JingJing Jiang

Jinchegn Hu, Jihao Li, Zhuoran Hou et al.

The problem of robustness in adverse weather conditions is considered a significant challenge for computer vision algorithms in the applicants of autonomous driving. Image rain removal algorithms are a general solution to this problem. They find a deep connection between raindrops/rain-streaks and images by mining the hidden features and restoring information about the rain-free environment based on the powerful representation capabilities of neural networks. However, previous research has focused on architecture innovations and has yet to consider the vulnerability issues that already exist in neural networks. This research gap hints at a potential security threat geared toward the intelligent perception of autonomous driving in the rain. In this paper, we propose a universal rain-removal attack (URA) on the vulnerability of image rain-removal algorithms by generating a non-additive spatial perturbation that significantly reduces the similarity and image quality of scene restoration. Notably, this perturbation is difficult to recognise by humans and is also the same for different target images. Thus, URA could be considered a critical tool for the vulnerability detection of image rain-removal algorithms. It also could be developed as a real-world artificial intelligence attack method. Experimental results show that URA can reduce the scene repair capability by 39.5% and the image generation quality by 26.4%, targeting the state-of-the-art (SOTA) single-image rain-removal algorithms currently available.

Jingjing Jiang, Ziyi Liu, Nanning Zheng

Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such models on limited data often suffers from overfitting and poor generalization issues, leading to a lack of model robustness. In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task. Input robustness refers to the ability of models to defend against visual and linguistic input variations, as well as shortcut learning involved in inputs. Generally, the representations obtained by pretrained VLMs inevitably contain irrelevant and redundant information for a specific downstream task, resulting in statistically spurious correlations and insensitivity to input variations. To encourage representations to converge to a minimal sufficient statistic in multimodal learning, we propose Correlation Information Bottleneck (CIB), which seeks a tradeoff between compression and redundancy in representations by minimizing the mutual information (MI) between inputs and representations while maximizing the MI between outputs and representations. Moreover, we derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations, incorporating different internal correlations that guide models to learn more robust representations and facilitate modality alignment. Extensive experiments consistently demonstrate the effectiveness and superiority of the proposed CIB in terms of input robustness and accuracy.

Jingjing Jiang, Nanning Zheng

Recently, finetuning pretrained Vision-Language Models (VLMs) has been a prevailing paradigm for achieving state-of-the-art performance in Visual Question Answering (VQA). However, as VLMs scale, finetuning full model parameters for a given task in low-resource settings becomes computationally expensive, storage inefficient, and prone to overfitting. Current parameter-efficient tuning methods dramatically reduce the number of tunable parameters, but there still exists a significant performance gap with full finetuning. In this paper, we propose MixPHM, a redundancy-aware parameter-efficient tuning method that outperforms full finetuning in low-resource VQA. Specifically, MixPHM is a lightweight module implemented by multiple PHM-experts in a mixture-of-experts manner. To reduce parameter redundancy, MixPHM reparameterizes expert weights in a low-rank subspace and shares part of the weights inside and across experts. Moreover, based on a quantitative redundancy analysis for adapters, we propose Redundancy Regularization to reduce task-irrelevant redundancy while promoting task-relevant correlation in MixPHM representations. Experiments conducted on VQA v2, GQA, and OK-VQA demonstrate that MixPHM outperforms state-of-the-art parameter-efficient methods and is the only one consistently surpassing full finetuning.

Jincheng Hu, Yang Lin, Jihao Li et al.

Reinforcement learning-based (RL-based) energy management strategy (EMS) is considered a promising solution for the energy management of electric vehicles with multiple power sources. It has been shown to outperform conventional methods in energy management problems regarding energy-saving and real-time performance. However, previous studies have not systematically examined the essential elements of RL-based EMS. This paper presents an empirical analysis of RL-based EMS in a Plug-in Hybrid Electric Vehicle (PHEV) and Fuel Cell Electric Vehicle (FCEV). The empirical analysis is developed in four aspects: algorithm, perception and decision granularity, hyperparameters, and reward function. The results show that the Off-policy algorithm effectively develops a more fuel-efficient solution within the complete driving cycle compared with other algorithms. Improving the perception and decision granularity does not produce a more desirable energy-saving solution but better balances battery power and fuel consumption. The equivalent energy optimization objective based on the instantaneous state of charge (SOC) variation is parameter sensitive and can help RL-EMSs to achieve more efficient energy-cost strategies.

Jincheng Hu, Yang Lin, Liang Chu et al.

The high emission and low energy efficiency caused by internal combustion engines (ICE) have become unacceptable under environmental regulations and the energy crisis. As a promising alternative solution, multi-power source electric vehicles (MPS-EVs) introduce different clean energy systems to improve powertrain efficiency. The energy management strategy (EMS) is a critical technology for MPS-EVs to maximize efficiency, fuel economy, and range. Reinforcement learning (RL) has become an effective methodology for the development of EMS. RL has received continuous attention and research, but there is still a lack of systematic analysis of the design elements of RL-based EMS. To this end, this paper presents an in-depth analysis of the current research on RL-based EMS (RL-EMS) and summarizes the design elements of RL-based EMS. This paper first summarizes the previous applications of RL in EMS from five aspects: algorithm, perception scheme, decision scheme, reward function, and innovative training method. The contribution of advanced algorithms to the training effect is shown, the perception and control schemes in the literature are analyzed in detail, different reward function settings are classified, and innovative training methods with their roles are elaborated. Finally, by comparing the development routes of RL and RL-EMS, this paper identifies the gap between advanced RL solutions and existing RL-EMS. Finally, this paper suggests potential development directions for implementing advanced artificial intelligence (AI) solutions in EMS.

Miao Kang, Shengqi Wang, Sanping Zhou et al.

Motion forecasting plays a crucial role in autonomous driving, with the aim of predicting the future reasonable motions of traffic agents. Most existing methods mainly model the historical interactions between agents and the environment, and predict multi-modal trajectories in a feedforward process, ignoring potential trajectory changes caused by future interactions between agents. In this paper, we propose a novel Future Feedback Interaction Network (FFINet) to aggregate features the current observations and potential future interactions for trajectory prediction. Firstly, we employ different spatial-temporal encoders to embed the decomposed position vectors and the current position of each scene, providing rich features for the subsequent cross-temporal aggregation. Secondly, the relative interaction and cross-temporal aggregation strategies are sequentially adopted to integrate features in the current fusion module, observation interaction module, future feedback module and global fusion module, in which the future feedback module can enable the understanding of pre-action by feeding the influence of preview information to feedforward prediction. Thirdly, the comprehensive interaction features are further fed into final predictor to generate the joint predicted trajectories of multiple agents. Extensive experimental results show that our FFINet achieves the state-of-the-art performance on Argoverse 1 and Argoverse 2 motion forecasting benchmarks.

Shibo Li, Zhuoran Hou, Liang Chu et al.

The multi-source electromechanical coupling makes the energy management of fuel cell electric vehicles (FCEVs) relatively nonlinear and complex especially in the types of 4-wheel-drive (4WD) FCEVs. Accurate state observing for complicated nonlinear system is the basis for fantastic energy managing in FCEVs. Aiming at releasing the energy-saving potential of FCEVs, a novel learning-based robust model predictive control (LRMPC) strategy is proposed for a 4WD FCEV, contributing to suitable power distribution among multiple energy sources. The well-designed strategy based on machine learning (ML) translates the knowledge of the nonlinear system to the explicit controlling scheme with superior robust performance. To start with, ML methods with high regression accuracy and superior generalization ability are trained offline to establish the precise state observer for SOC. Then, explicit data tables for SOC generated by state observer are used for grabbing accurate state changing, whose input features include the vehicle status and the states of vehicle components. To be specific, the vehicle velocity estimation for providing future speed reference is constructed by deep forest. Next, the components including explicit data tables and vehicle velocity estimation are combined with model predictive control (MPC) to release the state-of-the-art energy-saving ability for the multi-freedom system in FCEVs, whose name is LRMPC. At last, the detailed assessment is performed in simulation test to validate the advancing performance of LRMPC. The corresponding results highlight the optimal control effect in energy-saving potential and strong real-time application ability of LRMPC.

Jingjing Jiang, Chao Ma, Xurui Song et al.

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.

Jingjing Jiang, Chongjie Si, Jun Luo et al.

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.

Jingjing Jiang, Ziyi Liu, Yifan Liu et al.

Encouraging progress has been made towards Visual Question Answering (VQA) in recent years, but it is still challenging to enable VQA models to adaptively generalize to out-of-distribution (OOD) samples. Intuitively, recompositions of existing visual concepts (\ie, attributes and objects) can generate unseen compositions in the training set, which will promote VQA models to generalize to OOD samples. In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem. X-GGM leverages graph generative modeling to iteratively generate a relation matrix and node representations for the predefined graph that utilizes attribute-object pairs as nodes. Furthermore, to alleviate the unstable training issue in graph generative modeling, we propose a gradient distribution consistency loss to constrain the data distribution with adversarial perturbations and the generated distribution. The baseline VQA model (LXMERT) trained with the X-GGM scheme achieves state-of-the-art OOD performance on two standard VQA OOD benchmarks, \ie, VQA-CP v2 and GQA-OOD. Extensive ablation studies demonstrate the effectiveness of X-GGM components. Code is available at \url{https://github.com/jingjing12110/x-ggm}.

Yalei Yu, Matthew Coombes, Wen-Hua Chen et al.

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.

Jingjing Jiang

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.

Chongjie Si, Jingjing Jiang, Wei Shen

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.

Atsumoto Ohashi, Shinya Iizuka, Jingjing Jiang et al.

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.

Xue-Fang Wang, Jingjing Jiang, Wen-Hua Chen

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.

Chongjie Si, Kangtao Lv, Jingjing Jiang et al.

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.

Xurui Song, Shuo Huai, JingJing Jiang et al.

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by this reasoning remains a critical but unverified assumption. To investigate this, we build DriveMind, a large-scale driving Visual Question Answering (VQA) corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) and evaluate them with nuPlan's metrics. Our results, unfortunately, indicate a consistent causal disconnect in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we also introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the causal fidelity of future models.

Tao Yan, Zheyu Zhang, Jingjing Jiang et al.

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.

Tao Yan, Zheyu Zhang, Jingjing Jiang et al.

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.

Ryu Hirai, Shinya Iizuka, Haruhisa Iseno et al.

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.

Jingjing Jiang, Ziyi Liu, Nanning Zheng

Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content. From the perspective of video understanding, a good VideoQA framework needs to understand the video content at different semantic levels and flexibly integrate the diverse video content to distill question-related content. To this end, we propose a Lightweight Visual-Linguistic Reasoning framework named LiVLR. Specifically, LiVLR first utilizes the graph-based Visual and Linguistic Encoders to obtain multi-grained visual and linguistic representations. Subsequently, the obtained representations are integrated with the devised Diversity-aware Visual-Linguistic Reasoning module (DaVL). The DaVL considers the difference between the different types of representations and can flexibly adjust the importance of different types of representations when generating the question-related joint representation, which is an effective and general representation integration method. The proposed LiVLR is lightweight and shows its performance advantage on two VideoQA benchmarks, MRSVTT-QA and KnowIT VQA. Extensive ablation studies demonstrate the effectiveness of LiVLR key components.

Hui Chen, Jingjing Jiang, Nanning Zheng

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.