Searcharxiv⌕ Search

arXiv subjects

Ziqi Wang

Publications and source records attributed to Ziqi Wang.

At least 19 recordsLinked to original sources

Fairness-Aware Federated Learning with Trajectory Shapley Value

Federated learning is an emerging distributed paradigm that addresses the challenges posed by heterogeneous, privacy-sensitive data. It enables multiple clients to train a model collaboratively by aggregating their local updates at a server. However, conventional aggregation schemes typically use fixed weights that fail to reflect unequal and time-varying client contributions, leading to biased and unstable learning. To improve fairness and stability, we propose the Trajectory Shapley Value (TSV), a contribution metric that evaluates how each client influences the optimization trajectory of the global model using a validation-based, temporally consistent utility. Building on TSV, we design FedTSV, an adaptive aggregation method that converts per-round evaluations into dynamic client weights, allowing the server to respond to heterogeneous and adversarial participation in real time. Experiments on benchmark datasets show that FedTSV accelerates convergence, improves robustness, and yields more equitable contribution assessments, thereby providing a principled foundation for fairness-aware federated optimization. The source code is available at https://github.com/DCN-FAU-AvH/FedTSV.

cs.LG↗

FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning

Federated learning (FL) is a promising framework for learning from distributed data while maintaining privacy. The development of efficient FL algorithms encounters various challenges, including heterogeneous data and systems, limited communication capacities, and constrained local computational resources. Recently developed FedADMM methods show great resilience to both data and system heterogeneity. However, they still suffer from performance deterioration if the hyperparameters are not carefully tuned. To address this issue, we propose an inexact and self-adaptive FedADMM algorithm, termed FedADMM-InSa. First, we design an inexactness criterion for the clients' local updates to eliminate the need for empirically setting the local training accuracy. This inexactness criterion can be assessed by each client independently based on its unique condition, thereby reducing the local computational cost and mitigating the undesirable straggle effect. The convergence of the resulting inexact ADMM is proved under the assumption of strongly convex loss functions. Additionally, we present a self-adaptive scheme that dynamically adjusts each client's penalty parameter, enhancing algorithm robustness by mitigating the need for empirical penalty parameter choices for each client. Extensive numerical experiments on both synthetic and real-world datasets are conducted. As validated by some numerical tests, our proposed algorithm can reduce the clients' local computational load significantly and also accelerate the learning process compared to the vanilla FedADMM. The source code is available at https://github.com/DCN-FAU-AvH/FedADMM-InSa.

cs.LG↗

Approximate and Weighted Data Reconstruction Attack in Federated Learning

Federated Learning (FL) is a distributed learning paradigm that enables multiple clients to collaborate on building a machine learning model without sharing their private data. Although FL is considered privacy-preserved by design, recent data reconstruction attacks demonstrate that an attacker can recover clients' training data based on the parameters shared in FL. However, most existing methods fail to attack the most widely used horizontal Federated Averaging (FedAvg) scenario, where clients share model parameters after multiple local training steps. To tackle this issue, we propose an interpolation-based approximation method, which makes attacking FedAvg scenarios feasible by generating the intermediate model updates of the clients' local training processes. Then, we design a layer-wise weighted loss function to improve the data quality of reconstruction. We assign different weights to model updates in different layers concerning the neural network structure, with the weights tuned by Bayesian optimization. Finally, experimental results validate the superiority of our proposed approximate and weighted attack (AWA) method over the other state-of-the-art methods, as demonstrated by the substantial improvement in different evaluation metrics for image data reconstructions. The source code is available at https://github.com/DCN-FAU-AvH/FL-AWA-attack.

cs.LG↗

AURA: Auditory Spatial Intelligence via a Unified Representation from a General-Audio Encoder through Complete Alignment

Answering spatial questions about multi-source scenes requires a model both to identify each sound and to locate it. Existing spatial audio-language models obtain spatial information from a dedicated encoder, which separates spatial and semantic processing into distinct feature spaces. We study whether a general-audio codec trained without spatial supervision can serve both purposes. A controlled layer-wise analysis shows that the frozen codec retains spatial information, with lateral cues carried by the difference between the two ear channels. This information, however, is not readily accessible: in dual-source scenes, a model trained on these features predicts left/right at chance and, on the remaining axes, assigns the detected direction to the queried and the non-queried source equally often. We attribute this failure to an audio--text information asymmetry, in which the audio contains both sources while the answer describes only the queried one. A controlled $2\times2$ experiment shows that either completing the scene description or exposing the inter-channel difference lifts left/right accuracy above chance, whereas binding directions to the queried source requires both. Building on these findings, AURA keeps the codec and the language model frozen and exceeds the strongest dedicated system on SpatialSoundQA by 10.31 points in dual-source direction accuracy, with about 40\% of its trainable parameters.

cs.SD↗

Kelix Technical Report

Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation under self-supervision. Extending this paradigm to multimodal data requires a shared, discrete representation across modalities. However, most vision-language models (VLMs) still rely on a hybrid interface: discrete text tokens paired with continuous Vision Transformer (ViT) features. Because supervision is largely text-driven, these models are often biased toward understanding and cannot fully leverage large-scale self-supervised learning on non-text data. Recent work has explored discrete visual tokenization to enable fully autoregressive multimodal modeling, showing promising progress toward unified understanding and generation. Yet existing discrete vision tokens frequently lose information due to limited code capacity, resulting in noticeably weaker understanding than continuous-feature VLMs. We present Kelix, a fully discrete autoregressive unified model that closes the understanding gap between discrete and continuous visual representations.

cs.CV↗

CRAFT: Conflict-Resolved Aggregation for Federated Training

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while conflicting with specific clients, causing degradation for those clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a reference direction while satisfying conflict-free alignment constraints. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates conflicts through its projection geometry. Extensive experiments on heterogeneous benchmarks demonstrate that CRAFT improves the accuracy of the global model while reducing performance disparity across clients compared with state-of-the-art baselines. The source code for CRAFT is available at https://github.com/tum-pbs/CRAFT.

cs.LG↗

Kwai Summary Attention V2 Technical Report

Summary-token architectures such as Kwai Summary Attention (KSA) compress distant context into learnable Summary token per chunk, and hybrid variants interleave these layers with full attention to retain exact access to the original text. In such hybrid KSA-Full architecture, the interleaving inserted summary tokens are served as a streaming flow role across different layers. Although effective, however, it also introduce some bottlenecks: (1) the different layers summary compression chunk must be same, therefore hard to reach a flexible KV Cache compression, e.g., different layer set different summary compression chunk window. (2) in the full-attention layers, the summary token introduced additional computation cost, but such layer ignore them and still pay quadratic prefilling, therefore unfriendly to the computation side. Motivated by them, we developed the KSA V2, which not only achieves a more flexible KV cache memory compression but also reduces the computation cost in Full attention layer. Specifically, we found that the summary tokens can serve two roles: the KV memory and sparse indexer.

cs.LG↗

UTOPI: Efficient Egocentric Long-Video Understanding in AR via User-Guided Token Pre-Compression

As long-video understanding gains increasing attention, augmented reality (AR) devices are emerging as a compelling deployment platform. However, egocentric videos exhibit significant temporal redundancy, imposing substantial memory and computational burdens on resource-constrained AR hardware. To address this challenge, we introduce UTOPI, a plug-and-play pre-compression module designed specifically for egocentric long videos on AR platforms. First, we leverage user motion signals to estimate inter-frame overlap and propose a viewpoint-shift-invariant pruning algorithm. Second, we exploit eye-tracking sensors to identify user fixations, enabling the separation of attended foreground content from background and its preferential retention via a fine-tuned neural network-based adjustment mechanism. Across multiple benchmarks and model backbones, UTOPI achieves up to 95% compression while preserving performance. Code and project page are available at https://sai-lab-nyu.github.io/utopi/.

cs.LG↗

Decompose Dynamics Before Learning Dependencies in Spatiotemporal Systems

Relations in networked spatiotemporal systems are often learned from observations that entangle dynamics governed by different mechanisms, obscuring what evolves locally and how it propagates across nodes. We introduce Component-Aware Network Dynamics with Ordered Relations (CANDOR), which decomposes local dynamics before learning their dependencies. CANDOR represents each trajectory through a persistent background, gradual accumulation and release, and sparse shocks. Conditioned on these components, a delay-aware physical branch models edge and sample-dependent propagation over directed topology, while a topology-unconstrained functional branch discovers latent dependencies from background dynamics. Context-adaptive fusion combines functional, forward-propagation, and reverse-support forecasts, with training objectives encouraging specialized and semantically consistent representations. Experiments on two traffic benchmarks and three long-horizon water-quality datasets span two distinct spatiotemporal systems: human-driven urban traffic and naturally evolving river water quality. CANDOR achieves the lowest aggregate normalized error across five datasets, outperforming the overall runner-up by 7.25%. These results establish decomposition before dependency learning as an effective principle for spatiotemporal representation learning.

cs.CE↗

L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit

Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy. This measure overlooks a common failure: whether the citation source attached to an answer exists and supports the rule the system attributes to it. We present L-MARS, an open multi-agent legal QA system with agentic search and judge-driven evidence checks, and audit it claim by claim against its cited source. Each atomic claim is labelled with a six-class taxonomy and scored with strict-ALCE under cross-provider judging, where the answerer and verifier come from different model families. On a stratified 100-question Bar Exam audit, retrieval barely moves accuracy, yet the multi-turn judge loop lifts strict citation F1 from 0.13 (naive RAG) to 0.25 and cuts the no-citation rate from 34% to 13%. We further introduce Faith-Search, a post-draft step that re-verifies and repairs unreachable citations; it drops the unreachable rate below 1% but does not improve F1 over the multi-turn loop, so we report it as a targeted reachability intervention rather than a faithfulness breakthrough. A 50-question LegalSearchQA case study confirms the picture: retrieve-then-draft pipelines saturate near 0.75 citation F1, while a single-agent web-search baseline collapses to 0.22 under external audit.

cs.AI↗

Inertial rotation of a small oblate spheroid in a simple shear flow

We compare experiments and fully-resolved particle simulations designed to match the experimental conditions of a weakly inertial, neutrally buoyant, moderately oblate spheroid in shear flow under confinement. The study revisits an apparent discrepancy observed in earlier experiments, where a trajectory starting close to tumbling appeared to remain near the tumbling orbit, whereas weak-inertia theory predicts attraction to log-rolling for this particle shape. Experimental and numerical results are benchmarked against theory valid for asymptotically small particle Reynolds numbers and for unconfined systems. By accounting for confinement and inertia, together with sensitivity to initial conditions, and the finite observation time, we provide a consistent interpretation of the theoretical, experimental, and numerical results. Specifically, we show that log rolling is the only stable long-time orbit for the moderately oblate spheroid considered here; neither confinement nor finite inertia changes this orbit selection. Instead, inertia tends to accelerate the drift toward log rolling, whereas confinement reduces it, with the confinement effect being dominant in the present parameter range.

physics.flu-dyn↗

Phase Transitions in Collective Damage of Civil Structures under Natural Hazards

The fate of cities under natural hazards depends not only on hazard intensity but also on the coupling of structural damage, a collective process that remains poorly understood. Here we show that urban structural damage exhibits phase-transition phenomena. As hazard intensity increases, the system can shift abruptly from a largely safe to a largely damaged state, analogous to a discontinuous phase transition in statistical physics. Higher diversity in the building portfolio smooths this transition, but multiscale damage clustering traps the system in a highly volatile regime that suppresses the emergence of predictable Gaussian statistics. The observed phenomenological patterns are interpreted through an effective random-field Ising model, with its key parameters translated into tangible engineering variables such as hazard demand, structural diversity, and modeling uncertainty. These insights establish a phase-aware description of collective damage, revealing that common engineering simplifications can distort the inherent phase of real urban portfolios. Critically, such phase distortions can substantially bias hazard loss estimates, producing relative errors of up to 50% in exceedance probabilities under moderate earthquakes---equivalent to a several-fold gap in anticipated repair costs. The phase-aware description turns the collective behavior of civil infrastructure damage into actionable diagnostics for urban risk assessment and planning.

stat.AP↗

On the origin of nonreciprocal charge transport in topological insulator BiSbTeSe2

Nonreciprocal charge transport provides an effective approach for probing direction dependent charge dynamics and spin-momentum-locked electronic states. Here, we report highly gate-tunable nonreciprocal charge transport in dual-gated BiSbTeSe2 topological insulator device. The second-harmonic longitudinal resistance is linear in both current and magnetic field. The nonreciprocal response reaches its maximum near the charge neutrality point, exhibits sign reversals on either side, and is strongly suppressed once the Fermi level enters the bulk states. We suggest that the nonreciprocal response is attributed to the inhomogeneity of spin-momentum locking in the topological surface states. The nonreciprocal signal near the charge neutrality point is about one order of magnitude larger than that without gate modulation and remains robust up to 300 K, highlighting BiSbTeSe2 as a promising platform for room-temperature nonlinear electronics.

cond-mat.mes-hall↗

Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory

Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a significant challenge as they move toward long-horizon tasks and lifelong settings. Addressing this challenge requires effective memory mechanisms that can maintain continuity across sessions, adapt to changing users and environments, and refine memory-management policies through accumulated experience. We introduce a two-axis analytical framework for multimodal agent memory structured around two key questions: how multimodal information is formed and represented (Axis I, Formation and Representation), and how its management adapts with accumulated experience (Axis II, Memory Management). Axis I, Formation and Representation, characterizes what information is retained and how it is encoded (e.g., modality-specific embeddings, textual and structured records, latent and parametric representations) to support subsequent reasoning and action. Axis II, Memory Management, distinguishes three tiers: T1 Static Memory reuses fixed memory; T2 Dynamic Memory updates memory through a stable policy; and T3 Self-Evolving Memory updates memory through an evolving policy. Based on this framework, we synthesize recurring design patterns and derive principles for balancing source fidelity with abstraction, maintaining temporal validity and provenance, grounding memory use in recoverable evidence, and evolving memory policies over time. Furthermore, we discuss the challenges and potential future directions for the memory mechanism of multimodal agents.

cs.AI↗

Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning

Large Language Models (LLMs) inevitably internalize substantial amounts of sensitive or private information during pre-training, while LLM unlearning aims to selectively erase specific knowledge to prevent privacy leakage with minimal loss of model utility. However, existing methods struggle to balance forget quality with utility, and typically incur substantial computational costs due to parameter fine-tuning. To address this, we propose Nullify, a training-free, non-destructive activation steering method for LLM unlearning. Nullify employs steering vectors during inference to redirect privacy-related activations away from their memorized answers, while satisfying a null-space constraint that leaves retained-query activations essentially unaffected to maintain utility. Evaluations on TOFU and MUSE show that Nullify matches or surpasses established baselines in forget quality while achieving near-lossless preservation of model utility. By avoiding weight updates entirely, Nullify serves as an efficient, plug-and-play inference-time intervention framework.

cs.LG↗

Efficient seismic reliability and fragility analysis of lifeline networks using subset simulation

Various simulation-based and analytical methods have been developed to evaluate the seismic fragilities of individual structures. However, the seismic safety and resilience of a community are substantially affected by network reliability, determined not only by component fragilities but also by network topology and commodity/information flows. Seismic reliability analyses of networks often encounter significant computational challenges due to complex network topologies, interdependencies among ground motions, and low failure probabilities. This paper proposes a variance-reduction method for network fragility analysis using subset simulation to overcome these challenges. The binary network limit-state function is reformulated into more informative piecewise continuous functions. The proposed limit-state functions quantify the proximity of each sample to the network failure domain, thereby enabling the construction of specialized intermediate failure events, which can be utilized in subset simulation and other sequential Monte Carlo approaches. Moreover, by identifying an implicit relationship between intermediate failure events and seismic intensity, we propose a technique to obtain the entire network fragility curve with a single execution of specialized subset simulation. Numerical examples demonstrate that the proposed method can effectively evaluate system-level fragility for large-scale networks.

stat.AP↗

Gate-tunable large second-order and third-order nonlinear Hall effect in topological insulator BiSbTeSe2

The nonlinear Hall effect (NLHE) holds significant promise for next-generation electronic device applications, and it is essential to explore and engineer a strong and highly tunable NLHE. In this work, we report large second-order and third-order NLHEs in dual-gated BiSbTeSe2 devices. Both the second-order and third-order NLHE are highly gate-tunable. The second-order NLHE exhibits a higher generation efficiency than those reported in previous topological insulator systems, and it can be stably observed up to room temperature. Meanwhile, the generation efficiency of the third-order NLHE is comparable to previously reported values. The scaling analysis indicates that the second-order NLHE is consistent with contributions from skew scattering and a term compatible with either the Berry curvature dipole or side jump, whereas the third-order NLHE is consistent with contributions from the Berry connection polarizability tensor and higher-order skew scattering. Our work establishes a promising experimental platform for the development of NLHE-based devices.

cond-mat.mes-hall↗

Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning

In federated learning (FL), a central server typically allocates training efforts to clients. However, from a market-oriented perspective, clients may independently choose their training efforts based on rational self-interest. To study this setting, we propose a potential game framework in which each client's payoff is determined by its individual effort and the rewards provided by the server. The rewards are influenced by the collective efforts of all clients and can be modulated by a reward factor. We first establish the existence of Nash equilibria (NEs) and then investigate their uniqueness in a stationary setting. We show that the NEs depend nonlinearly on the reward factor and exhibit a nonsmooth transition at a critical value, where the stationary potential loses strict curvature, leading to nonunique NEs and a jump between low-effort and high-effort branches. Furthermore, we prove the convergence of the best-response algorithm for computing NEs in our FL game. Finally, we apply the clients' rational efforts derived from the NEs to FL training with various datasets and models, thereby validating the effectiveness of the identified critical reward factor. The source code is available at https://github.com/DCN-FAU-AvH/FL-Potential-Game

cs.LG↗