arXiv subjects

Honghao Fu

Publications and source records attributed to Honghao Fu.

At least 19 recordsLinked to original sources

arXiv2026

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful videos paired with benign queries achieve higher attack success rates than the same videos paired with explicitly harmful queries. To understand the underlying mechanism of this vulnerability, we present V-DEAL, a three-level diagnostic framework that jointly analyzes this failure across model behaviour, understanding, and internal representations. By progressively ruling out perception failure and quantifying the model's internal refusal tendency, V-DEAL provides a new diagnostic perspective for analyzing the underlying mechanism of the observed vulnerability. We tested six Video LLMs on three public benchmarks and observed that models correctly recognize harmful video content with over 81\% accuracy, yet the average attack success rate still reaches 48.33\% under the condition pairing harmful videos with benign queries. Hidden-state analysis further shows that visual understanding activates a weaker refusal tendency than textual understanding. Furthermore, we introduce a prompt injection intervention method that reduces attack success rates by an average of 48.24 percentage points and achieves performance comparable to prior fine-tuning-based methods, providing an effective and practical means to address such safety risks in Video LLMs.

cs.AI↗

arXiv2026

ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol and exposes support surfaces for context access, catalog grounding, and state management. Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search retrieval, listwise ranking, or product bundling. This model-centric design reduces lossy hand-offs between agent orchestration and item-space execution. To build ShopX, we design semantically recoverable, LLM-operable SIDs and a training recipe that equips a general LLM for flexible multi-turn item-space fulfillment while retaining the knowledge and instruction-following abilities needed by a shopping agent. We evaluate the ShopX framework against tool-mediated agentic systems on single- and multi-turn fulfillment tasks derived from anonymized Taobao production logs, showing that model-native fulfillment improves overall framework behavior, especially on complex or ambiguous requests.

cs.IR↗

arXiv2026

The Rise of Quantum Computing -- Take a BITE for Built Environment and Urban Microclimate Research

Quantum computing is a new approach to computation that utilizes superposition, entanglement, interference, and tunneling to solve problems too complex for classical computers. This paper discusses the basic concepts and development of quantum computing, exploring its potential applications in the built environment and urban microclimate research. In buildings, quantum computing may help optimize energy management, control HVAC systems, and plan electric vehicle charging networks more efficiently. For urban microclimates, it could accelerate renewable energy planning and support multi-objective design, making it easier to balance urban building performance with climate conditions. Since current quantum hardware is still in the Noisy Intermediate-Scale Quantum (NISQ) stage, we propose the "BITE" principle to guide researchers in choosing suitable problems for quantum acceleration: B (Big search), I (Input-light), T (Tiny computation), and E (Evaluation polish). Although quantum computing still faces challenges such as noise and hardware limits, it offers great potential for developing more climate-resilient, sustainable, and energy-efficient cities of the future.

physics.pop-ph↗

arXiv2026

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG

Scaling multimodal large language models (MLLMs) to long videos is constrained by limited context windows. While retrieval-augmented generation (RAG) is a promising remedy by organizing query-relevant visual evidence into a compact context, most existing methods (i) flatten videos into independent segments, breaking their inherent spatio-temporal structure, and (ii) depend on explicit semantic matching, which can miss cues that are implicitly relevant to the query's intent. To overcome these limitations, we propose VideoStir, a structured and intent-aware long-video RAG framework. It firstly structures a video as a spatio-temporal graph at clip level, and then performs multi-hop retrieval to aggregate evidence across distant yet contextually related events. Furthermore, it introduces an MLLM-backed intent-relevance scorer that retrieves frames based on their alignment with the query's reasoning intent. To support this capability, we curate IR-600K, a large-scale dataset tailored for learning frame-query intent alignment. Experiments show that VideoStir is competitive with state-of-the-art baselines without relying on auxiliary information, highlighting the promise of shifting long-video RAG from flattened semantic matching to structured, intent-aware reasoning. Codes and checkpoints are available at https://github.com/RomGai/VideoStir.

cs.CV↗

arXiv2026

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

OmniLottie is a versatile framework that generates high quality vector animations from multi-modal instructions. For flexible motion and visual content control, we focus on Lottie, a light weight JSON formatting for both shapes and animation behaviors representation. However, the raw Lottie JSON files contain extensive invariant structural metadata and formatting tokens, posing significant challenges for learning vector animation generation. Therefore, we introduce a well designed Lottie tokenizer that transforms JSON files into structured sequences of commands and parameters representing shapes, animation functions and control parameters. Such tokenizer enables us to build OmniLottie upon pretrained vision language models to follow multi-modal interleaved instructions and generate high quality vector animations. To further advance research in vector animation generation, we curate MMLottie-2M, a large scale dataset of professionally designed vector animations paired with textual and visual annotations. With extensive experiments, we validate that OmniLottie can produce vivid and semantically aligned vector animations that adhere closely to multi modal human instructions.

cs.CV↗

arXiv2026

Quantum Position Verification with Remote Untrusted Devices

Position information underpins many modern technologies, from navigation and timing to authentication and critical infrastructure. However, classical methods of proving that information originates from a particular position are vulnerable to spoofing. This limitation can be overcome with quantum technologies but current protocols rely on trust in quantum hardware that can be undermined, or require quantum computers and bounds on adversarial computation. Nevertheless, there has been significant interest in experimental demonstrations, and aspects of these protocols have been implemented. Here we introduce and experimentally demonstrate the Bell-test quantum position verification protocol for device-independent quantum position verification that guarantees security with only observed correlations from a loophole-free Bell test across a quantum network. We experimentally implement a version of this device-independent protocol against adversaries who, before each trial, are weakly entangled. Our demonstration achieves a one-dimensional localization 2.47(2) times smaller than the best, necessarily non-remote, classical localization protocol. Compared to classical protocols with identical latencies, the localization volume is 4.53(5) times smaller, and represents a certifiable quantum advantage. The general Bell-test protocol is loss tolerant and secure against adversaries with significant quantum resources. This work allows digital security to be anchored to physically trusted locations, enabling new position-based authentication protocols for applications such as financial transactions, legal agreements, and securing critical infrastructure.

quant-ph↗

arXiv2025

ContextNav: Towards Agentic Multimodal In-Context Learning

Recent advances demonstrate that multimodal large language models (MLLMs) exhibit strong multimodal in-context learning (ICL) capabilities, enabling them to adapt to novel vision-language tasks from a few contextual examples. However, existing ICL approaches face challenges in reconciling scalability with robustness across diverse tasks and noisy contextual examples: manually selecting examples produces clean contexts but is labor-intensive and task-specific, while similarity-based retrieval improves scalability but could introduce irrelevant or structurally inconsistent samples that degrade ICL performance. To address these limitations, we propose ContextNav, the first agentic framework that integrates the scalability of automated retrieval with the quality and adaptiveness of human-like curation, enabling noise-robust and dynamically optimized contextualization for multimodal ICL. ContextNav unifies context management and noise-robust contextualization within a closed-loop workflow driven by graph-based orchestration. Specifically, it builds a resource-aware multimodal embedding pipeline, maintains a retrievable vector database, and applies agentic retrieval and structural alignment to construct noise-resilient contexts. An Operational Grammar Graph (OGG) further supports adaptive workflow planning and optimization, enabling the agent to refine its operational strategies based on downstream ICL feedback. Experimental results demonstrate that ContextNav achieves state-of-the-art performance across various datasets, underscoring the promise of agentic workflows for advancing scalable and robust contextualization in multimodal ICL.

cs.AI↗

arXiv2025

Nonlocal Games in the High-Noise Regime: Optimal Quantum Values and Rigidity

Motivated by the limitations of near-term quantum devices, we study nonlocal games in the high-noise regime, where the two players may share arbitrarily many copies of a noisy entangled state. In this regime, existing rigidity theorems are unable to certify any nontrivial quantum structure. We first characterize the maximal quantum winning probabilities of the CHSH game [Clauser et al. '69], the Magic Square game [Mermin '90], and their 2-out-of-n variants [Chao et al. '18] as explicit functions of the noise rate. These characterizations enable the construction of device-independent protocols for estimating the underlying noise level. Building on these results, we prove noise-robust rigidity theorems showing that these games certify one, two, and n pairs of anticommuting Pauli observables, respectively. To our knowledge, these are the first rigidity results of Pauli measurements that remain sound in the high-noise regime, which has applications in Measurement-Device-Independent (MDI) cryptography and studying the computational power of Multi-prover Interactive Proof System with entanglement and a vanishing completeness-soundness gap ($\text{MIP}^*_0$). Our proofs rely on Sum-of-Squares decompositions and Pauli analysis techniques originating from quantum proof systems and quantum learning theory, respectively.

quant-ph↗

arXiv2025

VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft

Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments. Nonetheless, their performance is hindered by the absence of domain-specific knowledge. Methods that finetune on large-scale domain-specific data entail prohibitive development costs. This paper introduces VistaWise, a cost-effective agent framework that integrates cross-modal domain knowledge and finetunes a dedicated object detection model for visual analysis. It reduces the requirement for domain-specific training data from millions of samples to a few hundred. VistaWise integrates visual information and textual dependencies into a cross-modal knowledge graph (KG), enabling a comprehensive and accurate understanding of multimodal environments. We also equip the agent with a retrieval-based pooling strategy to extract task-related information from the KG, and a desktop-level skill library to support direct operation of the Minecraft desktop client via mouse and keyboard inputs. Experimental results demonstrate that VistaWise achieves state-of-the-art performance across various open-world tasks, highlighting its effectiveness in reducing development costs while enhancing agent performance.

cs.AI↗

arXiv2025

WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval

Text-Motion Retrieval (TMR) aims to retrieve 3D motion sequences semantically relevant to text descriptions. However, matching 3D motions with text remains highly challenging, primarily due to the intricate structure of the human body and its spatiotemporal dynamics. Existing approaches often overlook these complexities, relying on general encoding methods that fail to distinguish different body parts and their dynamics, limiting precise semantic alignment. To address this, we propose WaMo, a novel wavelet-based multi-frequency feature extraction framework. It fully captures joint-specific and time-varying motion details at multiple resolutions for individual joint trajectories, extracting discriminative motion features to achieve fine-grained alignment with texts. WaMo has three key components: (1) Trajectory Wavelet Decomposition decomposes motion signals into frequency components that preserve both local kinematic details and global motion semantics. (2) Trajectory Wavelet Reconstruction uses learnable inverse wavelet transforms to reconstruct original joint trajectories from extracted features, ensuring the preservation of essential spatiotemporal information. (3) Disordered Motion Sequence Prediction reorders shuffled motion sequences to improve learning of inherent temporal coherence, enhancing motion-text alignment. Extensive experiments demonstrate WaMo's superiority, achieving 17.0\% and 18.2\% relative improvements in $Rsum$ on HumanML3D and KIT-ML datasets, respectively, outperforming existing state-of-the-art (SOTA) methods. Code is available at https://github.com/3DAgentWorld/WaMo/.

cs.CV↗

arXiv2025

Step1X-Edit: A Practical Framework for General Image Editing

In recent years, image editing models have witnessed remarkable and rapid development. The recent unveiling of cutting-edge multimodal models such as GPT-4o and Gemini2 Flash has introduced highly promising image editing capabilities. These models demonstrate an impressive aptitude for fulfilling a vast majority of user-driven editing requirements, marking a significant advancement in the field of image manipulation. However, there is still a large gap between the open-source algorithm with these closed-source models. Thus, in this paper, we aim to release a state-of-the-art image editing model, called Step1X-Edit, which can provide comparable performance against the closed-source models like GPT-4o and Gemini2 Flash. More specifically, we adopt the Multimodal LLM to process the reference image and the user's editing instruction. A latent embedding has been extracted and integrated with a diffusion image decoder to obtain the target image. To train the model, we build a data generation pipeline to produce a high-quality dataset. For evaluation, we develop the GEdit-Bench, a novel benchmark rooted in real-world user instructions. Experimental results on GEdit-Bench demonstrate that Step1X-Edit outperforms existing open-source baselines by a substantial margin and approaches the performance of leading proprietary models, thereby making significant contributions to the field of image editing.

cs.CV↗

arXiv2025

Succinct Perfect Zero-knowledge for MIP*

In their recent breakthrough result, Slofstra and the second author show that there is a two-player one-round perfect zero-knowledge MIP* protocol for RE (STOC'24). We build on their result to show that there exists a succinct two-player one-round perfect zero-knowledge MIP* protocol for RE against dishonest verifiers with polylog question size and O(1) answer size, or with O(1) question size and polylog answer size. To prove our result, we study the three central compression techniques underlying the MIP*=RE proof (Ji et al. '20): question reduction, oracularization, and answer reduction. We show that question reduction preserves the perfect (as well as statistical and computational) zero-knowledge properties of the original protocol against dishonest verifiers, and oracularization and answer reduction preserve the perfect (as well as statistical and computational) zero-knowledge properties of the original protocol against honest verifiers. Secondly, we show that every constraint-constraint binary constraint system (BCS) nonlocal game, which provides a quantum information characterization of MIP*, can be converted to a synchronous constraint-variable BCS game to preserve perfect completeness for our compression. Lastly, we present a parametrized perfect-zero-knowledge transformation of MIP* protocols, which generalizes the transformation in (Slofstra and Kieran STOC'24) . This transformation allows us to preserve the zero-knowledge property against dishonest verifiers in the recursively oracularized protocols in our compression.

quant-ph↗

arXiv2024

Optimal Quantum Purity Amplification

Quantum purity amplification (QPA) provides a novel approach to counteracting the pervasive noise that degrades quantum states. We present the optimal QPA protocol for general quantum systems and global noise, resolving a two-decade open problem. Under strong depolarization, our protocol achieves an exponential reduction in sample complexity over the best-known methods. We provide an efficient implementation of the protocol based on generalized quantum phase estimation. Additionally, we introduce SWAPNET, a sparse and shallow circuit that enables QPA for near-term experiments. Simulations in both digital and analog quantum settings, along with experiments on superconducting quantum processors, confirm the protocol's robustness and practical utility. Our findings suggest that QPA could improve the performance of quantum information processing tasks, particularly in the context of Noisy Intermediate-Scale Quantum (NISQ) devices, where reducing the effect of noise with limited resources is critical.

quant-ph↗

arXiv2024

DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild

Blind image quality assessment (IQA) in the wild, which assesses the quality of images with complex authentic distortions and no reference images, presents significant challenges. Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem. Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA (DP-IQA), to utilize the T2I model's prior for improved performance and generalization ability. Specifically, we utilize pre-trained Stable Diffusion as the backbone, extracting multi-level features from the denoising U-Net guided by prompt embeddings through a tunable text adapter. Simultaneously, an image adapter compensates for information loss introduced by the lossy pre-trained encoder. Unlike T2I models that require full image distribution modeling, our approach targets image quality assessment, which inherently requires fewer parameters. To improve applicability, we distill the knowledge into a lightweight CNN-based student model, significantly reducing parameters while maintaining or even enhancing generalization performance. Experimental results demonstrate that DP-IQA achieves state-of-the-art performance on various in-the-wild datasets, highlighting the superior generalization capability of T2I priors in blind IQA tasks. To our knowledge, DP-IQA is the first method to apply pre-trained diffusion priors in blind IQA. Codes and checkpoints are available at https://github.com/RomGai/DP-IQA.

cs.CV↗

arXiv2024

Protocols and Trade-Offs of Quantum State Purification

Quantum state purification is crucial in quantum communication and computation, aiming to recover a purified state from multiple copies of an unknown noisy state. This work introduces a general state purification framework designed to achieve the highest fidelity with a specified probability and characterize the associated trade-offs. For i.i.d. quantum states under depolarizing noise, our framework can replicate the purification protocol proposed by [Barenco et al., SIAM Journal on Computing, 26(5), 1997] and further provide exact formulas for the purification fidelity and probability with explicit trade-offs. We prove the protocols' optimality for two copies of noisy states with any dimension and confirm its optimality for higher numbers of copies and dimensions through numerical analysis. Our methodological approach paves the way for proving the protocol's optimality in more general scenarios and leads to optimal protocols for other noise models. Furthermore, we present a systematic implementation method via block encoding and parameterized quantum circuits, providing explicit circuits for purifying three-copy and four-copy states under depolarizing noise. Finally, we estimate the sample complexity and generalize the protocol to a recursive form, demonstrating its practicality for quantum computers with limited memory.

quant-ph↗

arXiv2023

BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction

Analyzing and reconstructing visual stimuli from brain signals effectively advances the understanding of human visual system. However, the EEG signals are complex and contain significant noise. This leads to substantial limitations in existing works of visual stimuli reconstruction from EEG, such as difficulties in aligning EEG embeddings with the fine-grained semantic information and a heavy reliance on additional large self-collected dataset for training. To address these challenges, we propose a novel approach called BrainVis. Firstly, we divide the EEG signals into various units and apply a self-supervised approach on them to obtain EEG time-domain features, in an attempt to ease the training difficulty. Additionally, we also propose to utilize the frequency-domain features to enhance the EEG representations. Then, we simultaneously align EEG time-frequency embeddings with the interpolation of the coarse and fine-grained semantics in the CLIP space, to highlight the primary visual components and reduce the cross-modal alignment difficulty. Finally, we adopt the cascaded diffusion models to reconstruct images. Using only 10\% training data of the previous work, our proposed BrainVis outperforms state of the arts in both semantic fidelity reconstruction and generation quality. The code is available at https://github.com/RomGai/BrainVis.

cs.CV↗

arXiv2023

The Computational Advantage of MIP* Vanishes in the Presence of Noise

Quantum multiprover interactive proof systems with entanglement MIP* are much more powerful than its classical counterpart MIP (Babai et al. '91, Ji et al. '20): while MIP = NEXP, the quantum class MIP* is equal to RE, a class including the halting problem. This is because the provers in MIP* can share unbounded quantum entanglement. However, recent works of Qin and Yao '21 and '23 have shown that this advantage is significantly reduced if the provers' shared state contains noise. This paper attempts to exactly characterize the effect of noise on the computational power of quantum multiprover interactive proof systems. We investigate the quantum two-prover one-round interactive system MIP*[poly, O(1)], where the verifier sends polynomially many bits to the provers and the provers send back constantly many bits. We show noise completely destroys the computational advantage given by shared entanglement in this model. Specifically, we show that if the provers are allowed to share arbitrarily many noisy EPR states, where each EPR state is affected by an arbitrarily small constant amount of noise, the resulting complexity class is equivalent to NEXP = MIP. This improves significantly on the previous best-known bound of NEEEXP (nondeterministic triply exponential time) by Qin and Yao '21. We also show that this collapse in power is due to the noise, rather than the O(1) answer size, by showing that allowing for noiseless EPR states gives the class the full power of RE = MIP*[poly, poly]. Along the way, we develop two technical tools of independent interest. First, we give a new, deterministic tester for the positivity of an exponentially large matrix, provided it has a low-degree Fourier decomposition in terms of Pauli matrices. Secondly, we develop a new invariance principle for smooth matrix functions having bounded third-order Fr\'echet derivatives or which are Lipschitz continous.

quant-ph↗

arXiv2023

A Cryptographic Perspective on the Verifiability of Quantum Advantage

In recent years, achieving verifiable quantum advantage on a NISQ device has emerged as an important open problem in quantum information. The sampling-based quantum advantages are not known to have efficient verification methods. This paper investigates the verification of quantum advantage from a cryptographic perspective. We establish a strong connection between the verifiability of quantum advantage and cryptographic and complexity primitives, including efficiently samplable, statistically far but computationally indistinguishable pairs of (mixed) quantum states ($\mathsf{EFI}$), pseudorandom states ($\mathsf{PRS}$), and variants of minimum circuit size problems ($\mathsf{MCSP}$). Specifically, we prove that a) a sampling-based quantum advantage is either verifiable or can be used to build $\mathsf{EFI}$ and even $\mathsf{PRS}$ and b) polynomial-time algorithms for a variant of $\mathsf{MCSP}$ would imply efficient verification of quantum advantages. Our work shows that the quest for verifiable quantum advantages may lead to applications of quantum cryptography, and the construction of quantum primitives can provide new insights into the verifiability of quantum advantages.

quant-ph↗