arXiv subjects

Fushuo Huo

Publications and source records attributed to Fushuo Huo.

18 recordsLinked to original sources

arXiv2026

World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation

Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained manipulation, however, benefits from anticipating how wrist-local interactions may evolve under the global task context. To address this limitation, we present World-to-Wrist VLA (W2-VLA), a VLA model for fine-grained robot manipulation with task-conditioned future wrist modeling. Given current multi-view observations and a task instruction, W2-VLA contextualizes a set of latent modeling tokens as a compact interface between the vision-language model and the wrist predictor. Conditioned on this interface and the observed wrist history, the predictor forecasts future wrist latents, which are transformed into future-aware context for action prediction. In addition, we introduce W2-CoT, a synthesis pipeline that produces structured annotations describing manipulation progress, physical transition cues, and wrist-local evidence. These annotations provide auxiliary supervision that shapes the task-conditioned latent interface. Experiments on LIBERO, RoboTwin 2.0, and real-world manipulation tasks demonstrate improved fine-grained and contact-sensitive manipulation across both single-arm and bimanual settings, while maintaining action-generation rates above 80 Hz.

cs.RO↗

arXiv2026

UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following

Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks a more realistic requirement: an agent often needs to first find a language-described target and then persistently follow that target in a dynamic environment. While recent work has started to study human search, existing settings are typically evaluated in task-specific scenarios and often rely on stronger prior knowledge of the environment. Moreover, they usually treat searching and following as separate tasks and still lack a unified benchmark for systematic evaluation. To address these limitations, we introduce the Unified Embodied Seeking and Following Benchmark (UESF-Bench), a large-scale and diverse benchmark for embodied human seeking and following. The benchmark requires agents to handle semantic-guided exploration, reliable behavior switching and recovery, and delayed identity grounding. To this end, we propose SeekFollow-VLA, a vision-language-action framework with a task-driven routing mechanism for latent phase inference and transition modeling between seeking and following. Experimental results show that SeekFollow-VLA achieves clear improvements over both single-head and dual-head baselines across single-person and multi-person environments, establishing a baseline for unified embodied seek-and-follow.

cs.AI↗

arXiv2026

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

While spatial foundation models have demonstrated impressive performance on standard datasets, a critical question remains: are they truly all-round players capable of generalizing robustly across diverse downstream tasks, arbitrary viewpoints, shifting scene domains, varying input densities, and specific hardware constraints? Answering this overarching question requires a holistic assessment, yet current models are mainly evaluated on specific domains for which they were specifically designed or trained. Such evaluations are intrinsically limited by narrow paradigm coverage, limited scene domains, and arbitrary frame sampling, making it fundamentally difficult to assess their true generalization capabilities. To address this gap, we present SpatialBench, a cross-paradigm, domain-diverse benchmark for spatial foundation models with deterministic sampling. SpatialBench features unprecedented scale and rigorous deterministic design, comprising 19 datasets and 546 scenes across 5 diverse spatial domains. It comprehensively evaluates 41 models across 6 paradigms on 5 task suites under 4 different input density settings. Our extensive evaluation reveals that current models are not yet all-round players, and uncovers crucial insights for future advancement. Specifically, we demonstrate that full-context attention maximizes accuracy while bounded-memory strategies unlock long-sequence scalability. Moreover, our empirical evaluations in challenging embodied and egocentric tasks demonstrate that strict domain alignment and high data quality are far more critical to performance than simple dataset scaling. Furthermore, to address the largest data gap identified in our analysis, we go beyond evaluation by introducing a large-scale dataset, DA-Next-5M, and a strong baseline model, DA-Next, pushing the boundaries of spatial representation learning.

cs.CV↗

arXiv2026

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to training-loss degeneration, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting $\mathrm{MAE}_\mathrm{P}$ by $1.96\times$ over the leading baseline, while preserving clean performance within 5% $\mathrm{MAE}_\mathrm{C}$.

cs.CR↗

arXiv2026

PrismWF: A Multi-Granularity Patch-Based Transformer for Robust Website Fingerprinting Attack

Tor is a low-latency anonymous communication network that protects user privacy by encrypting website traffic. However, recent website fingerprinting (WF) attacks have shown that encrypted traffic can still leak users' visited websites by exploiting statistical features such as packet size, direction, and inter-arrival time. Most existing WF attacks formulate the problem as a single-tab classification task, which significantly limits their effectiveness in realistic browsing scenarios where users access multiple websites concurrently, resulting in mixed traffic traces. To this end, we propose PrismWF, a multi-granularity patch-based Transformer for multi-tab WF attack. Specifically, we design a robust traffic feature representation for raw web traffic traces and extract multi-granularity features using convolutional kernels with different receptive fields. To effectively integrate information across temporal scales, the proposed model refines features through three hierarchical interaction mechanisms: inter-granularity detail supplementation from fine to coarse granularities, intra-granularity patch interaction with dedicated router tokens, and router-guided dual-level intra- and cross-granularity fusion. This design aligns with the cognitive logic of global coarse-grained reconnaissance and local fine-grained querying, enabling effective modeling of mixed traffic patterns in WF attack scenarios. Extensive experiments on various datasets and WF defenses demonstrate that our method achieves state-of-the-art performance compared to existing baselines.

cs.CR↗

arXiv2025

Towards Robust Multimodal Learning in the Open World

The rapid evolution of machine learning has propelled neural networks to unprecedented success across diverse domains. In particular, multimodal learning has emerged as a transformative paradigm, leveraging complementary information from heterogeneous data streams (e.g., text, vision, audio) to advance contextual reasoning and intelligent decision-making. Despite these advancements, current neural network-based models often fall short in open-world environments characterized by inherent unpredictability, where unpredictable environmental composition dynamics, incomplete modality inputs, and spurious distributions relations critically undermine system reliability. While humans naturally adapt to such dynamic, ambiguous scenarios, artificial intelligence systems exhibit stark limitations in robustness, particularly when processing multimodal signals under real-world complexity. This study investigates the fundamental challenge of multimodal learning robustness in open-world settings, aiming to bridge the gap between controlled experimental performance and practical deployment requirements.

cs.LG↗

arXiv2025

Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection

The advent of multi-modal large language models (MLLMs) has greatly advanced research on video fake news detection (VFND) tasks. Existing benchmarks typically focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. To address these limitations, we introduce {POVFNDB (Process-oriented Video Fake News Detection Benchmark)}, a process-oriented benchmark comprising 10 tasks designed to systematically evaluate MLLMs' perception, understanding, and reasoning capabilities in VFND. This benchmark contains \textit{36,240} human-annotated question-answer (QA) in structured or open-ended formats, spanning 15 distinct evaluation dimensions that characterize different aspects of the video fake news detection process. Using POVFNDB, we conduct comprehensive evaluations on both proprietary and open-source MLLMs. Moreover, we establish a strong benchmark baseline by fine-tuning Qwen2.5VL-7B-Instruct on process-oriented chain-of-thought data constructed with our proposed POVFND-CoT framework, achieving state-of-the-art performance on VFND.

cs.CV↗

arXiv2025

Cross-Receiver Generalization for RF Fingerprint Identification via Feature Disentanglement and Adversarial Training

Radio frequency fingerprint identification (RFFI) is a key technique for wireless network security, leveraging intrinsic hardware imperfections to enable transmitter identification. Although deep neural networks are effective at extracting discriminative RF features, their performance is significantly affected by receiver-induced variability in practical deployments. In real-world scenarios, RF signals inherently entangle transmitter-specific characteristics with receiver-dependent distortions, leading models to capture receiver-related patterns when training and evaluation are conducted on the same device. Consequently, replacing the receiver during deployment often results in notable performance degradation. To address this issue, we propose a cross-receiver robust RFFI framework that explicitly disentangles transmitter-specific and receiver-specific representations. The proposed method integrates adversarial domain alignment with receiver-aware regularization to suppress residual receiver information in transmitter features while enforcing intra-receiver consistency in receiver-specific representations. A feature separation constraint is further introduced to decouple the two components in the latent space. Extensive experiments on multi-receiver WiFi datasets demonstrate that the proposed method consistently outperforms state-of-the-art baselines under cross-receiver evaluation and significantly improves robustness to receiver replacement.

cs.LG↗

arXiv2025

Responsible Diffusion: A Comprehensive Survey on Safety, Ethics, and Trust in Diffusion Models

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential threats to DMs. To provide advanced and comprehensive insights into safety, ethics, and trust in DMs, this survey comprehensively elucidates its framework, threats, and countermeasures. Each threat and its countermeasures are systematically examined and categorized to facilitate thorough analysis. Furthermore, we introduce specific examples of how DMs are used, what dangers they might bring, and ways to protect against these dangers. Finally, we discuss key lessons learned, highlight open challenges related to DM security, and outline prospective research directions in this critical field. This work aims to accelerate progress not only in the technical capabilities of generative artificial intelligence but also in the maturity and wisdom of its application.

cs.CR↗

arXiv2025

EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models

Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety. We study sycophancy -- models' tendency to uncritically echo user-provided information -- in high-stakes clinical settings. We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs. It contains 2,122 images across 18 departments and 20 modalities with 90 prompts that simulate biased inputs from patients, medical students, and physicians. We evaluate medical-specific, open-source, and proprietary LVLMs. All exhibit substantial sycophancy; the best proprietary model (Claude 3.7 Sonnet) still shows 45.98% sycophancy, and GPT-4.1 reaches 59.15%. Many medical-specific models exceed 95% sycophancy despite only moderate accuracy. Fine-grained analyses by bias type, department, perceptual granularity, and modality identify factors that increase susceptibility. We further show that higher data quality/diversity and stronger domain knowledge reduce sycophancy without harming unbiased accuracy. EchoBench also serves as a testbed for mitigation: simple prompt-level interventions (negative prompting, one-shot, few-shot) produce consistent reductions and motivate training- and decoding-time strategies. Our findings highlight the need for robust evaluation beyond accuracy and provide actionable guidance toward safer, more trustworthy medical LVLMs.

cs.CV↗

arXiv2025

On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View

Federated Learning (FL) enables training models across decentralized data silos while preserving client data privacy. Recent research has explored efficient methods for post-training large language models (LLMs) within FL to address computational and communication challenges. While existing approaches often rely on access to LLMs' internal information, which is frequently restricted in real-world scenarios, an inference-only paradigm (black-box FedLLM) has emerged to address these limitations. This paper presents a comprehensive survey on federated tuning for LLMs. We propose a taxonomy categorizing existing studies along two axes: model access-based and parameter efficiency-based optimization. We classify FedLLM approaches into white-box, gray-box, and black-box techniques, highlighting representative methods within each category. We review emerging research treating LLMs as black-box inference APIs and discuss promising directions and open challenges for future research.

cs.LG↗

arXiv2024

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. Existing methods mitigate this issue mainly from two perspectives: One approach leverages extra knowledge like robust instruction tuning LVLMs with curated datasets or employing auxiliary analysis networks, which inevitable incur additional costs. Another approach, known as contrastive decoding, induces hallucinations by manually disturbing the vision or instruction raw inputs and mitigates them by contrasting the outputs of the disturbed and original LVLMs. However, these approaches rely on empirical holistic input disturbances and double the inference cost. To avoid these issues, we propose a simple yet effective method named Self-Introspective Decoding (SID). Our empirical investigation reveals that pretrained LVLMs can introspectively assess the importance of vision tokens based on preceding vision and text (both instruction and generated) tokens. We develop the Context and Text-aware Token Selection (CT2S) strategy, which preserves only unimportant vision tokens after early layers of LVLMs to adaptively amplify text-informed hallucination during the auto-regressive decoding. This approach ensures that multimodal knowledge absorbed in the early layers induces multimodal contextual rather than aimless hallucinations. Subsequently, the original token logits subtract the amplified vision-and-text association hallucinations, guiding LVLMs decoding faithfully. Extensive experiments illustrate SID generates less-hallucination and higher-quality texts across various metrics, without extra knowledge and much additional computation burdens.

cs.CV↗

arXiv2023

Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection

Selecting proper clients to participate in each federated learning (FL) round is critical to effectively harness a broad range of distributed data. Existing client selection methods simply consider the mining of distributed uni-modal data, yet, their effectiveness may diminish in multi-modal FL (MFL) as the modality imbalance problem not only impedes the collaborative local training but also leads to a severe global modality-level bias. We empirically reveal that local training with a certain single modality may contribute more to the global model than training with all local modalities. To effectively exploit the distributed multiple modalities, we propose a novel Balanced Modality Selection framework for MFL (BMSFed) to overcome the modal bias. On the one hand, we introduce a modal enhancement loss during local training to alleviate local imbalance based on the aggregated global prototypes. On the other hand, we propose the modality selection aiming to select subsets of local modalities with great diversity and achieving global modal balance simultaneously. Our extensive experiments on audio-visual, colored-gray, and front-back datasets showcase the superiority of BMSFed over baselines and its effectiveness in multi-modal data exploitation.

cs.LG↗

arXiv2023

DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning

Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or enhances unseen composed entities, and as a result, entanglement between state and object primitives cannot be fully utilized. Admittedly, vision-language models (VLMs) could naturally cope with CZSL through tuning prompts, while uneven entanglement leads prompts to be dragged into local optimum. In this paper, we take a further step to introduce a novel Disentangled and Recurrent Prompt Tuning framework termed DRPT to better tap the potential of VLMs in CZSL. Specifically, the state and object primitives are deemed as learnable tokens of vocabulary embedded in prompts and tuned on seen compositions. Instead of jointly tuning state and object, we devise a disentangled and recurrent tuning strategy to suppress the traction force caused by entanglement and gradually optimize the token parameters, leading to a better prompt space. Notably, we develop a progressive fine-tuning procedure that allows for incremental updates to the prompts, optimizing the object first, then the state, and vice versa. Meanwhile, the optimization of state and object is independent, thus clearer features can be learned to further alleviate the issue of entangling misleading optimization. Moreover, we quantify and analyze the entanglement in CZSL and supplement entanglement rebalancing optimization schemes. DRPT surpasses representative state-of-the-art methods on extensive benchmark datasets, demonstrating superiority in both accuracy and efficiency.

cs.CV↗

arXiv2023

Non-Exemplar Online Class-incremental Continual Learning via Dual-prototype Self-augment and Refinement

This paper investigates a new, practical, but challenging problem named Non-exemplar Online Class-incremental continual Learning (NO-CL), which aims to preserve the discernibility of base classes without buffering data examples and efficiently learn novel classes continuously in a single-pass (i.e., online) data stream. The challenges of this task are mainly two-fold: (1) Both base and novel classes suffer from severe catastrophic forgetting as no previous samples are available for replay. (2) As the online data can only be observed once, there is no way to fully re-train the whole model, e.g., re-calibrate the decision boundaries via prototype alignment or feature distillation. In this paper, we propose a novel Dual-prototype Self-augment and Refinement method (DSR) for NO-CL problem, which consists of two strategies: 1) Dual class prototypes: vanilla and high-dimensional prototypes are exploited to utilize the pre-trained information and obtain robust quasi-orthogonal representations rather than example buffers for both privacy preservation and memory reduction. 2) Self-augment and refinement: Instead of updating the whole network, we optimize high-dimensional prototypes alternatively with the extra projection module based on self-augment vanilla prototypes, through a bi-level optimization problem. Extensive experiments demonstrate the effectiveness and superiority of the proposed DSR in NO-CL.

cs.CV↗

arXiv2022

ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning

Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which induces a tremendously large output space containing all possible state-object compositions. Existing works either learn the joint compositional state-object embedding or predict simple primitives with separate classifiers. However, the former heavily relies on external word embedding methods, and the latter ignores the interactions of interdependent primitives, respectively. In this paper, we revisit the primitive prediction approach and propose a novel method, termed Progressive Cross-primitive Compatibility (ProCC), to mimic the human learning process for OW-CZSL tasks. Specifically, the cross-primitive compatibility module explicitly learns to model the interactions of state and object features with the trainable memory units, which efficiently acquires cross-primitive visual attention to reason high-feasibility compositions, without the aid of external knowledge. Moreover, considering the partial-supervision setting (pCZSL) as well as the imbalance issue of multiple task prediction, we design a progressive training paradigm to enable the primitive classifiers to interact to obtain discriminative information in an easy-to-hard manner. Extensive experiments on three widely used benchmark datasets demonstrate that our method outperforms other representative methods on both OW-CZSL and pCZSL settings by large margins.

cs.CV↗

arXiv2022

REQA: Coarse-to-fine Assessment of Image Quality to Alleviate the Range Effect

Blind image quality assessment (BIQA) of user generated content (UGC) suffers from the range effect which indicates that on the overall quality range, mean opinion score (MOS) and predicted MOS (pMOS) are well correlated; focusing on a particular range, the correlation is lower. The reason for the range effect is that the predicted deviations both in a wide range and in a narrow range destroy the uniformity between MOS and pMOS. To tackle this problem, a novel method is proposed from coarse-grained metric to fine-grained prediction. Firstly, we design a rank-and-gradient loss for coarse-grained metric. The loss keeps the order and grad consistency between pMOS and MOS, thereby reducing the predicted deviation in a wide range. Secondly, we propose multi-level tolerance loss to make fine-grained prediction. The loss is constrained by a decreasing threshold to limite the predicted deviation in narrower and narrower ranges. Finally, we design a feedback network to conduct the coarse-to-fine assessment. On the one hand, the network adopts feedback blocks to process multi-scale distortion features iteratively and on the other hand, it fuses non-local context feature to the output of each iteration to acquire more quality-aware feature representation. Experimental results demonstrate that the proposed method can alleviate the range effect compared to the state-of-the-art methods effectively.

eess.IV↗

arXiv2022

Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention

Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each input sample. Existing works usually exploit attention mechanism to generate the correlation among different labels. However, most of them are usually biased on several major classes while neglect most of the minor classes with the same importance in input samples, and may thus result in overly diffused attention maps that cannot sufficiently cover minor classes. We argue that disregarding the connection between major and minor classes, i.e., correspond to the global and local information, respectively, is the cause of the problem. In this paper, we propose a novel framework of unbiased multi-label zero-shot learning, by considering various class-specific regions to calibrate the training process of the classifier. Specifically, Pyramid Feature Attention (PFA) is proposed to build the correlation between global and local information of samples to balance the presence of each class. Meanwhile, for the generated semantic representations of input samples, we propose Semantic Attention (SA) to strengthen the element-wise correlation among these vectors, which can encourage the coordinated representation of them. Extensive experiments on the large-scale multi-label zero-shot benchmarks NUS-WIDE and Open-Image demonstrate that the proposed method surpasses other representative methods by significant margins.

cs.CV↗