Searcharxiv⌕ Search

arXiv subjects

Jingjing Zhang

Publications and source records attributed to Jingjing Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Duet: Co-Optimizing P2P Message Propagation and Rotating-Leader Consensus

In blockchain systems, peer-to-peer (P2P) overlay networks play a crucial role in providing reliable, scalable and efficient message-delivery services to upper layers. However, the consensus layer and the underlying P2P network remain mutually opaque in existing blockchains, waiving the opportunity for further improvement. In contrast to other P2P applications, blockchain can naturally be abstracted as a state machine. We therefore leverage this abstraction to record network topologies and latencies in a trusted and coordinated manner. With this support, we propose three improvements to rotating-leader consensus protocols and their underlying P2P networks: (1) accelerating leader rotation; (2) introducing a reliable-broadcast paradigm that employs tree-based dissemination in the normal case and falls back to gossip only when necessary; and (3) constructing latency-aware dissemination trees. We integrate the above ideas into Tendermint and libp2p, and conduct empirical evaluation on Amazon EC2 platform using up to 300 nodes distributed across 10 regions. The results demonstrate that, compared with gossip-based dissemination over the same topology, our prototype improves peak throughput by up to $7.26\times$.

cs.DC↗
arXiv2026

Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach

Large language model (LLM) agents are increasingly extended through Agent Skills, reusable artifacts that package natural-language metadata, procedural instructions, and execution-time resources for runtime use. As open-source skill marketplaces expand, users and agents increasingly rely on brief metadata to select third-party skills, making it difficult to detect inconsistencies between a skill's description and its true behavior, a problem we call cross-layer misalignment. To address this issue, we propose Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), an LLM-based framework that detects misalignment by modeling the layered structure of Agent Skills and learning cross-layer consistency. Using a normalized corpus of over 264,000 open-source skills and a human-verified challenge set, PL-HCL improves Macro-F1 from approximately 0.45 for unadapted baselines to 0.87-0.89 across evaluated LLM backbones. This approach offers an effective screening tool for users and operators, as well as design principles for detecting inconsistencies in layered digital artifacts.

cs.AI↗
arXiv2026

InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization

Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through future prediction. In practice, existing designs tend to erode the semantics of the pretrained backbone, suffer interference among heterogeneous objectives, and learn future prediction from scratch in pixel space, leaving the dynamics priors of pretrained video generators unexploited. We present InternVLA-A1.5, which builds the policy on a native VLM backbone that keeps training on VQA and subtask prediction, and attaches a lightweight unified expert for continuous action generation. Future prediction is recast as a latent-querying problem, where a small set of learnable foresight tokens condenses the task-relevant future into a compact latent code under the supervision of a frozen pretrained video generation model, so the policy inherits world-model dynamics priors without ever learning pixel-level generation. The video branch is discarded at inference, keeping real-time control. Pretrained on 1.2M robot episodes and 3M multimodal samples, InternVLA-A1.5 achieves the best overall results on all six simulation benchmarks. In the real world, the preserved semantics deliver the strongest compositional generalization on held-out instruction bindings, and the two designs together sustain long-horizon execution.

cs.RO↗
arXiv2026

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on costly triplets, Zero-Shot CIR (ZS-CIR) alleviates this reliance through proxy tasks trained on image-text pairs. However, existing proxy tasks primarily enhance visual and textual representations to accommodate a predefined composition mechanism such as pseudo-word injection into a frozen text encoder or linear feature arithmetic. As a result, the composition function itself remains unlearned, limiting the model's ability to express diverse and fine-grained semantic modifications. To address this, we propose FoCo, which models composition as two coordinated stages: focusing on modification-relevant visual content, and then completing the target semantics. We realize these through two proxy tasks: text-anchored visual aggregation to selectively gather visual content guided by localized textual semantics, and context-conditioned semantic completion to transform these aggregated visuals with the remaining scene context into a coherent composed representation. The tasks are trained jointly with a cross-instance contrastive objective, encouraging semantic diversity and discouraging shortcut composition strategies. Extensive experiments on four ZS-CIR benchmarks show FoCo's state-of-the-art performance and improved generalization.

cs.CV↗
arXiv2026

Divergence-Based Adaptive Aggregation for Byzantine Robust Federated Learning

Inherent client drifts caused by data heterogeneity, as well as vulnerability to Byzantine attacks within the system, hinder effective model training and convergence in federated learning (FL). This paper presents two new frameworks, named DiveRgence-based Adaptive aGgregation (DRAG) and Byzantine-Resilient DRAG (BR-DRAG), to mitigate client drifts and resist attacks while expediting training. DRAG designs a reference direction and a metric named divergence of degree to quantify the deviation of local updates. Accordingly, each worker can align its local update via linear calibration without extra communication cost. BR-DRAG refines DRAG under Byzantine attacks by maintaining a vetted root dataset at the server to produce trusted reference directions. The workers' updates can be then calibrated to mitigate divergence caused by malicious attacks. We analytically prove that DRAG and BR-DRAG achieve fast convergence for non-convex models under partial worker participation, data heterogeneity, and Byzantine attacks. Experiments validate the effectiveness of DRAG and its superior performance over state-of-the-art methods in handling client drifts, and highlight the robustness of BR-DRAG in maintaining resilience against data heterogeneity and diverse Byzantine attacks.

cs.DC↗
arXiv2026

Back to the Future: Rethinking Endorsement in Order-Execute Blockchains

Due to regulatory compliance and governance management, modern (permissioned) blockchains require flexible endorsement, which allows the endorsement policy for each contract or state object to be individually defined. To enable flexible endorsement, Hyperledger Fabric employs an execute-order-validate (EOV) paradigm, in which transactions first undergo speculative execution and endorsement, and are only then ordered and validated. Meanwhile, most blockchain systems, including the platform targeted in this work (i.e., ChainMaker), still follow a conflict-free order-execute framework. We argue that the EOV paradigm still faces several limitations, notably high abort rates in high-contention workloads such as those in Decentralized Finance (DeFi). To avoid refactoring our system and better suit DeFi applications, we try to integrate flexible endorsement into the classical order-execute architecture and accordingly propose a new framework. The key challenge is to deterministically remove problematic transactions from an ordered list, while preserving censorship resistance and decentralization for the remaining ones. We instantiate this framework on top of Tendermint, a seminal Byzantine fault-tolerant (BFT) protocol adopted in our system, and thereby propose FlexTender. By elegantly embedding endorsements into consensus, FlexTender incurs no additional messaging overhead in the normal case. Empirical evaluation using an Ethereum USDT workload demonstrates that FlexTender achieves up to $10.6\times$ speedup in throughput over an EOV simulation on the same platform.

cs.DC↗
arXiv2026

Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object representations from continuous, uncurated first-person videos without relying on manual annotations. This setting poses challenges of separating, recognizing, and persistently tracking objects amid clutter, occlusion, and ego-motion. We propose EgoViT, a unified vision Transformer framework designed to learn stable object representations from unlabeled egocentric video. EgoViT bootstraps this learning process by jointly discovering and stabilizing "proto-objects" through three synergistic mechanisms: (1) Proto-object Learning, which uses intra-frame distillation to form discriminative representations; (2) Depth Regularization, which grounds these representations in geometric structure; and (3) Teacher-Filtered Temporal Consistency, which enforces identity over time. This creates a virtuous cycle where initial object hypotheses are progressively refined into stable, persistent representations. The framework is trained end-to-end on unlabeled first-person videos and exhibits robustness to geometric priors of varied origin and quality. On standard benchmarks, EgoViT achieves +8.0% CorLoc improvement in unsupervised object discovery and +4.8% mIoU improvement in semantic segmentation, demonstrating its potential to lay a foundation for robust visual abstraction in embodied intelligence.

cs.CV↗
arXiv2026

Evaluating VLMs' Spatial Reasoning Over Robot Motion: A Step Towards Robot Planning with Motion Preferences

Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. While foundation models have been applied to task planning, it is still unclear the degree to which they have the capability of spatial reasoning required to enforce user preferences or constraints on motion, such as desired distances from objects, topological properties, or motion style preferences. In this paper, we evaluate the capability of four state-of-the-art VLMs at spatial reasoning over robot motion, using four different querying methods. Our results show that, with the highest-performing querying method, Qwen2.5-VL achieves 71.4% accuracy zero-shot and 75% on a smaller model after fine-tuning, and GPT-4o leads to lower performance. We evaluate two types of motion preferences (object-proximity and path-style), and we also analyze the trade-off between accuracy and computation cost in number of tokens. This work shows some promise in the potential of VLM integration with robot motion planning pipelines.

cs.RO↗
arXiv2026

Retrieving Patient-Specific Radiomic Feature Sets for Transparent Knee MRI Assessment

Classical radiomic features are designed to quantify image appearance and intensity patterns. Compared with end-to-end deep learning (DL) models trained for disease classification, radiomics pipelines with low-dimensional parametric classifiers offer enhanced transparency and interpretability, yet often underperform because of the reliance on population-level predefined feature sets. Recent work on adaptive radiomics uses DL to predict feature weights over a radiomic pool, then thresholds these weights to retain the top-k features from large radiomic pool F (often ~10^3). However, such marginal ranking can over-admit redundant descriptors and overlook complementary feature interactions. We propose a patient-specific feature-set selection framework that predicts a single compact feature set per subject, targeting complementary and diverse evidence rather than marginal top-k features. To overcome the intractable combinatorial search space of F choose k features, our method utilizes a 2-stage retrieval strategy: randomly sample diverse candidate feature sets, then rank these sets with a learned scoring function to select a high-performing feature set for the specific patient. The system consists of a feature-set scorer, and a classifier that performs the final diagnosis. We empirically show that the proposed two-stage retrieval approximates the original exhaustive all k-feature selection. Validating on tasks including ACL tear detection and KL grading for osteoarthritis, the experimental results achieve diagnostic performance, outperforming the top-k approach with the same k values, and competitive with end-to-end DL models while maintaining high transparency. The model generates auditable feature sets that link clinical outcomes to specific anatomical regions and radiomic families, allowing clinicians to inspect which anatomical structures and quantitative descriptors drive the prediction.

cs.CV↗
arXiv2026

TaleBot: A Tangible AI Companion to Support Children in Co-creative Storytelling for Resilience Cultivation

Resilience is a key factor affecting children's mental wellbeing and future development. Yet, limited HCI research has explored how to help children build resilience through adversarial experiences. Informed by a formative study with elementary school teachers and professional psychologists, we design TaleBot, an AI-empowered system that supports children to co-create stories about overcoming everyday adversities tailored to their personal situations. We evaluated the system with 12 elementary children in school counseling rooms under teacher guidance and conducted reflective interviews with parents upon the Child-AI co-created stories. The findings show that TaleBot encourages children in self-expression of feelings and thoughts, creating opportunities for teachers to provide personalized support and for parents to better understand the profound impact of family communication on children's mental wellbeing. We conclude with design implications for using generative AI to support children's mental health education and interventions across school and family contexts.

cs.HC↗
arXiv2026

InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation

Prevalent Vision-Language-Action (VLA) models are typically built upon Multimodal Large Language Models (MLLMs) and demonstrate exceptional proficiency in semantic understanding, but they inherently lack the capability to deduce physical world dynamics. Consequently, recent approaches have shifted toward World Models, typically formulated via video prediction; however, these methods often suffer from a lack of semantic grounding and exhibit brittleness in the presence of video prediction errors. To synergize semantic understanding with dynamic predictive capabilities, we present InternVLA-A1. This model employs a unified Mixture-of-Transformers architecture, coordinating three experts for scene understanding, visual foresight generation, and action execution. These components interact seamlessly through a unified masked self attention mechanism. Building upon InternVL3 and Qwen3-VL, we instantiate InternVLA-A1 at 2B and 3B parameter scales. We pre-train these models on heterogeneous data sources over real-world robot data, synthetic simulation data, and human videos, covering over 692M frames. This hybrid training strategy effectively harnesses the diversity of synthetic simulation data while minimizing the sim-to-real gap. We evaluated InternVLA-A1 on 12 real-world robotic tasks and a simulation benchmark. The results show that InternVLA-A1 consistently outperforms prior leading models: compared with pi0.5, it achieves +4.4\% on static manipulation tasks and +2.6\% on the RoboTwin 2.0 simulation benchmark, and delivers a +26.7\% boost on dynamic manipulation tasks.

cs.RO↗
arXiv2026

How Long Does It Take to Alleviate Discomfort? A Preliminary Study on Reducing Cybersickness in Novice Users

Cybersickness significantly impacts the user experience in VR applications. Locomotion tunneling is a widely adopted technique for mitigating cybersickness in susceptible users. However, there is a lack of research investigating the effects of prolonged use of locomotion tunneling among novice users. To fill this gap, we used VRChat as our experimental platform. We recruited 24 novice VR users, defined as participants with no prior experience using immersive virtual environments. We collected five days of data within a one-week period. The results indicated that participants exhibited significant mitigation to cybersickness by Day 4. However, a change in the VR scene on Day 5 led to a notable increase in cybersickness symptoms. Qualitative feedback revealed participant-perceived causes of cybersickness and suggested that the effectiveness of locomotion tunneling was limited in some scenarios. Finally, we discussed the limitations of the study and proposed directions for future research.

cs.HC↗
arXiv2025

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

Vision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models.

cs.RO↗
arXiv2025

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.

cs.RO↗
arXiv2025

pBeeGees: A Prudent Approach to Certificate-Decoupled BFT Consensus

Pipelined Byzantine Fault Tolerant (BFT) consensus is fundamental to permissioned blockchains. However, many existing protocols are limited by the requirement for view-consecutive quorum certificates (QCs). This constraint impairs performance and creates liveness vulnerabilities under adverse network conditions. Achieving "certificate decoupling"-committing blocks without this requirement-is therefore a key research goal. While the recent BeeGees algorithm achieves this, our work reveals that it suffers from security and liveness issues. To address this problem, this paper makes two primary contributions. First, we formally define these flaws as the Invalid Block Problem and the Hollow Chain Problem. Second, we propose pBeeGees, a new algorithm that addresses these issues while preserving certificate decoupling with no additional computational overhead. To achieve this, pBeeGees integrates traceback and pre-commit validation to solve the Invalid Block Problem.Further, to mitigate the Hollow Chain Problem, we introduce a prudent validation mechanism, which prevents unverified branches from growing excessively. To summarize, pBeeGees is the first protocol to simultaneously achieve safety, liveness, and certificate decoupling in a pipelined BFT framework. Experiments confirm that our design significantly reduces block commit latency compared to classic algorithms, particularly under frequent stopping faults.

cs.DC↗
arXiv2025

Extension of generalized KYP lemma: from LTI systems to LPV systems

The generalized Kalman-Yakubovich-Popov (gKYP) lemma, established by Iwasaki and Hara (2005 IEEE TAC), has served as a fundamental tool for finite-frequency analysis and synthesis of linear time-invariant (LTI) systems. Over the past two decades, efforts to extend the gKYP lemma from LTI systems to linear parameter varying (LPV) systems have been hindered by the intricate time-frequency inter-modulation effect between the input signal and the time-varying scheduling parameter. A key element in this framework is the frequency-dependent Integral Quadratic Constraint (IQC) function, which enables time-domain interpretation of the gKYP lemma, as demonstrated by Iwasaki et al in their companion 2005 System and Control Letter paper. The non-negativity property of this IQC function plays a crucial role in characterizing system behavior under frequency-limited inputs. In this paper, we first demonstrate through a counterexample that the IQC non-negativity property may fail for LPV systems, thereby invalidating existing results that rely on this assumption. To address this issue, we propose a reformulation strategy that replaces the original frequency range with an enlarged one, thereby restoring the non-negativity property for LPV systems. Moreover, we establish that the minimal required expansion depends on the interaction(or gap) between the system poles and the original frequency range, as well as a set of controllability Gramians. Building upon this results, an extension of gKYP lemma is presented, which allows us to conduct finite-frequency analysis of LPV systems in a direct and reliable manner. The potential and efficiency compared to existing results are demonstrated through numerical examples.

math.DS↗
arXiv2025

DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction

Decoding speech from brain signals is a challenging research problem. Although existing technologies have made progress in reconstructing the mel spectrograms of auditory stimuli at the word or letter level, there remain core challenges in the precise reconstruction of minute-level continuous imagined speech: traditional models struggle to balance the efficiency of temporal dependency modeling and information retention in long-sequence decoding. To address this issue, this paper proposes the Dynamic Multiscale Fusion Network (DMF2Mel), which consists of four core components: the Dynamic Contrastive Feature Aggregation Module (DC-FAM), the Hierarchical Attention-Guided Multi-Scale Network (HAMS-Net), the SplineMap attention mechanism, and the bidirectional state space module (convMamba). Specifically, the DC-FAM separates speech-related "foreground features" from noisy "background features" through local convolution and global attention mechanisms, effectively suppressing interference and enhancing the representation of transient signals. HAMS-Net, based on the U-Net framework,achieves cross-scale fusion of high-level semantics and low-level details. The SplineMap attention mechanism integrates the Adaptive Gated Kolmogorov-Arnold Network (AGKAN) to combine global context modeling with spline-based local fitting. The convMamba captures long-range temporal dependencies with linear complexity and enhances nonlinear dynamic modeling capabilities. Results on the SparrKULee dataset show that DMF2Mel achieves a Pearson correlation coefficient of 0.074 in mel spectrogram reconstruction for known subjects (a 48% improvement over the baseline) and 0.048 for unknown subjects (a 35% improvement over the baseline).Code is available at: https://github.com/fchest/DMF2Mel.

cs.SD↗
arXiv2025

Composed Multi-modal Retrieval: A Survey of Approaches and Applications

The burgeoning volume of multi-modal data necessitates advanced retrieval paradigms beyond unimodal and cross-modal approaches. Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology, enabling users to query images or videos by integrating a reference visual input with textual modifications, thereby achieving unprecedented flexibility and precision. This paper provides a comprehensive survey of CMR, covering its fundamental challenges, technical advancements, and applications. CMR is categorized into supervised, zero-shot, and semi-supervised learning paradigms. We discuss key research directions, including data construction, model architecture, and loss optimization in supervised CMR, as well as transformation frameworks and linear integration in zero-shot CMR, and semi-supervised CMR that leverages generated pseudo-triplets while addressing data noise/uncertainty. Additionally, we extensively survey the diverse application landscape of CMR, highlighting its transformative potential in e-commerce, social media, search engines, public security, etc. Seven high impact application scenarios are explored in detail with benchmark data sets and performance analysis. Finally, we further provide new potential research directions with the hope of inspiring exploration in other yet-to-be-explored fields. A curated list of works is available at: https://github.com/kkzhang95/Awesome-Composed-Multi-modal-Retrieval

cs.IR↗