The advances in multimodal large language models (MLLMs) have led to growing interests in LLM-based autonomous driving agents to leverage their strong reasoning capabilities. However, capitalizing on MLLMs' strong reasoning capabilities for improved planning behavior is challenging since planning requires full 3D situational awareness beyond 2D reasoning. To address this challenge, our work proposes a holistic framework for strong alignment between agent models and 3D driving tasks. Our framework starts with a novel 3D MLLM architecture that uses sparse queries to lift and compress visual representations into 3D before feeding them into an LLM. This query-based representation allows us to jointly encode dynamic objects and static map elements (e.g., traffic lanes), providing a condensed world model for perception-action alignment in 3D. We further propose OmniDrive-nuScenes, a new visual question-answering dataset challenging the true 3D situational awareness of a model with comprehensive visual question-answering (VQA) tasks, including scene description, traffic regulation, 3D grounding, counterfactual reasoning, decision making and planning. Extensive studies show the effectiveness of the proposed architecture as well as the importance of the VQA tasks for reasoning and planning in complex 3D scenes.
相關內容
Federated Learning (FL) enables model training across decentralized devices by communicating solely local model updates to an aggregation server. Although such limited data sharing makes FL more secure than centralized approached, FL remains vulnerable to inference attacks during model update transmissions. Existing secure aggregation approaches rely on differential privacy or cryptographic schemes like Functional Encryption (FE) to safeguard individual client data. However, such strategies can reduce performance or introduce unacceptable computational and communication overheads on clients running on edge devices with limited resources. In this work, we present EncCluster, a novel method that integrates model compression through weight clustering with recent decentralized FE and privacy-enhancing data encoding using probabilistic filters to deliver strong privacy guarantees in FL without affecting model performance or adding unnecessary burdens to clients. We performed a comprehensive evaluation, spanning various datasets and architectures, to demonstrate EncCluster's scalability across encryption levels. Our findings reveal that EncCluster significantly reduces communication costs - below even conventional FedAvg - and accelerates encryption by more than four times over all baselines; at the same time, it maintains high model accuracy and enhanced privacy assurances.
While substantial advancements have been made in developing large language models (LLMs), achieving control over their behavior can be difficult. Direct preference optimization (DPO) assumes the existence of a latent reward function to evaluate the responses of LLMs. This assumption indicates a strict preference ordering of different responses to the same input. However, there always exist contradictions of preference in LLMs according to our experimental observations. In this paper, we construct a graph structure of the preference relationship among different responses with self-annotation to find contradictions in the preference order. We propose ContraSolver, an algorithm that traverses all edges on the preference graph to identify those that might cause contradictions. ContraSolver initializes the graph with a maximum spanning tree and identifies contradictory edges, prioritizing the resolution of low-confidence preferences while preserving high-confidence ones. Experimental results on four different generation tasks show that the performance of different LLMs can be largely improved through our completely unsupervised self-alignment. Furthermore, by analyzing the preference graphs of LLMs with and without self-alignment by ContraSolver, we quantify the reduction in contradictions, suggesting that resolving preference contradictions is crucial for achieving better alignment performance.
Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered significant interest from the research community in natural language processing (NLP) and human-computer interaction (HCI). Such systems can provide answers to user questions about explanations, have the potential to enhance users' comprehension and offer more information about the decision-making and generation processes of LLMs. Currently available ConvXAI systems are based on intent recognition rather than free chat. Thus, reliably grasping users' intentions in ConvXAI systems still presents a challenge, because there is a broad range of XAI methods to map requests onto and each of them can have multiple slots to take care of. In order to bridge this gap, we present CoXQL, the first dataset for user intent recognition in ConvXAI, covering 31 intents, seven of which require filling additional slots. Subsequently, we enhance an existing parsing approach by incorporating template validations, and conduct an evaluation of several LLMs on CoXQL using different parsing strategies. We conclude that the improved parsing approach (MP+) surpasses the performance of previous approaches. We also discover that intents with multiple slots remain highly challenging for LLMs.
The rapid advancements in the development of multimodal large language models (MLLMs) have consistently led to new breakthroughs on various benchmarks. In response, numerous challenging and comprehensive benchmarks have been proposed to more accurately assess the capabilities of MLLMs. However, there is a dearth of exploration of the higher-order perceptual capabilities of MLLMs. To fill this gap, we propose the Image Implication understanding Benchmark, II-Bench, which aims to evaluate the model's higher-order perception of images. Through extensive experiments on II-Bench across multiple MLLMs, we have made significant findings. Initially, a substantial gap is observed between the performance of MLLMs and humans on II-Bench. The pinnacle accuracy of MLLMs attains 74.8%, whereas human accuracy averages 90%, peaking at an impressive 98%. Subsequently, MLLMs perform worse on abstract and complex images, suggesting limitations in their ability to understand high-level semantics and capture image details. Finally, it is observed that most models exhibit enhanced accuracy when image sentiment polarity hints are incorporated into the prompts. This observation underscores a notable deficiency in their inherent understanding of image sentiment. We believe that II-Bench will inspire the community to develop the next generation of MLLMs, advancing the journey towards expert artificial general intelligence (AGI). II-Bench is publicly available at //huggingface.co/datasets/m-a-p/II-Bench.
Mapping is one of the crucial tasks enabling autonomous navigation of a mobile robot. Conventional mapping methods output dense geometric map representation, e.g. an occupancy grid, which is not trivial to keep consistent for the prolonged runs covering large environments. Meanwhile, capturing the topological structure of the workspace enables fast path planning, is less prone to odometry error accumulation and does not consume much memory. Following this idea, this paper introduces PRISM-TopoMap -- a topological mapping method that maintains a graph of locally aligned locations not relying on global metric coordinates. The proposed method involves learnable multimodal place recognition paired with the scan matching pipeline for localization and loop closure in the graph of locations. The latter is updated online and the robot is localized in a proper node at each time step. We conduct a broad experimental evaluation of the suggested approach in a range of photo-realistic environments and on a real robot (wheeled differential driven Husky robot), and compare it to state of the art. The results of the empirical evaluation confirm that PRISM-Topomap consistently outperforms competitors across several measures of mapping and navigation efficiency and performs well on a real robot. The code of PRISM-Topomap is open-sourced and available at //github.com/kirillMouraviev/prism-topomap.
Recent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This CCSP can be solved through sampling or optimization to find a skill sequence and continuous parameter settings that achieve the goal while avoiding constraint violations. Additionally, we consider cases where the LLM proposes unsatisfiable CCSPs, such as those that are kinematically infeasible, dynamically unstable, or lead to collisions, and re-prompt the LLM to form a new CCSP accordingly. Experiments across three different simulated 3D domains demonstrate that our proposed strategy, PRoC3S, is capable of solving a wide range of complex manipulation tasks with realistic constraints on continuous parameters much more efficiently and effectively than existing baselines.
Recent progress in large language models (LLMs) has led to their widespread adoption in various domains. However, these advancements have also introduced additional safety risks and raised concerns regarding their detrimental impact on already marginalized populations. Despite growing mitigation efforts to develop safety safeguards, such as supervised safety-oriented fine-tuning and leveraging safe reinforcement learning from human feedback, multiple concerns regarding the safety and ingrained biases in these models remain. Furthermore, previous work has demonstrated that models optimized for safety often display exaggerated safety behaviors, such as a tendency to refrain from responding to certain requests as a precautionary measure. As such, a clear trade-off between the helpfulness and safety of these models has been documented in the literature. In this paper, we further investigate the effectiveness of safety measures by evaluating models on already mitigated biases. Using the case of Llama 2 as an example, we illustrate how LLMs' safety responses can still encode harmful assumptions. To do so, we create a set of non-toxic prompts, which we then use to evaluate Llama models. Through our new taxonomy of LLMs responses to users, we observe that the safety/helpfulness trade-offs are more pronounced for certain demographic groups which can lead to quality-of-service harms for marginalized populations.
Deep learning-based image compression algorithms typically focus on designing encoding and decoding networks and improving the accuracy of entropy model estimation to enhance the rate-distortion (RD) performance. However, few algorithms leverage the compression distortion prior from existing compression algorithms to improve RD performance. In this paper, we propose a latent diffusion model-based remote sensing image compression (LDM-RSIC) method, which aims to enhance the final decoding quality of RS images by utilizing the generated distortion prior from a LDM. Our approach consists of two stages. In the first stage, a self-encoder learns prior from the high-quality input image. In the second stage, the prior is generated through an LDM, conditioned on the decoded image of an existing learning-based image compression algorithm, to be used as auxiliary information for generating the texture-rich enhanced image. To better utilize the prior, a channel attention and gate-based dynamic feature attention module (DFAM) is embedded into a Transformer-based multi-scale enhancement network (MEN) for image enhancement. Extensive experiments demonstrate the proposed LDM-RSIC significantly outperforms existing state-of-the-art traditional and learning-based image compression algorithms in terms of both subjective perception and objective metrics. Additionally, we use the LDM-based scheme to improve the traditional image compression algorithm JPEG2000 and obtain 32.00% bit savings on the DOTA testing set. The code will be available at //github.com/mlkk518/LDM-RSIC.
Self-Supervised Learning (SSL) models have demonstrated exceptional performance in various speech tasks, particularly in low-resource and multilingual domains. Recent works show that fusing diverse SSL models could achieve superior performance compared to using one SSL model. However, fusing models increases the overall parameter size, leading to higher computational costs. We propose EFFUSE, a novel approach that uses a single SSL model to mimic the features of multiple SSL models via prediction, resulting in a lightweight framework with competitive performance. Our experiments show that EFFUSE outperforms individual SSL models in multilingual speech recognition tasks. Our best performing model achieves an average SUPERB score increase of 63.5 (6.3%) from the SSL baselines in Multilingual Speech Universal PERformance Benchmark (ML-SUPERB), while decreasing parameter size on average by 317M parameters (49%) from the fusion models.
Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. When such models are deployed in real world environments, they inevitably interface with other entities and agents. For example, language models are often used to interact with human beings through dialogue, and visual perception models are used to autonomously navigate neighborhood streets. In response to these developments, new paradigms are emerging for training foundation models to interact with other agents and perform long-term reasoning. These paradigms leverage the existence of ever-larger datasets curated for multimodal, multitask, and generalist interaction. Research at the intersection of foundation models and decision making holds tremendous promise for creating powerful new systems that can interact effectively across a diverse range of applications such as dialogue, autonomous driving, healthcare, education, and robotics. In this manuscript, we examine the scope of foundation models for decision making, and provide conceptual tools and technical background for understanding the problem space and exploring new research directions. We review recent approaches that ground foundation models in practical decision making applications through a variety of methods such as prompting, conditional generative modeling, planning, optimal control, and reinforcement learning, and discuss common challenges and open problems in the field.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191