Search

The development of autonomous agents increasingly relies on Multimodal Language Models (MLMs) to perform tasks described in natural language with GUI environments, such as websites, desktop computers, or mobile phones. Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexities of constructing tasks and evaluators. To overcome these limitations, we introduce Crab, the first agent benchmark framework designed to support cross-environment tasks, incorporating a graph-based fine-grained evaluation method and an efficient mechanism for task and evaluator construction. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. Leveraging Crab, we developed a cross-platform Crab Benchmark-v0 comprising 100 tasks in computer desktop and mobile phone environments. We evaluated four advanced MLMs using different single and multi-agent system configurations on this benchmark. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 35.26%. All framework code, agent code, and task datasets are publicly available at https://github.com/camel-ai/crab.

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world scenarios, immediate reward signals are not obtainable; instead, agents receive a single reward that is contingent upon a partial sequence or a complete trajectory. In this work, we define this challenging problem as Reinforcement Learning from Bagged Reward (RLBR), where sequences of data are treated as bags with non-Markovian bagged rewards. We provide a theoretical study to establish the connection between RLBR and standard RL in Markov Decision Processes (MDPs). To effectively explore the reward distributions within these bags and enhance policy training, we propose a Transformer-based reward model, the Reward Bag Transformer, which employs a bidirectional attention mechanism to interpret contextual nuances and temporal dependencies within each bag. Our empirical evaluations reveal that the challenge intensifies as the bag length increases, leading to the performance degradation due to reduced informational granularity. Nevertheless, our approach consistently outperforms existing methods, demonstrating the least decline in efficacy across varying bag lengths and excelling in approximating the original MDP's reward distribution.

Despite the great success of neural visual generative models in recent years, integrating them with strong symbolic reasoning systems remains a challenging task. There are two levels of symbol grounding problems among the core challenges: the first is symbol assignment, i.e. mapping latent factors of neural visual generators to semantic-meaningful symbolic factors from the reasoning systems by learning from limited labeled data. The second is rule learning, i.e. learning new rules that govern the generative process to enhance the symbolic reasoning systems. To deal with these two problems, we propose a neurosymbolic learning approach, Abductive visual Generation (AbdGen), for integrating logic programming systems with neural visual generative models based on the abductive learning framework. To achieve reliable and efficient symbol grounding, the quantized abduction method is introduced for generating abduction proposals by the nearest-neighbor lookup within semantic codebooks. To achieve precise rule learning, the contrastive meta-abduction method is proposed to eliminate wrong rules with positive cases and avoid less informative rules with negative cases simultaneously. Experimental results show that compared to the baseline approaches, AbdGen requires significantly less labeled data for symbol assignment. Furthermore, AbdGen can effectively learn underlying logical generative rules from data, which is out of the capability of existing approaches. The code is released at this link: https://github.com/candytalking/AbdGen.

As drones become increasingly prevalent in human life, they also raises security concerns such as unauthorized access and control, as well as collisions and interference with manned aircraft. Therefore, ensuring the ability to accurately detect and identify between different drones holds significant implications for coverage extension. Assisted by machine learning, radio frequency (RF) detection can recognize the type and flight mode of drones based on the sampled drone signals. In this paper, we first utilize Short-Time Fourier. Transform (STFT) to extract two-dimensional features from the raw signals, which contain both time-domain and frequency-domain information. Then, we employ a Convolutional Neural Network (CNN) built with ResNet structure to achieve multi-class classifications. Our experimental results show that the proposed ResNet-STFT can achieve higher accuracy and faster convergence on the extended dataset. Additionally, it exhibits balanced performance compared to other baselines on the raw dataset.

Figuring out which Pre-Trained Model (PTM) from a model zoo fits the target task is essential to take advantage of plentiful model resources. With the availability of numerous heterogeneous PTMs from diverse fields, efficiently selecting the most suitable PTM is challenging due to the time-consuming costs of carrying out forward or backward passes over all PTMs. In this paper, we propose Model Spider, which tokenizes both PTMs and tasks by summarizing their characteristics into vectors to enable efficient PTM selection. By leveraging the approximated performance of PTMs on a separate set of training tasks, Model Spider learns to construct tokens and measure the fitness score between a model-task pair via their tokens. The ability to rank relevant PTMs higher than others generalizes to new tasks. With the top-ranked PTM candidates, we further learn to enrich task tokens with their PTM-specific semantics to re-rank the PTMs for better selection. Model Spider balances efficiency and selection ability, making PTM selection like a spider preying on a web. Model Spider demonstrates promising performance in various configurations of model zoos.

In many real-world imitation learning tasks, the demonstrator and the learner have to act under different observation spaces. This situation brings significant obstacles to existing imitation learning approaches, since most of them learn policies under homogeneous observation spaces. On the other hand, previous studies under different observation spaces have strong assumptions that these two observation spaces coexist during the entire learning process. However, in reality, the observation coexistence will be limited due to the high cost of acquiring expert observations. In this work, we study this challenging problem with limited observation coexistence under heterogeneous observations: Heterogeneously Observable Imitation Learning (HOIL). We identify two underlying issues in HOIL: the dynamics mismatch and the support mismatch, and further propose the Importance Weighting with REjection (IWRE) algorithm based on importance weighting and learning with rejection to solve HOIL problems. Experimental results show that IWRE can solve various HOIL tasks, including the challenging tasks of transforming the vision-based demonstrations to random access memory (RAM)-based policies in the Atari domain, even with limited visual observations.

Rapid progress in nonlinear plasmonic metasurfaces enabled many novel optical characteristics for metasurfaces, with potential applications in frequency metrology, timing characterization and quantum information. However, the spectrum of nonlinear optical response was typically based upon the linear optical resonance. In this work, a wavelength-multiplexed nonlinear plasmon-MoS2 hybrid metasurface with suppression phenomenon was proposed, where multiple nonlinear signals could to be simultaneously processed and optionally tuned. A clear physical picture to depict the nonlinear plasmonic bound states in the continuum (BICs) was presented, from the perspective of both classical and quantum approaches. Particularly, beyond the ordinary plasmon-polariton effect, we numerically demonstrated a giant BIC-inspired second-order nonlinear susceptibility $10^{-5}$~$m/V$ of MoS2 in the infrared band. The novelty in our study lies in the presence of a quantum oscillator that can be adopted to both suppress and enhance the nonlinear quasi BICs. This selectable nonlinear BIC-based suppression and enhancement effect can optionally block undesired modes, resulting in narrower linewidth as well as smaller quantum decay rates, which is also promising in slow-light-associated technologies.

The COVID-19 pandemic demands assimilation of all available biomedical knowledge to decode its mechanisms of pathogenicity and transmission. Despite the recent renaissance in unsupervised neural networks for decoding unstructured natural languages, a platform for the real-time synthesis of the exponentially growing biomedical literature and its comprehensive triangulation with deep omic insights is not available. Here, we present the nferX platform for dynamic inference from over 45 quadrillion possible conceptual associations extracted from unstructured biomedical text, and their triangulation with Single Cell RNA-sequencing based insights from over 25 tissues. Using this platform, we identify intersections between the pathologic manifestations of COVID-19 and the comprehensive expression profile of the SARS-CoV-2 receptor ACE2. We find that tongue keratinocytes and olfactory epithelial cells are likely under-appreciated targets of SARS-CoV-2 infection, correlating with reported loss of sense of taste and smell as early indicators of COVID-19 infection, including in otherwise asymptomatic patients. Airway club cells, ciliated cells and type II pneumocytes in the lung, and enterocytes of the gut also express ACE2. This study demonstrates how a holistic data science platform can leverage unprecedented quantities of structured and unstructured publicly available data to accelerate the generation of impactful biological insights and hypotheses., Comment: 5 figures

One of the key issues for imitation learning lies in making policy learned from limited samples to generalize well in the whole state-action space. This problem is much more severe in high-dimensional state environments, such as game playing with raw pixel inputs. Under this situation, even state-of-the-art adversary-based imitation learning algorithms fail. Through empirical studies, we find that the main cause lies in the failure of training a powerful discriminator to generate meaningful rewards in high-dimensional environments. Although it seems that dimensionality reduction can help, a straightforward application of off-the-shelf methods cannot achieve good performance. In this work, we show in theory that the balance between dimensionality reduction and discriminative training is essential for effective learning. To achieve this target, we propose HashReward, which utilizes the idea of supervised hashing to realize such an ideal balance. Experimental results show that HashReward could outperform state-of-the-art methods for a large gap under the challenging high-dimensional environments., Comment: Accepted by AAMAS-2021

One of the fundamental problems in crowdsourcing is the trade-off between the number of the workers needed for high-accuracy aggregation and the budget to pay. For saving budget, it is important to ensure high quality of the crowd-sourced labels, hence the total cost on label collection will be reduced. Since the self-confidence of the workers often has a close relationship with their abilities, a possible way for quality control is to request the workers to return the labels only when they feel confident, by means of providing unsure option to them. On the other hand, allowing workers to choose unsure option also leads to the potential danger of budget waste. In this work, we propose the analysis towards understanding when providing the unsure option indeed leads to significant cost reduction, as well as how the confidence threshold is set. We also propose an online mechanism, which is alternative for threshold selection when the estimation of the crowd ability distribution is difficult., Comment: 25 pages, 1 figures