed based on expert-labeled object-level annotations, which are not applicable in such scenarios. To address this issue, we propose RS-SQA, an unsupervised quality assessment model for RSI semantic segmentation based on vision language model (VLM). This framework leverages a pre-trained RS VLM for semantic understanding and utilizes intermediate features from segmentation methods to extract implicit information about segmentation quality. Specifically, we introduce CLIP-RS, a large-scale pre-trained VLM trained with purified text to reduce textual noise and capture robust semantic information in the RS domain. Feature visualizations confirm that CLIP-RS can effectively differentiate between various levels of segmentation quality. Semantic features and low-level segmentation features are effectively integrated through a semantic-guided approach to enhance evaluation accuracy. To further support the development of RS semantic segmentation quality assessment, we present RS-SQED, a dedicated dataset sampled from four major RS semantic segmentation datasets and annotated with segmentation accuracy derived from the inference results of 8 representative segmentation methods. Experimental results on the established dataset demonstrate that RS-SQA significantly outperforms state-of-the-art quality assessment models. This provides essential support for predicting segmentation accuracy and high-quality semantic segmentation interpretation, offering substantial practical value.

eess.IV↗

arXiv2025

MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems

Multimodal Large Language Models (MLLMs) have demonstrated impressive abilities across various tasks, including visual question answering and chart comprehension, yet existing benchmarks for chart-related tasks fall short in capturing the complexity of real-world multi-chart scenarios. Current benchmarks primarily focus on single-chart tasks, neglecting the multi-hop reasoning required to extract and integrate information from multiple charts, which is essential in practical applications. To fill this gap, we introduce MultiChartQA, a benchmark that evaluates MLLMs' capabilities in four key areas: direct question answering, parallel question answering, comparative reasoning, and sequential reasoning. Our evaluation of a wide range of MLLMs reveals significant performance gaps compared to humans. These results highlight the challenges in multi-chart comprehension and the potential of MultiChartQA to drive advancements in this field. Our code and data are available at https://github.com/Zivenzhu/Multi-chart-QA

cs.CL↗

arXiv2024

Adaptivity can help exponentially for shadow tomography

In recent years there has been significant interest in understanding the statistical complexity of learning from quantum data under the constraint that one can only make unentangled measurements. While a key challenge in establishing tight lower bounds in this setting is to deal with the fact that the measurements can be chosen in an adaptive fashion, a recurring theme has been that adaptivity offers little advantage over more straightforward, nonadaptive protocols. In this note, we offer a counterpoint to this. We show that for the basic task of shadow tomography, protocols that use adaptively chosen two-copy measurements can be exponentially more sample-efficient than any protocol that uses nonadaptive two-copy measurements.

quant-ph↗

arXiv2024

Stabilizer bootstrapping: A recipe for efficient agnostic tomography and magic estimation

We study the task of agnostic tomography: given copies of an unknown $n$-qubit state $ρ$ which has fidelity $τ$ with some state in a given class $C$, find a state which has fidelity $\ge τ- ε$ with $ρ$. We give a new framework, stabilizer bootstrapping, for designing computationally efficient protocols for this task, and use this to get new agnostic tomography protocols for the following classes: Stabilizer states: We give a protocol that runs in time $\mathrm{poly}(n,1/ε)\cdot (1/τ)^{O(\log(1/τ))}$, answering an open question posed by Grewal, Iyer, Kretschmer, Liang [43] and Anshu and Arunachalam [6]. Previous protocols ran in time $\mathrm{exp}(Θ(n))$ or required $τ>\cos^2(π/8)$. States with stabilizer dimension $n - t$: We give a protocol that runs in time $n^3\cdot(2^t/τ)^{O(\log(1/ε))}$, extending recent work on learning quantum states prepared by circuits with few non-Clifford gates, which only applied in the realizable setting where $τ= 1$ [33, 40, 49, 66]. Discrete product states: If $C = K^{\otimes n}$ for some $μ$-separated discrete set $K$ of single-qubit states, we give a protocol that runs in time $(n/μ)^{O((1 + \log (1/τ))/μ)}/ε^2$. This strictly generalizes a prior guarantee which applied to stabilizer product states [42]. For stabilizer product states, we give a further improved protocol that runs in time $(n^2/ε^2)\cdot (1/τ)^{O(\log(1/τ))}$. As a corollary, we give the first protocol for estimating stabilizer fidelity, a standard measure of magic for quantum states, to error $ε$ in $n^3 \mathrm{quasipoly}(1/ε)$ time.

quant-ph↗

arXiv2024

On the sample complexity of purity and inner product estimation

We study the sample complexity of the prototypical tasks quantum purity estimation and quantum inner product estimation. In purity estimation, we are to estimate $tr(ρ^2)$ of an unknown quantum state $ρ$ to additive error $ε$. Meanwhile, for quantum inner product estimation, Alice and Bob are to estimate $tr(ρσ)$ to additive error $ε$ given copies of unknown quantum state $ρ$ and $σ$ using classical communication and restricted quantum communication. In this paper, we show a strong connection between the sample complexity of purity estimation with bounded quantum memory and inner product estimation with bounded quantum communication and unentangled measurements. We propose a protocol that solves quantum inner product estimation with $k$-qubit one-way quantum communication and unentangled local measurements using $O(median\{1/ε^2,2^{n/2}/ε,2^{n-k}/ε^2\})$ copies of $ρ$ and $σ$. Our protocol can be modified to estimate the purity of an unknown quantum state $ρ$ using $k$-qubit quantum memory with the same complexity. We prove that arbitrary protocols with $k$-qubit quantum memory that estimate purity to error $ε$ require $Ω(median\{1/ε^2,2^{n/2}/\sqrtε,2^{n-k}/ε^2\})$ copies of $ρ$. This indicates the same lower bound for quantum inner product estimation with one-way $k$-qubit quantum communication and classical communication, and unentangled local measurements. For purity estimation, we further improve the lower bound to $Ω(\max\{1/ε^2,2^{n/2}/ε\})$ for any protocols using an identical single-copy projection-valued measurement. Additionally, we investigate a decisional variant of quantum distributed inner product estimation without quantum communication for mixed state and provide a lower bound on the sample complexity.

quant-ph↗

arXiv2024

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems. However, this repeated independent process often leads to the same mistakes, making the selected solution still incorrect. We propose a novel prompting method named Stepwise Correction (StepCo) that helps LLMs identify and revise incorrect steps in their generated reasoning paths. It iterates verification and revision phases that employ a process-supervised verifier. The verify-then-revise process not only improves answer correctness but also reduces token consumption with fewer paths needed to generate. With StepCo, a series of LLMs demonstrate exceptional performance. Notably, using GPT-4o as the backend LLM, StepCo achieves an average accuracy of 94.1 across eight datasets, significantly outperforming the state-of-the-art Best-of-N method by +2.4, while reducing token consumption by 77.8%.

cs.CL↗

arXiv2024

TOWER: Tree Organized Weighting for Evaluating Complex Instructions

Evaluating the ability of large language models (LLMs) to follow complex human-written instructions is essential for their deployment in real-world applications. While benchmarks like Chatbot Arena use human judges to assess model performance, they are resource-intensive and time-consuming. Alternative methods using LLMs as judges, such as AlpacaEval, MT Bench, WildBench, and InFoBench offer improvements but still do not capture that certain complex instruction aspects are more important than others to follow. To address this gap, we propose a novel evaluation metric, \textsc{TOWER}, that incorporates human-judged importance into the assessment of complex instruction following. We show that human annotators agree with tree-based representations of these complex instructions nearly as much as they agree with other human annotators. We release tree-based annotations of the InFoBench dataset and the corresponding evaluation code to facilitate future research.

cs.CL↗

arXiv2024

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning

Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. To maximize such benefits, existing research focuses on broadening the training set with various data augmentation techniques, which is effective for standard single-round question-answering settings. Our work introduces a novel technique aimed at cultivating a deeper understanding of the training problems at hand, enhancing performance not only in standard settings but also in more complex scenarios that require reflective thinking. Specifically, we propose reflective augmentation, a method that embeds problem reflection into each training instance. It trains the model to consider alternative perspectives and engage with abstractions and analogies, thereby fostering a thorough comprehension through reflective reasoning. Extensive experiments validate the achievement of our aim, underscoring the unique advantages of our method and its complementary nature relative to existing augmentation techniques.

cs.CL↗

arXiv2024

A generalized cycle benchmarking algorithm for characterizing mid-circuit measurements

Mid-circuit measurements (MCMs) are crucial ingredients in the development of fault-tolerant quantum computation. While there have been rapid experimental progresses in realizing MCMs, a systematic method for characterizing noisy MCMs is still under exploration. In this work we develop a cycle benchmarking (CB)-type algorithm to characterize noisy MCMs. The key idea is to use a joint Fourier transform on the classical and quantum registers and then estimate parameters in the Fourier space, analogous to Pauli fidelities used in CB-type algorithms for characterizing the Pauli noise channel of Clifford gates. Furthermore, we develop a theory of the noise learnability of MCMs, which determines what information can be learned about the noise model (in the presence of state preparation and terminating measurement (SPAM) noise) and what cannot, which shows that all learnable information can be learned using our algorithm. As an application, we show how to use the learned information to test the independence between measurement noise and state preparation noise in an MCM. Finally, we conduct numerical simulations to illustrate the practical applicability of the algorithm. Similar to other CB-type algorithms, we expect the algorithm to provide a useful toolkit that is of experimental interest.

quant-ph↗

arXiv2024

Large Language Models Can Self-Correct with Key Condition Verification

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback. Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet. We find that a simple yet effective verification method can unleash inherent capabilities of the LLMs. That is to mask a key condition in the question, add the current response to construct a verification question, and predict the condition to verify the response. The condition can be an entity in an open-domain question or a numeric value in a math question, which requires minimal effort (via prompting) to identify. We propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named ProCo. We conduct experiments on three reasoning tasks. On average, ProCo, with GPT-3.5-Turbo as the backend LLM, yields $+6.8$ exact match on four open-domain question answering datasets, $+14.1$ accuracy on three arithmetic reasoning datasets, and $+9.6$ accuracy on a commonsense reasoning dataset, compared to Self-Correct. Our implementation is made publicly available at https://wzy6642.github.io/proco.github.io/.

cs.CL↗

arXiv2024

Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples

Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy construction highly desirable. In this work, we introduce Chain-of-Layer which is an in-context learning framework designed to induct taxonomies from a given set of entities. Chain-of-Layer breaks down the task into selecting relevant candidate entities in each layer and gradually building the taxonomy from top to bottom. To minimize errors, we introduce the Ensemble-based Ranking Filter to reduce the hallucinated content generated at each iteration. Through extensive experiments, we demonstrate that Chain-of-Layer achieves state-of-the-art performance on four real-world benchmarks.

cs.CL↗

arXiv2024

Hallucination Mitigation Prompts Long-term Video Understanding

Recently, multimodal large language models have made significant advancements in video understanding tasks. However, their ability to understand unprocessed long videos is very limited, primarily due to the difficulty in supporting the enormous memory overhead. Although existing methods achieve a balance between memory and information by aggregating frames, they inevitably introduce the severe hallucination issue. To address this issue, this paper constructs a comprehensive hallucination mitigation pipeline based on existing MLLMs. Specifically, we use the CLIP Score to guide the frame sampling process with questions, selecting key frames relevant to the question. Then, We inject question information into the queries of the image Q-former to obtain more important visual features. Finally, during the answer generation stage, we utilize chain-of-thought and in-context learning techniques to explicitly control the generation of answers. It is worth mentioning that for the breakpoint mode, we found that image understanding models achieved better results than video understanding models. Therefore, we aggregated the answers from both types of models using a comparison mechanism. Ultimately, We achieved 84.2\% and 62.9\% for the global and breakpoint modes respectively on the MovieChat dataset, surpassing the official baseline model by 29.1\% and 24.1\%. Moreover the proposed method won the third place in the CVPR LOVEU 2024 Long-Term Video Question Answering Challenge. The code is avaiable at https://github.com/lntzm/CVPR24Track-LongVideo

cs.CV↗