arXiv subjects

Quang Nguyen

Publications and source records attributed to Quang Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

Robots Need More than VLA and World Models

Generalist robot intelligence is often framed as a policy-scaling problem: collect more robot demonstrations, train larger Vision-Language-Action (VLA) models, and expect broader generalisation. In this position paper, we argue that this framing is incomplete. The central bottleneck is not only policy learning, but the absence of mechanisms that convert the world's abundant unstructured behavioural data into grounded robot supervision. Human motion, internet video, simulation rollouts, and interactive demonstrations contain rich information about tasks, goals, contacts, failures, and physical constraints, yet most of this information is not directly usable by robot policies because it lacks embodiment-specific action labels, task semantics, and reward structure. We identify four missing components for the next generation of robotics: data interfaces for autolabelling unstructured behaviour, embodiment interfaces for retargeting human motion to robot actions, world-model interfaces for physics-grounded 3D reasoning, and reward interfaces for inferring task progress and success from video and language. We survey recent progress in robot foundation models, cross-embodiment datasets, learning from video, world models, and reward modelling, and propose a research agenda for building robotics systems that can learn not only from robot demonstrations, but from the broader physical world.

cs.RO↗

arXiv2026

Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust

Agent-based modeling (ABM) has long been used in economics to study human behavior, and large language model (LLM) agents now enable new forms of social and economic simulation. While prior work has discovered strategic deception by LLM agents in financial trading and auction markets, e-commerce remains underexplored despite its distinctive information asymmetry: sellers privately observe product quality, whereas buyers rely on advertised claims and reputation signals. We introduce TruthMarketTwin, a controlled simulation framework for studying LLM-agent behavior in e-commerce markets. The framework is one of the first to model bilateral trade under asymmetric information sharing, where agents make strategic listing, purchasing, rating, and recourse-related decisions to optimize seller profit and buyer utility. We find that LLM agents released into traditional markets autonomously exploit weaknesses in reputation-based governance, while warrant enforcement reduces deception and reshapes strategic reasoning. Our results position LLM-agent simulation as a tool for studying institution-governed autonomous markets.

cs.AI↗

arXiv2026

SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Images

Seismic images reconstruct subsurface reflectivity from field recordings, guiding exploration and reservoir monitoring. Gas chimneys are vertical anomalies caused by subsurface fluid migration. Understanding these phenomena is crucial for assessing hydrocarbon potential and avoiding drilling hazards. However, accurate detection is challenging due to strong seismic attenuation and scattering. Traditional physics-based methods are computationally expensive and sensitive to model errors, while deep learning offers efficient alternatives, yet lacks labeled datasets. In this work, we introduce \textbf{SIGMA}, a new physics-based dataset for gas chimney understanding in seismic images, featuring (i) pixel-level gas-chimney mask for detection and (ii) paired degraded and ground-truth image for enhancement. We employed physics-based methods that cover a wide range of geological settings and data acquisition conditions. Comprehensive experiments demonstrate that SIGMA serves as a challenging benchmark for gas chimney interpretation and benefits general seismic understanding.

cs.CV↗

arXiv2026

NFL step-and-turn: A generative framework for evaluating player movement in American football

In sports analytics, player tracking data have driven significant advancements in the task of player evaluation. We present a novel generative framework for evaluating the observed frame-by-frame player positioning against a distribution of hypothetical alternatives. We illustrate our approach by modeling the within-play movement of an individual ball carrier in the National Football League (NFL). Specifically, we develop Bayesian multilevel models for frame-level player movement based on two components: step length (distance between successive locations) and turn angle (change in direction between successive steps). Using the step-and-turn models, we perform posterior predictive simulation to generate hypothetical ball carrier steps at each frame during a play. This enables comparison of the observed player movement with a distribution of simulated alternatives using common valuation measures in American football. We apply our framework to tracking data from the first nine weeks of the 2022 NFL season and derive novel player performance metrics based on hypothetical evaluation.

stat.AP↗

arXiv2026

DeDPO: Debiased Direct Preference Optimization for Diffusion Models

Direct Preference Optimization (DPO) has emerged as a predominant alignment method for diffusion models, facilitating off-policy training without explicit reward modeling. However, its reliance on large-scale, high-quality human preference labels presents a severe cost and scalability bottleneck. To overcome this, We propose a semi-supervised framework augmenting limited human data with a large corpus of unlabeled pairs annotated via cost-effective synthetic AI feedback. Our paper introduces Debiased DPO (DeDPO), which uniquely integrates a debiased estimation technique from causal inference into the DPO objective. By explicitly identifying and correcting the systematic bias and noise inherent in synthetic annotators, DeDPO ensures robust learning from imperfect feedback sources, including self-training and Vision-Language Models (VLMs). Experiments demonstrate that DeDPO is robust to the variations in synthetic labeling methods, achieving performance that matches and occasionally exceeds the theoretical upper bound of models trained on fully human-labeled data. This establishes DeDPO as a scalable solution for human-AI alignment using inexpensive synthetic supervision.

cs.CV↗

arXiv2026

Accelerated Sinkhorn Algorithms for Partial Optimal Transport

Partial Optimal Transport (POT) addresses the problem of transporting only a fraction of the total mass between two distributions, making it suitable when marginals have unequal size or contain outliers. While Sinkhorn-based methods are widely used, their complexity bounds for POT remain suboptimal and can limit scalability. We introduce Accelerated Sinkhorn for POT (ASPOT), which integrates alternating minimization with Nesterov-style acceleration in the POT setting, yielding a complexity of $\mathcal{O}(n^{7/3}\varepsilon^{-5/3})$. We also show that an informed choice of the entropic parameter $\gamma$ improves rates for the classical Sinkhorn method. Experiments on real-world applications validate our theories and demonstrate the favorable performance of our proposed methods.

cs.LG↗

arXiv2025

SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities

Recent advances in 3D-aware generative models have enabled high-fidelity image synthesis of human identities. However, this progress raises urgent questions around user consent and the ability to remove specific individuals from a model's output space. We address this by introducing SUGAR, a framework for scalable generative unlearning that enables the removal of many identities (simultaneously or sequentially) without retraining the entire model. Rather than projecting unwanted identities to unrealistic outputs or relying on static template faces, SUGAR learns a personalized surrogate latent for each identity, diverting reconstructions to visually coherent alternatives while preserving the model's quality and diversity. We further introduce a continual utility preservation objective that guards against degradation as more identities are forgotten. SUGAR achieves state-of-the-art performance in removing up to 200 identities, while delivering up to a 700% improvement in retention utility compared to existing baselines. Our code is publicly available at https://github.com/judydnguyen/SUGAR-Generative-Unlearn.

cs.CV↗

arXiv2025

Overcoming the Curvature Bottleneck in MeanFlow

MeanFlow offers a promising framework for one-step generative modeling by directly learning a mean-velocity field, bypassing expensive numerical integration. However, we find that the highly curved generative trajectories of existing models induce a noisy loss landscape, severely bottlenecking convergence and model quality. We leverage a fundamental geometric principle to overcome this: mean-velocity estimation is drastically simpler along straight paths. Building on this insight, we propose Rectified MeanFlow, a self-distillation approach that learns the mean-velocity field over a straightened velocity field, induced by rectified couplings from a pretrained model. To further promote linearity, we introduce a distance-based truncation heuristic that prunes residual high-curvature pairs. By smoothing the optimization landscape, our method achieves strong one-step generation performance. We improve the FID of baseline MeanFlow models from 30.9 to 8.6 under same training budget, and outperform the recent 2-rectified flow++ by 33.4% in FID while running 26x faster. Our work suggests that the difficulty of one-step flow generation stems partially from the rugged optimization landscapes induced by curved trajectories. Code is available at https://github.com/Xinxi-Zhang/Re-MeanFlow.

cs.CV↗

arXiv2025

Learning Human Motion with Temporally Conditional Mamba

Learning human motion based on a time-dependent input signal presents a challenging yet impactful task with various applications. The goal of this task is to generate or estimate human movement that consistently reflects the temporal patterns of conditioning inputs. Existing methods typically rely on cross-attention mechanisms to fuse the condition with motion. However, this approach primarily captures global interactions and struggles to maintain step-by-step temporal alignment. To address this limitation, we introduce Temporally Conditional Mamba, a new mamba-based model for human motion generation. Our approach integrates conditional information into the recurrent dynamics of the Mamba block, enabling better temporally aligned motion. To validate the effectiveness of our method, we evaluate it on a variety of human motion tasks. Extensive experiments demonstrate that our model significantly improves temporal alignment, motion realism, and condition consistency over state-of-the-art approaches. Our project page is available at https://zquang2202.github.io/TCM.

cs.CV↗

arXiv2025

LEAF: A Robust Expert-Based Framework for Few-Shot Continual Event Detection

Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full fine-tuning of a shared base model, which leads to knowledge interference between tasks. Moreover, they frequently rely on data augmentation strategies that can introduce unnatural or semantically distorted inputs. To address these limitations, we propose LEAF, a novel and robust expert-based framework for FCED. LEAF integrates a specialized mixture of experts architecture into the base model, where each expert is parameterized with low-rank adaptation (LoRA) matrices. A semantic-aware expert selection mechanism dynamically routes instances to the most relevant experts, enabling expert specialization and reducing knowledge interference. To improve generalization in limited-data settings, LEAF incorporates a contrastive learning objective guided by label descriptions, which capture high-level semantic information about event types. Furthermore, to prevent overfitting on the memory buffer, our framework employs a knowledge distillation strategy that transfers knowledge from previous models to the current one. Extensive experiments on multiple FCED benchmarks demonstrate that LEAF consistently achieves state-of-the-art performance.

cs.LG↗

arXiv2025

EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba

Estimating human dance motion is a challenging task with various industrial applications. Recently, many efforts have focused on predicting human dance motion using either egocentric video or music as input. However, the task of jointly estimating human motion from both egocentric video and music remains largely unexplored. In this paper, we aim to develop a new method that predicts human dance motion from both egocentric video and music. In practice, the egocentric view often obscures much of the body, making accurate full-pose estimation challenging. Additionally, incorporating music requires the generated head and body movements to align well with both visual and musical inputs. We first introduce EgoAIST++, a new large-scale dataset that combines both egocentric views and music with more than 36 hours of dancing motion. Drawing on the success of diffusion models and Mamba on modeling sequences, we develop an EgoMusic Motion Network with a core Skeleton Mamba that explicitly captures the skeleton structure of the human body. We illustrate that our approach is theoretically supportive. Intensive experiments show that our method clearly outperforms state-of-the-art approaches and generalizes effectively to real-world data.

cs.CV↗

arXiv2025

CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models

Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual synthesis. While recent personalization methods have explored the decomposition of explicit content style, they remain tailored for diffusion models. Meanwhile, Visual Autoregressive Modeling (VAR) has emerged as a promising alternative with a next-scale prediction paradigm, achieving performance comparable to that of diffusion models. In this paper, we explore VAR as a generative framework for CSD, leveraging its scale-wise generation process for improved disentanglement. To this end, we propose CSD-VAR, a novel method that introduces three key innovations: (1) a scale-aware alternating optimization strategy that aligns content and style representation with their respective scales to enhance separation, (2) an SVD-based rectification method to mitigate content leakage into style representations, and (3) an Augmented Key-Value (K-V) memory enhancing content identity preservation. To benchmark this task, we introduce CSD-100, a dataset specifically designed for content-style decomposition, featuring diverse subjects rendered in various artistic styles. Experiments demonstrate that CSD-VAR outperforms prior approaches, achieving superior content preservation and stylization fidelity.

cs.CV↗

arXiv2025

ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

We present ExCyTIn-Bench, the first benchmark to Evaluate an LLM agent X on the task of Cyber Threat Investigation through security questions derived from investigation graphs. Real-world security analysts must sift through a large number of heterogeneous security logs, follow multi-hop chains of evidence to investigate threats. With the developments of LLMs, building LLM-based agents for automatic threat investigation is a promising direction. We construct a benchmark from a controlled Azure tenant including a SQL environment covering 57 log tables from Microsoft Sentinel and related services, and 7542 generated questions. We leverage security logs extracted with expert-crafted detection logic to build threat investigation graphs, and then generate questions with LLMs using paired nodes on the graph, taking the start node as background context and the end node as answer. Anchoring each question to these explicit nodes and edges not only provides automatic, explainable ground truth answers but also makes the pipeline reusable and readily extensible to new logs. Our comprehensive experiments on the test set with different models confirm the difficulty of the task: the best model so far can achieve a reward of 0.606, leaving much headroom for future research. The code is available at https://github.com/microsoft/SecRL

cs.CR↗

arXiv2025

A Bayesian circular mixed-effects model for explaining variability in directional movement in American football

Change of direction is a key element of player movement in American football, yet there remains a lack of objective approaches for in-game performance evaluation of this athletic trait. Using tracking data, we propose a Bayesian mixed-effects model with heterogeneous variances for assessing a player's ability to make variable directional adjustments while moving on the field. We model the turn angle (i.e., angle between successive displacement vectors) for NFL ball carriers on both passing and rushing plays, focusing on receivers after the catch and running backs after the handoff. In particular, we consider a von Mises distribution for the frame-level turn angle and explicitly model both the mean and concentration parameters with relevant spatiotemporal and contextual covariates. Of primary interest, we include player random effects that allow the turn angle concentration to vary by ball carrier nested within position groups. This offers practical insight into player evaluation, as it reveals the shiftiest ball carriers with great variability in turning behavior. We illustrate our approach with results from the first nine weeks of the 2022 NFL regular season and explore player-specific and positional differences in turn angle variability.

stat.AP↗

arXiv2025

FurniMAS: Language-Guided Furniture Decoration using Multi-Agent System

Furniture decoration is an important task in various industrial applications. However, achieving a high-quality decorative result is often time-consuming and requires specialized artistic expertise. To tackle these challenges, we explore how multi-agent systems can assist in automating the decoration process. We propose FurniMAS, a multi-agent system for automatic furniture decoration. Specifically, given a human prompt and a household furniture item such as a working desk or a TV stand, our system suggests relevant assets with appropriate styles and materials, and arranges them on the item, ensuring the decorative result meets functionality, aesthetic, and ambiance preferences. FurniMAS assembles a hybrid team of LLM-based and non-LLM agents, each fulfilling distinct roles in a typical decoration project. These agents collaborate through communication, logical reasoning, and validation to transform the requirements into the final outcome. Extensive experiments demonstrate that our FurniMAS significantly outperforms other baselines in generating high-quality 3D decor.

cs.AI↗

arXiv2025

GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System

Language-driven grasp detection has the potential to revolutionize human-robot interaction by allowing robots to understand and execute grasping tasks based on natural language commands. However, existing approaches face two key challenges. First, they often struggle to interpret complex text instructions or operate ineffectively in densely cluttered environments. Second, most methods require a training or finetuning step to adapt to new domains, limiting their generation in real-world applications. In this paper, we introduce GraspMAS, a new multi-agent system framework for language-driven grasp detection. GraspMAS is designed to reason through ambiguities and improve decision-making in real-world scenarios. Our framework consists of three specialized agents: Planner, responsible for strategizing complex queries; Coder, which generates and executes source code; and Observer, which evaluates the outcomes and provides feedback. Intensive experiments on two large-scale datasets demonstrate that our GraspMAS significantly outperforms existing baselines. Additionally, robot experiments conducted in both simulation and real-world settings further validate the effectiveness of our approach. Our project page is available at https://zquang2202.github.io/GraspMAS

cs.RO↗

arXiv2025

Leveraging Cloud-Fog Automation for Autonomous Collision Detection and Classification in Intelligent Unmanned Surface Vehicles

Industrial Cyber-Physical Systems (ICPS) technologies are foundational in driving maritime autonomy, particularly for Unmanned Surface Vehicles (USVs). However, onboard computational constraints and communication latency significantly restrict real-time data processing, analysis, and predictive modeling, hence limiting the scalability and responsiveness of maritime ICPS. To overcome these challenges, we propose a distributed Cloud-Edge-IoT architecture tailored for maritime ICPS by leveraging design principles from the recently proposed Cloud-Fog Automation paradigm. Our proposed architecture comprises three hierarchical layers: a Cloud Layer for centralized and decentralized data aggregation, advanced analytics, and future model refinement; an Edge Layer that executes localized AI-driven processing and decision-making; and an IoT Layer responsible for low-latency sensor data acquisition. Our experimental results demonstrated improvements in computational efficiency, responsiveness, and scalability. When compared with our conventional approaches, we achieved a classification accuracy of 86\%, with an improved latency performance. By adopting Cloud-Fog Automation, we address the low-latency processing constraints and scalability challenges in maritime ICPS applications. Our work offers a practical, modular, and scalable framework to advance robust autonomy and AI-driven decision-making and autonomy for intelligent USVs in future maritime ICPS.

cs.DC↗

arXiv2025

WAVE++: Capturing Within-Task Variance for Continual Relation Extraction with Adaptive Prompting

Memory-based approaches have shown strong performance in Continual Relation Extraction (CRE). However, storing examples from previous tasks increases memory usage and raises privacy concerns. Recently, prompt-based methods have emerged as a promising alternative, as they do not rely on storing past samples. Despite this progress, current prompt-based techniques face several core challenges in CRE, particularly in accurately identifying task identities and mitigating catastrophic forgetting. Existing prompt selection strategies often suffer from inaccuracies, lack robust mechanisms to prevent forgetting in shared parameters, and struggle to handle both cross-task and within-task variations. In this paper, we propose WAVE++, a novel approach inspired by the connection between prefix-tuning and mixture of experts. Specifically, we introduce task-specific prompt pools that enhance flexibility and adaptability across diverse tasks while avoiding boundary-spanning risks; this design more effectively captures both within-task and cross-task variations. To further refine relation classification, we incorporate label descriptions that provide richer, more global context, enabling the model to better distinguish among different relations. We also propose a training-free mechanism to improve task prediction during inference. Moreover, we integrate a generative model to consolidate prior knowledge within the shared parameters, thereby removing the need for explicit data storage. Extensive experiments demonstrate that WAVE++ outperforms state-of-the-art prompt-based and rehearsal-based methods, offering a more robust solution for continual relation extraction. Our code is publicly available at https://github.com/PiDinosauR2804/WAVE-CRE-PLUS-PLUS.

cs.CL↗