Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approaches that scale offline RL either rely heavily on expert trajectories or struggle to generalize to diverse unseen tasks. Inspired by the excellent generalization of world model in conditional video generation, we explore the potential of image observation-based world model for scaling offline RL and enhancing generalization on novel tasks. In this paper, we introduce JOWA: Jointly-Optimized World-Action model, an offline model-based RL agent pretrained on multiple Atari games to learn general-purpose representation and decision-making ability. Our method jointly optimizes a world-action model through shared transformer backbone, which stabilize temporal difference learning with large models during pretraining. Moreover, we propose an provably efficient and parallelizable planning algorithm to compensate for the Q-value estimation error and thus search out better policies. Experimental results indicate that our largest agent, with 150 million parameters, achieves 78.9% human-level performance on pretrained games using only 10% subsampled offline data, outperforming existing state-of-the-art large-scale offline RL baselines by 31.6% on averange. Furthermore, JOWA scales favorably with model capacity and can sample-efficiently transfer to novel games using only 5k offline fine-tuning data corresponding to about 4 trajectories per game, which demonstrates superior generalization of JOWA. We will release codes at https://github.com/CJReinforce/JOWA.

MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving

Vision-language models (VLMs) serve as general-purpose end-to-end models in autonomous driving, performing subtasks such as prediction, planning, and perception through question-and-answer interactions. However, most existing methods rely on computationally expensive visual encoders and large language models (LLMs), making them difficult to deploy in real-world scenarios and real-time applications. Meanwhile, most existing VLMs lack the ability to process multiple images, making it difficult to adapt to multi-camera perception in autonomous driving. To address these issues, we propose a novel framework called MiniDrive, which incorporates our proposed Feature Engineering Mixture of Experts (FE-MoE) module and Dynamic Instruction Adapter (DI-Adapter). The FE-MoE effectively maps 2D features into visual token embeddings before being input into the language model. The DI-Adapter enables the visual token embeddings to dynamically change with the instruction text embeddings, resolving the issue of static visual token embeddings for the same image in previous approaches. Compared to previous works, MiniDrive achieves state-of-the-art performance in terms of parameter size, floating point operations, and response efficiency, with the smallest version containing only 83M parameters.

MambaOcc: Visual State Space Model for BEV-based Occupancy Prediction with Local Adaptive Reordering

Occupancy prediction has attracted intensive attention and shown great superiority in the development of autonomous driving systems. The fine-grained environmental representation brought by occupancy prediction in terms of both geometry and semantic information has facilitated the general perception and safe planning under open scenarios. However, it also brings high computation costs and heavy parameters in existing works that utilize voxel-based 3d dense representation and Transformer-based quadratic attention. To address these challenges, in this paper, we propose a Mamba-based occupancy prediction method (MambaOcc) adopting BEV features to ease the burden of 3D scenario representation, and linear Mamba-style attention to achieve efficient long-range perception. Besides, to address the sensitivity of Mamba to sequence order, we propose a local adaptive reordering (LAR) mechanism with deformable convolution and design a hybrid BEV encoder comprised of convolution layers and Mamba. Extensive experiments on the Occ3D-nuScenes dataset demonstrate that MambaOcc achieves state-of-the-art performance in terms of both accuracy and computational efficiency. For example, compared to FlashOcc, MambaOcc delivers superior results while reducing the number of parameters by 42\% and computational costs by 39\%. Code will be available at https://github.com/Hub-Tian/MambaOcc.

Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models

Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents' past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features into a form that LLMs understand. On this basis, we innovatively explore LLMs' powerful comprehension abilities to capture a spectrum of high-level scene knowledge and interactive information. Emulating the human-like lane focus cognitive function and enhancing Traj-LLM's scene comprehension, we introduce lane-aware probabilistic learning powered by the pioneering Mamba module. Finally, a multi-modal Laplace decoder is designed to achieve scene-compliant multi-modal predictions. Extensive experiments manifest that Traj-LLM, fortified by LLMs' strong prior knowledge and understanding prowess, together with lane-aware probability learning, outstrips state-of-the-art methods across evaluation metrics. Moreover, the few-shot analysis further substantiates Traj-LLM's performance, wherein with just 50% of the dataset, it outperforms the majority of benchmarks relying on complete data utilization. This study explores equipping the trajectory prediction task with advanced capabilities inherent in LLMs, furnishing a more universal and adaptable solution for forecasting agent motion in a new way.

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

Recent trends in Large Vision Language Models (LVLMs) research have been increasingly focusing on advancing beyond general image understanding towards more nuanced, object-level referential comprehension. In this paper, we present and delve into the self-consistency capability of LVLMs, a crucial aspect that reflects the models' ability to both generate informative captions for specific objects and subsequently utilize these captions to accurately re-identify the objects in a closed-loop process. This capability significantly mirrors the precision and reliability of fine-grained visual-language understanding. Our findings reveal that the self-consistency level of existing LVLMs falls short of expectations, posing limitations on their practical applicability and potential. To address this gap, we introduce a novel fine-tuning paradigm named Self-Consistency Tuning (SC-Tune). It features the synergistic learning of a cyclic describer-locator system. This paradigm is not only data-efficient but also exhibits generalizability across multiple LVLMs. Through extensive experiments, we demonstrate that SC-Tune significantly elevates performance across a spectrum of object-level vision-language benchmarks and maintains competitive or improved performance on image-level vision-language benchmarks. Both our model and code will be publicly available at https://github.com/ivattyue/SC-Tune.

BjTT: A Large-scale Multimodal Dataset for Traffic Prediction

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) limited performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation, and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.

RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences

Preference-based Reinforcement Learning (PbRL) avoids the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL algorithms over-reliance on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method incorporates a sample selection-based discriminator to dynamically filter denoised preferences for robust training. To mitigate the accumulated error caused by incorrect selection, we propose to warm start the reward model, which additionally bridges the performance gap during transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the current state-of-the-art PbRL method. Ablation studies further demonstrate that the warm start is crucial for both robustness and feedback-efficiency in limited-feedback cases.

Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning

Kriging aims at estimating the attributes of unsampled geo-locations from observations in the spatial vicinity or physical connections, which helps mitigate skewed monitoring caused by under-deployed sensors. Existing works assume that neighbors' information offers the basis for estimating the attributes of the unobserved target while ignoring non-neighbors. However, non-neighbors could also offer constructive information, and neighbors could also be misleading. To this end, we propose ``Contrastive-Prototypical'' self-supervised learning for Kriging (KCP) to refine valuable information from neighbors and recycle the one from non-neighbors. As a pre-trained paradigm, we conduct the Kriging task from a new perspective of representation: we aim to first learn robust and general representations and then recover attributes from representations. A neighboring contrastive module is designed that coarsely learns the representations by narrowing the representation distance between the target and its neighbors while pushing away the non-neighbors. In parallel, a prototypical module is introduced to identify similar representations via exchanged prediction, thus refining the misleading neighbors and recycling the useful non-neighbors from the neighboring contrast component. As a result, not all the neighbors and some of the non-neighbors will be used to infer the target. To encourage the two modules above to learn general and robust representations, we design an adaptive augmentation module that incorporates data-driven attribute augmentation and centrality-based topology augmentation over the spatiotemporal Kriging graph data. Extensive experiments on real-world datasets demonstrate the superior performance of KCP compared to its peers with 6% improvements and exceptional transferability and robustness. The code is available at https://github.com/bonaldli/KCP

ChatTraffic: Text-to-Traffic Generation via Diffusion Model

Traffic prediction is one of the most significant foundations in Intelligent Transportation Systems (ITS). Traditional traffic prediction methods rely only on historical traffic data to predict traffic trends and face two main challenges. 1) insensitivity to unusual events. 2) poor performance in long-term prediction. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation and name the task Text-to-Traffic Generation (TTG). The key challenge of the TTG task is how to associate text with the spatial structure of the road network and traffic data for generating traffic situations. To this end, we propose ChatTraffic, the first diffusion model for text-to-traffic generation. To guarantee the consistency between synthetic and real data, we augment a diffusion model with the Graph Convolutional Network (GCN) to extract spatial correlations of traffic data. In addition, we construct a large dataset containing text-traffic pairs for the TTG task. We benchmarked our model qualitatively and quantitatively on the released dataset. The experimental results indicate that ChatTraffic can generate realistic traffic situations from the text. Our code and dataset are available at https://github.com/ChyaZhang/ChatTraffic.

Multi-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance

The accurate and efficient vessel draft reading (VDR) is an important component of intelligent maritime surveillance, which could be exploited to assist in judging whether the vessel is normally loaded or overloaded. The computer vision technique with an excellent price-to-performance ratio has become a popular medium to estimate vessel draft depth. However, the traditional estimation methods easily suffer from several limitations, such as sensitivity to low-quality images, high computational cost, etc. In this work, we propose a multi-task learning-enabled computational method (termed MTL-VDR) for generating highly reliable VDR. In particular, our MTL-VDR mainly consists of four components, i.e., draft mark detection, draft scale recognition, vessel/water segmentation, and final draft depth estimation. We first construct a benchmark dataset related to draft mark detection and employ a powerful and efficient convolutional neural network to accurately perform the detection task. The multi-task learning method is then proposed for simultaneous draft scale recognition and vessel/water segmentation. To obtain more robust VDR under complex conditions (e.g., damaged and stained scales, etc.), the accurate draft scales are generated by an automatic correction method, which is presented based on the spatial distribution rules of draft scales. Finally, an adaptive computational method is exploited to yield an accurate and robust draft depth. Extensive experiments have been implemented on the realistic dataset to compare our MTL-VDR with state-of-the-art methods. The results have demonstrated its superior performance in terms of accuracy, robustness, and efficiency. The computational speed exceeds 40 FPS, which satisfies the requirements of real-time maritime surveillance to guarantee vessel traffic safety.