Chunxiao Liu

Xuan Yang, Hao Xu, Tingfeng Hui et al.

Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations covering both ideal rational patterns and heterogeneous non-ideal behaviors across single-turn and multi-turn dialogues. We conduct comprehensive evaluations on 19 widely adopted open-source and proprietary LLMs using our benchmark. Experimental results reveal that no tested LLMs achieve an overall success rate above 40%, and nearly all of them experience noticeable performance drops when facing more complicated non-ideal user inputs. Our code and data is available at https://github.com/Miaow-Lab/RUT-Bench.

Ezequiel Perez-Zarate, Oscar Ramos-Soto, Chunxiao Liu et al.

Low-light image enhancement is an important task in computer vision, essential for improving the visibility and quality of images captured in non-optimal lighting conditions. Inadequate illumination can lead to significant information loss and poor image quality, impacting various applications such as surveillance. photography, or even autonomous driving. In this regard, automated methods have been developed to automatically adjust illumination in the image for a better visual perception. Current enhancement techniques often use specific datasets to enhance low-light images, but still present challenges when adapting to diverse real-world conditions, where illumination degradation may be localized to specific regions. To address this challenge, the Adaptive Light Enhancement Network (ALEN) is introduced, whose main approach is the use of a classification mechanism to determine whether local or global illumination enhancement is required. Subsequently, estimator networks adjust illumination based on this classification and simultaneously enhance color fidelity. ALEN integrates the Light Classification Network (LCNet) for illuminance categorization, complemented by the Single-Channel Network (SCNet), and Multi-Channel Network (MCNet) for precise estimation of illumination and color, respectively. Extensive experiments on publicly available datasets for low-light conditions were carried out to underscore ALEN's robust generalization capabilities, demonstrating superior performance in both quantitative metrics and qualitative assessments when compared to recent state-of-the-art methods. The ALEN not only enhances image quality in terms of visual perception but also represents an advancement in high-level vision tasks, such as semantic segmentation, as presented in this work. The code of this method is available at https://github.com/xingyumex/ALEN

Ziyang Gong, Zehang Luo, Anke Tang et al.

Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However, existing embodied brain in training a unified model over diverse embodiments frequently triggers long-tail data, gradient interference, and catastrophic forgetting, making it notoriously difficult to balance universal generalization with domain-specific proficiency. In this report, we introduce ACE-Brain-0, a generalist foundation brain that unifies spatial reasoning, autonomous driving, and embodied manipulation within a single multimodal large language model~(MLLM). Our key insight is that spatial intelligence serves as a universal scaffold across diverse physical embodiments: although vehicles, robots, and UAVs differ drastically in morphology, they share a common need for modeling 3D mental space, making spatial cognition a natural, domain-agnostic foundation for cross-embodiment transfer. Building on this insight, we propose the Scaffold-Specialize-Reconcile~(SSR) paradigm, which first establishes a shared spatial foundation, then cultivates domain-specialized experts, and finally harmonizes them through data-free model merging. Furthermore, we adopt Group Relative Policy Optimization~(GRPO) to strengthen the model's comprehensive capability. Extensive experiments demonstrate that ACE-Brain-0 achieves competitive and even state-of-the-art performance across 24 spatial and embodiment-related benchmarks.

Yijing Tu, Shaojin Wu, Mengqi Huang et al.

While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration costs and lack temporal guidance. To address these structural bottlenecks, we propose shifting the focus to streaming video generation. We identify that its chunk-level synthesis and few denoising steps are intrinsically suited for TTS, significantly lowering computational overhead while enabling fine-grained temporal control. Driven by this insight, we introduced Stream-T1, a pioneering comprehensive TTS framework exclusively tailored for streaming video generation. Specifically, Stream-T1 is composed of three units: (1) Stream -Scaled Noise Propagation, which actively refines the initial latent noise of the generating chunk using historically proven, high-quality previous chunk noise, effectively establishes temporal dependency and utilizing the historical Gaussian prior to guide the current generation; (2) Stream -Scaled Reward Pruning, which comprehensively evaluates generated candidates to strike an optimal balance between local spatial aesthetics and global temporal coherence by integrating immediate short-term assessments with sliding-window-based long-term evaluations; (3) Stream-Scaled Memory Sinking, which dynamically routes the context evicted from KV-cache into distinct updating pathways guided by the reward feedback, ensuring that previously generated visual information effectively anchors and guides the subsequent video stream. Evaluated on both 5s and 30s comprehensive video benchmarks, Stream-T1 demonstrates profound superiority, significantly improving temporal consistency, motion smoothness, and frame-level visual quality.

Tingfeng Hui, Hao Xu, Pengyu Zhu et al.

Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge of adaptive replanning under spatio-temporal dynamics largely unexplored. We introduce STT-Arena (Spatio-Temporal Tool-Use Arena), a benchmark of 227 high-quality interactive tasks spanning nine spatio-temporal conflict types and four solvability levels. Each task is grounded in a realistic, executable environment equipped with injected spatio-temporal triggers that can abruptly invalidate an ongoing plan, forcing the model to detect the state shift and construct a revised execution strategy. Extensive evaluation of frontier LLMs reveals that even the SOTA proprietary models, including Claude-4.6-Opus, achieves less than 40\% overall accuracies, highlighting the fundamental difficulty of spatio-temporal dynamic reasoning. Systematic analysis of failure trajectories uncovers three recurring error modes of existing models: Stale-State Execution, Misdiagnosis of Dynamic Triggers, and Missing Post-Adaptation Verification. Guided by these findings, we propose an iterative trajectory refinement technique that eliminates these failure patterns from training data, and combine it with online RL to produce STT-Agent-4B which outperforms frontier LLMs on STT-Arena.

Xuanjin Jin, Chendong Zeng, Shengfa Zhu et al.

Uncertainties in dynamic road environments pose significant challenges for behavior and trajectory planning in autonomous driving. This paper introduces Hi-Drive, a hierarchical planning algorithm addressing uncertainties at both behavior and trajectory levels using a hierarchical Partially Observable Markov Decision Process (POMDP) formulation. Hi-Drive employs driver models to represent uncertain behavioral intentions of other vehicles and uses their parameters to infer hidden driving styles. By treating driver models as high-level decision-making actions, our approach effectively manages the exponential complexity inherent in POMDPs. To further enhance safety and robustness, Hi-Drive integrates a trajectory optimization based on importance sampling, refining trajectories using a comprehensive analysis of critical agents. Evaluations on real-world urban driving datasets demonstrate that Hi-Drive significantly outperforms state-of-the-art planning-based and learning-based methods across diverse urban driving situations in real-world benchmarks.

Yuenan Hou, Zheng Ma, Chunxiao Liu et al.

Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network. Contemporary methods typically perform iterative pruning procedure from the original over-parameterized model, which is both tedious and expensive especially when the pruning is aggressive. In this paper, we propose a simple yet effective channel pruning technique, termed network Pruning via rEsource rEalLocation (PEEL), to quickly produce a desired slim model with negligible cost. Specifically, PEEL first constructs a predefined backbone and then conducts resource reallocation on it to shift parameters from less informative layers to more important layers in one round, thus amplifying the positive effect of these informative layers. To demonstrate the effectiveness of PEEL , we perform extensive experiments on ImageNet with ResNet-18, ResNet-50, MobileNetV2, MobileNetV3-small and EfficientNet-B0. Experimental results show that structures uncovered by PEEL exhibit competitive performance with state-of-the-art pruning algorithms under various pruning settings. Our code is available at https://github.com/cardwing/Codes-for-PEEL.

Yuenan Hou, Zheng Ma, Chunxiao Liu et al.

We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation. In this work, we explore a novel knowledge distillation (KD) approach that can transfer 'knowledge' on scene structure more effectively from a teacher to a student model. Our method is known as Inter-Region Affinity KD (IntRA-KD). It decomposes a given road scene image into different regions and represents each region as a node in a graph. An inter-region affinity graph is then formed by establishing pairwise relationships between nodes based on their similarity in feature distribution. To learn structural knowledge from the teacher network, the student is required to match the graph generated by the teacher. The proposed method shows promising results on three large-scale road marking segmentation benchmarks, i.e., ApolloScape, CULane and LLAMAS, by taking various lightweight models as students and ResNet-101 as the teacher. IntRA-KD consistently brings higher performance gains on all lightweight models, compared to previous distillation methods. Our code is available at https://github.com/cardwing/Codes-for-IntRA-KD.

Chunxiao Liu, Zhendong Mao, Tianzhu Zhang et al.

Image-text matching has received growing interest since it bridges vision and language. The key challenge lies in how to learn correspondence between image and text. Existing works learn coarse correspondence based on object co-occurrence statistics, while failing to learn fine-grained phrase correspondence. In this paper, we present a novel Graph Structured Matching Network (GSMN) to learn fine-grained correspondence. The GSMN explicitly models object, relation and attribute as a structured phrase, which not only allows to learn correspondence of object, relation and attribute separately, but also benefits to learn fine-grained correspondence of structured phrase. This is achieved by node-level matching and structure-level matching. The node-level matching associates each node with its relevant nodes from another modality, where the node can be object, relation or attribute. The associated nodes then jointly infer fine-grained correspondence by fusing neighborhood associations at structure-level matching. Comprehensive experiments show that GSMN outperforms state-of-the-art methods on benchmarks, with relative Recall@1 improvements of nearly 7% and 2% on Flickr30K and MSCOCO, respectively. Code will be released at: https://github.com/CrossmodalGroup/GSMN.

Shoukang Hu, Sirui Xie, Hehui Zheng et al.

If NAS methods are solutions, what is the problem? Most existing NAS methods require two-stage parameter optimization. However, performance of the same architecture in the two stages correlates poorly. In this work, we propose a new problem definition for NAS, task-specific end-to-end, based on this observation. We argue that given a computer vision task for which a NAS method is expected, this definition can reduce the vaguely-defined NAS evaluation to i) accuracy of this task and ii) the total computation consumed to finally obtain a model with satisfying accuracy. Seeing that most existing methods do not solve this problem directly, we propose DSNAS, an efficient differentiable NAS framework that simultaneously optimizes architecture and parameters with a low-biased Monte Carlo estimate. Child networks derived from DSNAS can be deployed directly without parameter retraining. Comparing with two-stage methods, DSNAS successfully discovers networks with comparable accuracy (74.4%) on ImageNet in 420 GPU hours, reducing the total time by more than 34%. Our implementation is available at https://github.com/SNAS-Series/SNAS-Series.

Yuenan Hou, Zheng Ma, Chunxiao Liu et al.

Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations. Without learning from much richer context, these models often fail in challenging scenarios, e.g., severe occlusion, ambiguous lanes, and poor lighting conditions. In this paper, we present a novel knowledge distillation approach, i.e., Self Attention Distillation (SAD), which allows a model to learn from itself and gains substantial improvement without any additional supervision or labels. Specifically, we observe that attention maps extracted from a model trained to a reasonable level would encode rich contextual information. The valuable contextual information can be used as a form of 'free' supervision for further representation learning through performing topdown and layer-wise attention distillation within the network itself. SAD can be easily incorporated in any feedforward convolutional neural networks (CNN) and does not increase the inference time. We validate SAD on three popular lane detection benchmarks (TuSimple, CULane and BDD100K) using lightweight models such as ENet, ResNet-18 and ResNet-34. The lightest model, ENet-SAD, performs comparatively or even surpasses existing algorithms. Notably, ENet-SAD has 20 x fewer parameters and runs 10 x faster compared to the state-of-the-art SCNN, while still achieving compelling performance in all benchmarks. Our code is available at https://github.com/cardwing/Codes-for-Lane-Detection.

Sirui Xie, Hehui Zheng, Chunxiao Liu et al.

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline. In this work, NAS is reformulated as an optimization problem on parameters of a joint distribution for the search space in a cell. To leverage the gradient information in generic differentiable loss for architecture search, a novel search gradient is proposed. We prove that this search gradient optimizes the same objective as reinforcement-learning-based NAS, but assigns credits to structural decisions more efficiently. This credit assignment is further augmented with locally decomposable reward to enforce a resource-efficient constraint. In experiments on CIFAR-10, SNAS takes less epochs to find a cell architecture with state-of-the-art accuracy than non-differentiable evolution-based and reinforcement-learning-based NAS, which is also transferable to ImageNet. It is also shown that child networks of SNAS can maintain the validation accuracy in searching, with which attention-based NAS requires parameter retraining to compete, exhibiting potentials to stride towards efficient NAS on big datasets. We have released our implementation at https://github.com/SNAS-Series/SNAS-Series.

Jinrong Zhang, Penghui Wang, Chunxiao Liu et al.

To break through the limitations of pre-training models on fixed categories, Open-Set Object Detection (OSOD) and Open-Set Segmentation (OSS) have attracted a surge of interest from researchers. Inspired by large language models, mainstream OSOD and OSS methods generally utilize text as a prompt, achieving remarkable performance. Following SAM paradigm, some researchers use visual prompts, such as points, boxes, and masks that cover detection or segmentation targets. Despite these two prompt paradigms exhibit excellent performance, they also reveal inherent limitations. On the one hand, it is difficult to accurately describe characteristics of specialized category using textual description. On the other hand, existing visual prompt paradigms heavily rely on multi-round human interaction, which hinders them being applied to fully automated pipeline. To address the above issues, we propose a novel prompt paradigm in OSOD and OSS, that is, \textbf{Image Prompt Paradigm}. This brand new prompt paradigm enables to detect or segment specialized categories without multi-round human intervention. To achieve this goal, the proposed image prompt paradigm uses just a few image instances as prompts, and we propose a novel framework named \textbf{MI Grounding} for this new paradigm. In this framework, high-quality image prompts are automatically encoded, selected and fused, achieving the single-stage and non-interactive inference. We conduct extensive experiments on public datasets, showing that MI Grounding achieves competitive performance on OSOD and OSS benchmarks compared to text prompt paradigm methods and visual prompt paradigm methods. Moreover, MI Grounding can greatly outperform existing method on our constructed specialized ADR50K dataset.

Xinhua Wang, Caibo Feng, Xiangjun Fu et al.

We propose an innovative enhancement to the Mamba framework by increasing the Hausdorff dimension of its scanning pattern through a novel Hilbert Selective Scan mechanism. This mechanism explores the feature space more effectively, capturing intricate fine-scale details and improving overall coverage. As a result, it mitigates information inconsistencies while refining spatial locality to better capture subtle local interactions without sacrificing the model's ability to handle long-range dependencies. Extensive experiments on publicly available benchmarks demonstrate that our approach significantly improves both the quantitative metrics and qualitative visual fidelity of existing Mamba-based low-light image enhancement methods, all while reducing computational resource consumption and shortening inference time. We believe that this refined strategy not only advances the state-of-the-art in low-light image enhancement but also holds promise for broader applications in fields that leverage Mamba-based techniques.

Zhenghao Peng, Quanyi Li, Ka Ming Hui et al.

Self-Driven Particles (SDP) describe a category of multi-agent systems common in everyday life, such as flocking birds and traffic flows. In a SDP system, each agent pursues its own goal and constantly changes its cooperative or competitive behaviors with its nearby agents. Manually designing the controllers for such SDP system is time-consuming, while the resulting emergent behaviors are often not realistic nor generalizable. Thus the realistic simulation of SDP systems remains challenging. Reinforcement learning provides an appealing alternative for automating the development of the controller for SDP. However, previous multi-agent reinforcement learning (MARL) methods define the agents to be teammates or enemies before hand, which fail to capture the essence of SDP where the role of each agent varies to be cooperative or competitive even within one episode. To simulate SDP with MARL, a key challenge is to coordinate agents' behaviors while still maximizing individual objectives. Taking traffic simulation as the testing bed, in this work we develop a novel MARL method called Coordinated Policy Optimization (CoPO), which incorporates social psychology principle to learn neural controller for SDP. Experiments show that the proposed method can achieve superior performance compared to MARL baselines in various metrics. Noticeably the trained vehicles exhibit complex and diverse social behaviors that improve performance and safety of the population as a whole. Demo video and source code are available at: https://decisionforce.github.io/CoPO/

Zhenghao Peng, Quanyi Li, Chunxiao Liu et al.

When learning common skills like driving, beginners usually have domain experts standing by to ensure the safety of the learning process. We formulate such learning scheme under the Expert-in-the-loop Reinforcement Learning where a guardian is introduced to safeguard the exploration of the learning agent. While allowing the sufficient exploration in the uncertain environment, the guardian intervenes under dangerous situations and demonstrates the correct actions to avoid potential accidents. Thus ERL enables both exploration and expert's partial demonstration as two training sources. Following such a setting, we develop a novel Expert Guided Policy Optimization (EGPO) method which integrates the guardian in the loop of reinforcement learning. The guardian is composed of an expert policy to generate demonstration and a switch function to decide when to intervene. Particularly, a constrained optimization technique is used to tackle the trivial solution that the agent deliberately behaves dangerously to deceive the expert into taking over. Offline RL technique is further used to learn from the partial demonstration generated by the expert. Safe driving experiments show that our method achieves superior training and test-time safety, outperforms baselines with a substantial margin in sample efficiency, and preserves the generalizabiliy to unseen environments in test-time. Demo video and source code are available at: https://decisionforce.github.io/EGPO/

Xiaoxu Cao, Linyi Gu, JunChen Mu et al.

Autonomous Underwater Vehicle-Manipulator systems (AUVMS) is a new tool for ocean exploration, the AUVMS path planning problem is addressed in this paper. AUVMS is a high dimension system with a large difference in inertia distribution, also it works in a complex environment with obstacles. By integrating the rapidly-exploring random tree(RRT) algorithm with the AUVMS kinematics model, the proposed RRTAUVMS algorithm could randomly sample in the configuration space(C-Space), and also grow the tree directly towards the workspace goal in the task space. The RRTAUVMS can also deal with the redundant mapping of workspace planning goal and configuration space goal. Compared with the traditional RRT algorithm, the efficiency of the AUVMS path planning can be significantly improved.

Quanyi Li, Zhenghao Peng, Qihang Zhang et al.

Over the past few years there is a growing interest in the learning-based self driving system. To ensure safety, such systems are first developed and validated in simulators before being deployed in the real world. However, most of the existing driving simulators only contain a fixed set of scenes and a limited number of configurable settings. That might easily cause the overfitting issue for the learning-based driving systems as well as the lack of their generalization ability to unseen scenarios. To better evaluate and improve the generalization of end-to-end driving, we introduce an open-ended and highly configurable driving simulator called PGDrive, following a key feature of procedural generation. Diverse road networks are first generated by the proposed generation algorithm via sampling from elementary road blocks. Then they are turned into interactive training environments where traffic flows of nearby vehicles with realistic kinematics are rendered. We validate that training with the increasing number of procedurally generated scenes significantly improves the generalization of the agent across scenarios of different traffic densities and road networks. Many applications such as multi-agent traffic simulation and safe driving benchmark can be further built upon the simulator. To facilitate the joint research effort of end-to-end driving, we release the simulator and pretrained models at https://decisionforce.github.io/pgdrive

Xi Zhu, Zhendong Mao, Chunxiao Liu et al.

Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency answers (e.g., yellow) ignoring image contents. Existing approaches tackle this problem by creating delicate models or introducing additional visual annotations to reduce question dependency while strengthening image dependency. However, they are still subject to the language prior problem since the data biases have not been even alleviated. In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and propose a self-supervised auxiliary task to utilize the balanced data to assist the base VQA model to overcome language priors. Our method can compensate for the data biases by generating balanced data without introducing external annotations. Experimental results show that our method can significantly outperform the state-of-the-art, improving the overall accuracy from 49.50% to 57.59% on the most commonly used benchmark VQA-CP v2. In other words, we can increase the performance of annotation-based methods by 16% without using external annotations.

Hang Yang, Shan Jiang, Xinge Zhu et al.

Generic object detection has been immensely promoted by the development of deep convolutional neural networks in the past decade. However, in the domain shift circumstance, the changes in weather, illumination, etc., often cause domain gap, and thus performance drops substantially when detecting objects from one domain to another. Existing methods on this task usually draw attention on the high-level alignment based on the whole image or object of interest, which naturally, cannot fully utilize the fine-grained channel information. In this paper, we realize adaptation from a thoroughly different perspective, i.e., channel-wise alignment. Motivated by the finding that each channel focuses on a specific pattern (e.g., on special semantic regions, such as car), we aim to align the distribution of source and target domain on the channel level, which is finer for integration between discrepant domains. Our method mainly consists of self channel-wise and cross channel-wise alignment. These two parts explore the inner-relation and cross-relation of attention regions implicitly from the view of channels. Further more, we also propose a RPN domain classifier module to obtain a domain-invariant RPN network. Extensive experiments show that the proposed method performs notably better than existing methods with about 5% improvement under various domain-shift settings. Experiments on different task (e.g. instance segmentation) also demonstrate its good scalability.

Sirui Xie, Shoukang Hu, Xinjiang Wang et al.

Controversy exists on whether differentiable neural architecture search methods discover wiring topology effectively. To understand how wiring topology evolves, we study the underlying mechanism of several existing differentiable NAS frameworks. Our investigation is motivated by three observed searching patterns of differentiable NAS: 1) they search by growing instead of pruning; 2) wider networks are more preferred than deeper ones; 3) no edges are selected in bi-level optimization. To anatomize these phenomena, we propose a unified view on searching algorithms of existing frameworks, transferring the global optimization to local cost minimization. Based on this reformulation, we conduct empirical and theoretical analyses, revealing implicit inductive biases in the cost's assignment mechanism and evolution dynamics that cause the observed phenomena. These biases indicate strong discrimination towards certain topologies. To this end, we pose questions that future differentiable methods for neural wiring discovery need to confront, hoping to evoke a discussion and rethinking on how much bias has been enforced implicitly in existing NAS methods.

Liming Jiang, Changxu Zhang, Mingyang Huang et al.

We introduce a simple and versatile framework for image-to-image translation. We unearth the importance of normalization layers, and provide a carefully designed two-stream generative model with newly proposed feature transformations in a coarse-to-fine fashion. This allows multi-scale semantic structure information and style representation to be effectively captured and fused by the network, permitting our method to scale to various tasks in both unsupervised and supervised settings. No additional constraints (e.g., cycle consistency) are needed, contributing to a very clean and simple method. Multi-modal image synthesis with arbitrary style control is made possible. A systematic study compares the proposed method with several state-of-the-art task-specific baselines, verifying its effectiveness in both perceptual quality and quantitative evaluations.

Junning Huang, Sirui Xie, Jiankai Sun et al.

Autonomous driving systems have a pipeline of perception, decision, planning, and control. The decision module processes information from the perception module and directs the execution of downstream planning and control modules. On the other hand, the recent success of deep learning suggests that this pipeline could be replaced by end-to-end neural control policies, however, safety cannot be well guaranteed for the data-driven neural networks. In this work, we propose a hybrid framework to learn neural decisions in the classical modular pipeline through end-to-end imitation learning. This hybrid framework can preserve the merits of the classical pipeline such as the strict enforcement of physical and logical constraints while learning complex driving decisions from data. To circumvent the ambiguous annotation of human driving decisions, our method learns high-level driving decisions by imitating low-level control behaviors. We show in the simulation experiments that our modular driving agent can generalize its driving decision and control to various complex scenarios where the rule-based programs fail. It can also generate smoother and safer driving trajectories than end-to-end neural policies.

Chunxiao Liu, Zhendong Mao, An-An Liu et al.

Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing methods achieve this goal by representing the shared semantic as a weighted combination of all the fragments (image regions or text words), where fragments relevant to the shared semantic obtain more attention, otherwise less. However, despite relevant ones contribute more to the shared semantic, irrelevant ones will more or less disturb it, and thus will lead to semantic misalignment in the correlation phase. To address this issue, we present a novel Bidirectional Focal Attention Network (BFAN), which not only allows to attend to relevant fragments but also diverts all the attention into these relevant fragments to concentrate on them. The main difference with existing works is they mostly focus on learning attention weight while our BFAN focus on eliminating irrelevant fragments from the shared semantic. The focal attention is achieved by pre-assigning attention based on inter-modality relation, identifying relevant fragments based on intra-modality relation and reassigning attention. Furthermore, the focal attention is jointly applied in both image-to-text and text-to-image directions, which enables to avoid preference to long text or complex image. Experiments show our simple but effective framework significantly outperforms state-of-the-art, with relative Recall@1 gains of 2.2% on both Flicr30K and MSCOCO benchmarks.

Sirui Xie, Junning Huang, Lanxin Lei et al.

Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for tasks with either sparse rewards or long term information. In this work, we introduce a novel on-policy temporally consistent exploration strategy - Neural Adaptive Dropout Policy Exploration (NADPEx) - for deep reinforcement learning agents. Modeled as a global random variable for conditional distribution, dropout is incorporated to reinforcement learning policies, equipping them with inherent temporal consistency, even when the reward signals are sparse. Two factors, gradients' alignment with the objective and KL constraint in policy space, are discussed to guarantee NADPEx policy's stable improvement. Our experiments demonstrate that NADPEx solves tasks with sparse reward while naive exploration and parameter noise fail. It yields as well or even faster convergence in the standard mujoco benchmark for continuous control.

Yuenan Hou, Zheng Ma, Chunxiao Liu et al.

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, these methods are susceptible to the presence of sharp road curves, challenging traffic conditions, strong shadows, and severe lighting changes. In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction. Specifically, we train our steering angle predictive model by distilling multi-layer knowledge from multiple heterogeneous auxiliary networks that perform related but different tasks, e.g., image segmentation or optical flow estimation. As opposed to multi-task learning, our method does not require expensive annotations of related tasks on the target set. This is made possible by applying contemporary off-the-shelf networks on the target set and mimicking their features in different layers after transformation. The auxiliary networks are discarded after training without affecting the runtime efficiency of our model. Our approach achieves a new state-of-the-art on Udacity and Comma.ai, outperforming the previous best by a large margin of 12.8% and 52.1%, respectively. Encouraging results are also shown on Berkeley Deep Drive (BDD) dataset.