Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refinement mechanism for automated reward function design. The framework commences with the LLM formulating an initial reward function based on natural language inputs. Then, the performance of the reward function is assessed, and the results are presented back to the LLM for guiding its self-refinement process. We examine the performance of our proposed framework through a variety of continuous robotic control tasks across three diverse robotic systems. The results indicate that our LLM-designed reward functions are able to rival or even surpass manually designed reward functions, highlighting the efficacy and applicability of our approach.
相關內容
Existing work on jailbreak Multimodal Large Language Models (MLLMs) has focused primarily on adversarial examples in model inputs, with less attention to vulnerabilities in model APIs. To fill the research gap, we carry out the following work: 1) We discover a system prompt leakage vulnerability in GPT-4V. Through carefully designed dialogue, we successfully steal the internal system prompts of GPT-4V. This finding indicates potential exploitable security risks in MLLMs; 2)Based on the acquired system prompts, we propose a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt). By employing GPT-4 as a red teaming tool against itself, we aim to search for potential jailbreak prompts leveraging stolen system prompts. Furthermore, in pursuit of better performance, we also add human modification based on GPT-4's analysis, which further improves the attack success rate to 98.7\%; 3) We evaluated the effect of modifying system prompts to defend against jailbreaking attacks. Results show that appropriately designed system prompts can significantly reduce jailbreak success rates. Overall, our work provides new insights into enhancing MLLM security, demonstrating the important role of system prompts in jailbreaking, which could be leveraged to greatly facilitate jailbreak success rates while also holding the potential for defending against jailbreaks.
Compositional generalisation (CG), in NLP and in machine learning more generally, has been assessed mostly using artificial datasets. It is important to develop benchmarks to assess CG also in real-world natural language tasks in order to understand the abilities and limitations of systems deployed in the wild. To this end, our GenBench Collaborative Benchmarking Task submission utilises the distribution-based compositionality assessment (DBCA) framework to split the Europarl translation corpus into a training and a test set in such a way that the test set requires compositional generalisation capacity. Specifically, the training and test sets have divergent distributions of dependency relations, testing NMT systems' capability of translating dependencies that they have not been trained on. This is a fully-automated procedure to create natural language compositionality benchmarks, making it simple and inexpensive to apply it further to other datasets and languages. The code and data for the experiments is available at //github.com/aalto-speech/dbca.
Dynamic Metasurface Antenna (DMA) is a cutting-edge antenna technology offering scalable and sustainable solutions for large antenna arrays. The effectiveness of DMAs stems from their inherent configurable analog signal processing capabilities, which facilitate cost-limited implementations. However, when DMAs are used in multiple input multiple output (MIMO) communication systems, they pose challenges in channel estimation due to their analog compression. In this paper, we propose two model-based learning methods to overcome this challenge. Our approach starts by casting channel estimation as a compressed sensing problem. Here, the sensing matrix is formed using a random DMA weighting matrix combined with a spatial gridding dictionary. We then employ the learned iterative shrinkage and thresholding algorithm (LISTA) to recover the sparse channel parameters. LISTA unfolds the iterative shrinkage and thresholding algorithm into a neural network and trains the neural network into a highly efficient channel estimator fitting with the previous channel. As the sensing matrix is crucial to the accuracy of LISTA recovery, we introduce another data-aided method, LISTA-sensing matrix optimization (LISTA-SMO), to jointly optimize the sensing matrix. LISTA-SMO takes LISTA as a backbone and embeds the sensing matrix optimization layers in LISTA's neural network, allowing for the optimization of the sensing matrix along with the training of LISTA. Furthermore, we propose a self-supervised learning technique to tackle the difficulty of acquiring noise-free data. Our numerical results demonstrate that LISTA outperforms traditional sparse recovery methods regarding channel estimation accuracy and efficiency. Besides, LISTA-SMO achieves better channel accuracy than LISTA, demonstrating the effectiveness in optimizing the sensing matrix.
Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection
Human-Object Interaction Detection is a crucial aspect of human-centric scene understanding, with important applications in various domains. Despite recent progress in this field, recognizing subtle and detailed interactions remains challenging. Existing methods try to use human-related clues to alleviate the difficulty, but rely heavily on external annotations or knowledge, limiting their practical applicability in real-world scenarios. In this work, we propose a novel Part Semantic Network (PSN) to solve this problem. The core of PSN is a Conditional Part Attention (CPA) mechanism, where human features are taken as keys and values, and the object feature is used as query for the computation in a cross-attention mechanism. In this way, our model learns to automatically focus on the most informative human parts conditioned on the involved object, generating more semantically meaningful features for interaction recognition. Additionally, we propose an Occluded Part Extrapolation (OPE) strategy to facilitate interaction recognition under occluded scenarios, which teaches the model to extrapolate detailed features from partially occluded ones. Our method consistently outperforms prior approaches on the V-COCO and HICO-DET datasets, without external data or extra annotations. Additional ablation studies validate the effectiveness of each component of our proposed method.
Unmanned Aerial Vehicles (UAVs) have gained widespread recognition for their diverse applications, ranging from surveillance to delivery services. Among the various control algorithms employed to stabilize and navigate UAVs, the Proportional-Integral-Derivative (PID) controller stands out as a classical yet robust solution. This review provides a comprehensive examination of PID controller applications in the context of UAVs, addressing their fundamental principles, dynamics modeling, stability control, navigation tasks, parameter tuning methods, challenges, and future directions.
Autonomous driving systems are always built on motion-related modules such as the planner and the controller. An accurate and robust trajectory tracking method is indispensable for these motion-related modules as a primitive routine. Current methods often make strong assumptions about the model such as the context and the dynamics, which are not robust enough to deal with the changing scenarios in a real-world system. In this paper, we propose a Deep Reinforcement Learning (DRL)-based trajectory tracking method for the motion-related modules in autonomous driving systems. The representation learning ability of DL and the exploration nature of RL bring strong robustness and improve accuracy. Meanwhile, it enhances versatility by running the trajectory tracking in a model-free and data-driven manner. Through extensive experiments, we demonstrate both the efficiency and effectiveness of our method compared to current methods.
The Human Activity Recognition (HAR) tasks automatically identify human activities using the sensor data, which has numerous applications in healthcare, sports, security, and human-computer interaction. Despite significant advances in HAR, critical challenges still exist. Game theory has emerged as a promising solution to address these challenges in machine learning problems including HAR. However, there is a lack of research work on applying game theory solutions to the HAR problems. This review paper explores the potential of game theory as a solution for HAR tasks, and bridges the gap between game theory and HAR research work by suggesting novel game-theoretic approaches for HAR problems. The contributions of this work include exploring how game theory can improve the accuracy and robustness of HAR models, investigating how game-theoretic concepts can optimize recognition algorithms, and discussing the game-theoretic approaches against the existing HAR methods. The objective is to provide insights into the potential of game theory as a solution for sensor-based HAR, and contribute to develop a more accurate and efficient recognition system in the future research directions.
The development of unmanned aerial vehicles (UAVs) has been gaining momentum in recent years owing to technological advances and a significant reduction in their cost. UAV technology can be used in a wide range of domains, including communication, agriculture, security, and transportation. It may be useful to group the UAVs into clusters/flocks in certain domains, and various challenges associated with UAV usage can be alleviated by clustering. Several computational challenges arise in UAV flock management, which can be solved by using machine learning (ML) methods. In this survey, we describe the basic terms relating to UAVS and modern ML methods, and we provide an overview of related tutorials and surveys. We subsequently consider the different challenges that appear in UAV flocks. For each issue, we survey several machine learning-based methods that have been suggested in the literature to handle the associated challenges. Thereafter, we describe various open issues in which ML can be applied to solve the different challenges of flocks, and we suggest means of using ML methods for this purpose. This comprehensive review may be useful for both researchers and developers in providing a wide view of various aspects of state-of-the-art ML technologies that are applicable to flock management.
Deep Learning has implemented a wide range of applications and has become increasingly popular in recent years. The goal of multimodal deep learning is to create models that can process and link information using various modalities. Despite the extensive development made for unimodal learning, it still cannot cover all the aspects of human learning. Multimodal learning helps to understand and analyze better when various senses are engaged in the processing of information. This paper focuses on multiple types of modalities, i.e., image, video, text, audio, body gestures, facial expressions, and physiological signals. Detailed analysis of past and current baseline approaches and an in-depth study of recent advancements in multimodal deep learning applications has been provided. A fine-grained taxonomy of various multimodal deep learning applications is proposed, elaborating on different applications in more depth. Architectures and datasets used in these applications are also discussed, along with their evaluation metrics. Last, main issues are highlighted separately for each domain along with their possible future research directions.
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks. Despite its powerful capacity to learn and generalize from few samples, GNN usually suffers from severe over-fitting and over-smoothing as the model becomes deep, which limit the model scalability. In this work, we propose a novel Attentive GNN to tackle these challenges, by incorporating a triple-attention mechanism, \ie node self-attention, neighborhood attention, and layer memory attention. We explain why the proposed attentive modules can improve GNN for few-shot learning with theoretical analysis and illustrations. Extensive experiments show that the proposed Attentive GNN outperforms the state-of-the-art GNN-based methods for few-shot learning over the mini-ImageNet and Tiered-ImageNet datasets, with both inductive and transductive settings.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191