Searcharxiv⌕ Search

arXiv subjects

Jingjing Jiang

Publications and source records attributed to Jingjing Jiang.

At least 19 recordsLinked to original sources
arXiv2026

Integrating Facial Generation into Full-Duplex Spoken Dialogue Systems

Full-duplex spoken dialogue models, such as Moshi, enable natural, low-latency voice conversations. However, they remain limited to the audio modality, lacking the facial expressions that are integral to human communication. We present Moshi-Face, the first full-duplex dialogue model that jointly processes the user's audio and facial input while simultaneously generating speech and facial motion. We first construct a vector-quantized variational autoencoder (VQ-VAE) as a face codec that encodes 3D head meshes extracted from facial videos into compact discrete tokens, referred to as face tokens, and conversely reconstructs 3D meshes from these tokens. We then extend Moshi with a Face Transformer module that generates face tokens non-autoregressively, enabling Moshi-Face to produce synchronized audio and face tokens in real time. Experiments show that Moshi-Face achieves audiovisual alignment at low latency while preserving the dialogue quality of the original audio-only model.

cs.HC↗
arXiv2026

GS-DOT: Gaussian splatting-based image reconstruction for diffuse optical tomography

This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficients are represented as a sparse sum of anisotropic Gaussian primitives optimized to fit measured time-resolved point-spread functions through analytic gradients and Adam optimization. This is the first adaptation of GS algorithms in the photon diffusion regime, where the ray transport function is replaced by the diffusion functions to enable accurate modeling of light transport in highly scattering media. Validation on synthetic tissue models demonstrate high accuracy in localization and quantification of reconstructed absorption maps for both clean and noisy signals. GS-DOT has demonstrated high robustness to noise and showed a huge reduction in memory demand.

eess.IV↗
arXiv2026

A Goal-Oriented Approach for Active Object Detection with Exploration-Exploitation Balance

Active object detection, which aims to identify objects of interest through controlled camera movements, plays a pivotal role in real-world visual perception for autonomous robotic applications, such as manufacturing tasks (e.g., assembly operations) performed in unknown environments. A dual control for exploration and exploitation (DCEE) algorithm is presented within goal-oriented control systems to achieve efficient active object detection, leveraging active learning by incorporating variance-based uncertainty estimation in the cost function. This novel method employs an exploration-exploitation balanced cost function to actively guide the selection of the next viewpoint. Specifically, active object detection is achieved through the development of a reward function that encodes knowledge about the confidence variation of objects as a function of viewpoint position within a given domain. By identifying the unknown parameters of this function, the system generates an optimal viewpoint planning strategy. DCEE integrates parameter estimation of the reward function and view planning, ensuring a balanced trade-off between the exploitation of learned knowledge and active exploration during the planning process. Moreover, it demonstrates remarkable adaptability across diverse scenarios, effectively handling LEGO brick detection at varying locations. Importantly, the algorithm maintains consistent configuration settings and a fixed number of parameters across various scenarios, underscoring its efficiency and robustness. To validate the proposed approach, extensive numerical studies, high-fidelity virtual simulations, and real-world experiments under various scenarios were conducted. The results confirm the effectiveness of DCEE in active object detection, showcasing superior performance compared to existing methods, including model predictive control (MPC) and entropy approaches.

eess.SY↗
arXiv2025

Transposed Poisson structures on the $q$-analog Virasoro-like algebras and $q$-Quantum Torus Lie algebras

We investigate the transposed Poisson structures on both the $q$-analog Virasoro-like algebra and $q$-quantum torus Lie algebra considering the cases where $q$ is generic and where $q$ is a primitive root of unity, respectively. We establish the following results: When $q$ is generic, there are no non-trivial $\frac{1}{2}$-derivations and consequently, no non-trivial transposed Poisson algebra structures exist on the $q$-analog Virasoro-like algebra. Meanwhile, the $q$-quantum torus Lie algebra does possess non-trivial $\frac{1}{2}$-derivations but lacks of a non-trivial transposed Poisson structure. When $q$ is a primitive root of unity, both the $q$-analog Virasoro-like algebra and the $q$-quantum torus Lie algebra possess non-trivial $\frac{1}{2}$-derivations. We present the non-trivial transposed Poisson algebra structure for the $q$-analog Virasoro-like algebra. However, the $q$-quantum torus Lie algebra lacks of a non-trivial transposed Poisson structure.

math.RA↗
arXiv2025

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at simultaneously reinforcing generation and understanding capabilities. Through systematic pilot studies, we uncover the significant potential of ULMs to enable the synergistic co-evolution of dual capabilities within a shared policy optimization framework. Building on this insight, we introduce CoRL, a co-reinforcement learning framework comprising a unified RL stage for joint optimization and a refined RL stage for task-specific enhancement. With the proposed CoRL, our resulting model, ULM-R1, achieves average improvements of 7% on three text-to-image generation datasets and 23% on nine multimodal understanding benchmarks. These results demonstrate the effectiveness of CoRL and highlight the substantial benefit of reinforcement learning in facilitating cross-task synergy and optimization for ULMs. Code is available at https://github.com/mm-vl/ULM-R1.

cs.CV↗
arXiv2025

Transposed Poisson Structures on Two Nambu 3-Lie Algebras

We describe the $\frac{1}{3}$-derivations and transposed Poisson structures of the Nambu 3-Lie algebras $A_ω^δ$ and $ A_{f,k} $. Specifically, we first present that $A_ω^δ$ is finitely generated and graded. Then we find that $A_ω^δ$ has non-trivial $\frac{1}{3}$-derivations and admits only trivial transposed Poisson structures. The 3-Lie algebra $A_{f,k}$ admits non-trivial transposed Poisson structures.

math.RA↗
arXiv2025

Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks

Inferring the unseen attribute-object composition is critical to make machines learn to decompose and compose complex concepts like people. Most existing methods are limited to the composition recognition of single-attribute-object, and can hardly learn relations between the attributes and objects. In this paper, we propose an attribute-object semantic association graph model to learn the complex relations and enable knowledge transfer between primitives. With nodes representing attributes and objects, the graph can be constructed flexibly, which realizes both single- and multi-attribute-object composition recognition. In order to reduce mis-classifications of similar compositions (e.g., scratched screen and broken screen), driven by the contrastive loss, the anchor image feature is pulled closer to the corresponding label feature and pushed away from other negative label features. Specifically, a novel balance loss is proposed to alleviate the domain bias, where a model prefers to predict seen compositions. In addition, we build a large-scale MultiAttribute Dataset (MAD) with 116,099 images and 8,030 label categories for inferring unseen multi-attribute-object compositions. Along with MAD, we propose two novel metrics Hard and Soft to give a comprehensive evaluation in the multi-attribute setting. Experiments on MAD and two other single-attribute-object benchmarks (MIT-States and UT-Zappos50K) demonstrate the effectiveness of our approach.

cs.CV↗
arXiv2025

Control Analysis and Design for Autonomous Vehicles Subject to Imperfect AI-Based Perception

Safety is a critical concern in autonomous vehicle (AV) systems, especially when AI-based sensing and perception modules are involved. However, due to the black box nature of AI algorithms, it makes closed-loop analysis and synthesis particularly challenging, for example, establishing closed-loop stability and ensuring performance, while they are fundamental to AV safety. To approach this difficulty, this paper aims to develop new modeling, analysis, and synthesis tools for AI-based AVs. Inspired by recent developments in perception error models (PEMs), the focus is shifted from directly modeling AI-based perception processes to characterizing the perception errors they produce. Two key classes of AI-induced perception errors are considered: misdetection and measurement noise. These error patterns are modeled using continuous-time Markov chains and Wiener processes, respectively. By means of that, a PEM-augmented driving model is proposed, with which we are able to establish the closed-loop stability for a class of AI-driven AV systems via stochastic calculus. Furthermore, a performance-guaranteed output feedback control synthesis method is presented, which ensures both stability and satisfactory performance. The method is formulated as a convex optimization problem, allowing for efficient numerical solutions. The results are then applied to an adaptive cruise control (ACC) scenario, demonstrating their effectiveness and robustness despite the corrupted and misleading perception.

eess.SY↗
arXiv2025

Approaches to Analysis and Design of AI-Based Autonomous Vehicles

Artificial intelligence (AI) models are becoming key components in an autonomous vehicle (AV), especially in handling complicated perception tasks. However, closing the loop through AI-based feedback may pose significant risks on reliability of autonomous driving due to very limited understanding about the mechanism of AI-driven perception processes. To overcome it, this paper aims to develop tools for modeling, analysis, and synthesis for a class of AI-based AV; in particular, their closed-loop properties, e.g., stability, robustness, and performance, are rigorously studied in the statistical sense. First, we provide a novel modeling means for the AI-driven perception processes by looking at their error characteristics. Specifically, three fundamental AI-induced perception uncertainties are recognized and modeled by Markov chains, Gaussian processes, and bounded disturbances, respectively. By means of that, the closed-loop stochastic stability (SS) is established in the sense of mean square, and then, an SS control synthesis method is presented within the framework of linear matrix inequalities (LMIs). Besides the SS properties, the robustness and performance of AI-based AVs are discussed in terms of a stochastic guaranteed cost, and criteria are given to test the robustness level of an AV when in the presence of AI-induced uncertainties. Furthermore, the stochastic optimal guaranteed cost control is investigated, and an efficient design procedure is developed innovatively based on LMI techniques and convex optimization. Finally, to illustrate the effectiveness, the developed results are applied to an example of car following control, along with extensive simulation.

eess.SY↗
arXiv2025

Corvid: Improving Multimodal Large Language Models Towards Chain-of-Thought Reasoning

Recent advancements in multimodal large language models (MLLMs) have demonstrated exceptional performance in multimodal perception and understanding. However, leading open-source MLLMs exhibit significant limitations in complex and structured reasoning, particularly in tasks requiring deep reasoning for decision-making and problem-solving. In this work, we present Corvid, an MLLM with enhanced chain-of-thought (CoT) reasoning capabilities. Architecturally, Corvid incorporates a hybrid vision encoder for informative visual representation and a meticulously designed connector (GateMixer) to facilitate cross-modal alignment. To enhance Corvid's CoT reasoning capabilities, we introduce MCoT-Instruct-287K, a high-quality multimodal CoT instruction-following dataset, refined and standardized from diverse public reasoning sources. Leveraging this dataset, we fine-tune Corvid with a two-stage CoT-formatted training approach to progressively enhance its step-by-step reasoning abilities. Furthermore, we propose an effective inference-time scaling strategy that enables Corvid to mitigate over-reasoning and under-reasoning through self-verification. Extensive experiments demonstrate that Corvid outperforms existing o1-like MLLMs and state-of-the-art MLLMs with similar parameter scales, with notable strengths in mathematical reasoning and science problem-solving. Project page: https://mm-vl.github.io/corvid.

cs.CV↗
arXiv2025

Towards a Japanese Full-duplex Spoken Dialogue System

Full-duplex spoken dialogue systems, which can model simultaneous bidirectional features of human conversations such as speech overlaps and backchannels, have attracted significant attention recently. However, the study of full-duplex spoken dialogue systems for the Japanese language has been limited, and the research on their development in Japanese remains scarce. In this paper, we present the first publicly available full-duplex spoken dialogue model in Japanese, which is built upon Moshi, a full-duplex dialogue model in English. Our model is trained through a two-stage process: pre-training on a large-scale spoken dialogue data in Japanese, followed by fine-tuning on high-quality stereo spoken dialogue data. We further enhance the model's performance by incorporating synthetic dialogue data generated by a multi-stream text-to-speech system. Evaluation experiments demonstrate that the trained model outperforms Japanese baseline models in both naturalness and meaningfulness.

cs.CL↗
arXiv2025

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging

Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the merging coefficients, limiting their scalability and generality. In this work, we revisit model merging through the lens of least-squares optimization and show that the optimal merging weights should scale with the amount of task-specific information encoded in each model. Based on this insight, we propose NAN, a simple yet effective method that estimates model merging coefficients via the inverse of parameter norm. NAN is training-free, plug-and-play, and applicable to a wide range of merging strategies. Extensive experiments on show that NAN consistently improves performance of baseline methods.

cs.LG↗
arXiv2025

Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades

This paper presents a pioneering exploration of the mechanisms underlying large foundation models' (LFMs) weights, aiming to simplify AI research. Through extensive observation and analysis on prevailing LFMs, we find that regardless of initialization strategies, their weights predominantly follow a Gaussian distribution, with occasional sharp, inverted T-shaped, or linear patterns. We further discover that the weights share the i.i.d. properties of Gaussian noise, and explore their direct relationship. We find that transformation weights can be derived from Gaussian noise, and they primarily serve to increase the standard deviation of pre-trained weights, with their standard deviation growing with layer depth. In other words, transformation weights broaden the acceptable deviation from the optimal weights, facilitating adaptation to downstream tasks. Building upon the above conclusions, we thoroughly discussed the nature of optimal weights, ultimately concluding that they should exhibit zero-mean, symmetry, and sparsity, with the sparse values being a truncated Gaussian distribution and a few outliers. Our experiments in LFM adaptation and editing demonstrate the effectiveness of these insights. We hope these findings can provide a foundational understanding to pave the way for future advancements in the LFM community.

cs.LG↗
arXiv2024

Multi-UAV Search and Rescue in Wilderness Using Smart Agent-Based Probability Models

The application of Multiple Unmanned Aerial Vehicles (Multi-UAV) in Wilderness Search and Rescue (WiSAR) significantly enhances mission success due to their rapid coverage of search areas from high altitudes and their adaptability to complex terrains. This capability is particularly crucial because time is a critical factor in searching for a lost person in the wilderness; as time passes, survival rates decrease and the search area expands. The probability of success in such searches can be further improved if UAVs leverage terrain features to predict the lost person's position. In this paper, we aim to enhance search missions by proposing a smart agent-based probability model that combines Monte Carlo simulations with an agent strategy list, mimicking the behavior of a lost person in the wildness areas. Furthermore, we develop a distributed Multi-UAV receding horizon search strategy with dynamic partitioning, utilizing the generated probability density model as prior information to prioritize locations where the lost person is most likely to be found. Simulated search experiments across different terrains have been conducted to validate the search efficiency of the proposed methods compared to other benchmark methods.

cs.RO↗
arXiv2024

Autonomous Emergency Braking With Driver-In-The-Loop: Torque Vectoring for Active Learning

Autonomous Emergency Braking (AEB) potentially brings significant improvements in automotive safety due to its ability to autonomously prevent collisions in situations where the driver may not be able to do so. Driven by the poor performance of the state of the art in recent testing, this work provides an online solution to identify critical parameters such as the current and maximum friction coefficients. The method introduced here, namely Torque Vectoring for Active Learning (TVAL), can perform state and parameter estimation whilst following the driver's input. Importantly with less power requirements than normal driving. Our method is designed with a crucial focus on ensuring minimal disruption to the driver, allowing them to maintain full control of the vehicle. Additionally, we exploit a rain/light sensor to drive the observer resampling to maintain estimation certainty across prolonged operation. Then a scheme to modulate TVAL is introduced that considers powertrain efficiency, safety, and availability in an online fashion. Using a high-fidelity vehicle model and drive cycle we demonstrate the functionality of TVAL controller across changing road surfaces where we successfully identify the road surface whenever possible.

eess.SY↗
arXiv2024

A hierarchical control framework for autonomous decision-making systems: Integrating HMDP and MPC

This paper proposes a comprehensive hierarchical control framework for autonomous decision-making arising in robotics and autonomous systems. In a typical hierarchical control architecture, high-level decision making is often characterised by discrete state and decision/control sets. However, a rational decision is usually affected by not only the discrete states of the autonomous system, but also the underlying continuous dynamics even the evolution of its operational environment. This paper proposes a holistic and comprehensive design process and framework for this type of challenging problems, from new modelling and design problem formulation to control design and stability analysis. It addresses the intricate interplay between traditional continuous systems dynamics utilized at the low levels for control design and discrete Markov decision processes (MDP) for facilitating high-level decision making. We model the decision making system in complex environments as a hybrid system consisting of a controlled MDP and autonomous (i.e. uncontrolled) continuous dynamics. Consequently, the new formulation is called as hybrid Markov decision process (HMDP). The design problem is formulated with a focus on ensuring both safety and optimality while taking into account the influence of both the discrete and continuous state variables of different levels. With the help of the model predictive control (MPC) concept, a decision maker design scheme is proposed for the proposed hybrid decision making model. By carefully designing key ingredients involved in this scheme, it is shown that the recursive feasibility and stability of the proposed autonomous decision making scheme are guaranteed. The proposed framework is applied to develop an autonomous lane changing system for intelligent vehicles.

eess.SY↗
arXiv2023

Team Flow at DRC2023: Building Common Ground and Text-based Turn-taking in a Travel Agent Spoken Dialogue System

At the Dialogue Robot Competition 2023 (DRC2023), which was held to improve the capability of dialogue robots, our team developed a system that could build common ground and take more natural turns based on user utterance texts. Our system generated queries for sightseeing spot searches using the common ground and engaged in dialogue while waiting for user comprehension.

cs.CL↗