Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance during training or inference. However, due to the lack of annotations of intermediate interactions, most existing works use an outcome reward model to optimize policies across entire trajectories. This may lead to sub-optimal policies and hinder the overall performance. To address this, we propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values in a stepwise manner for open language agents. By introducing a reasoning tree and performing process reward modeling, QLASS provides effective intermediate guidance for each step. With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value, resulting in significant performance improvement during model inference on complex interactive agent tasks. Notably, even with almost half the annotated data, QLASS retains strong performance, demonstrating its efficiency in handling limited supervision. We also empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis. We will release our code and data.

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills. Through extensive experiments, we show that CurrMask exhibits superior zero-shot performance on skill prompting tasks, goal-conditioned planning tasks, and competitive finetuning performance on offline RL tasks. Additionally, our analysis of training dynamics reveals that CurrMask gradually acquires skills of varying complexity by dynamically adjusting its masking scheme. Code is available at here.

Multi-view egocentric hand tracking is a challenging task and plays a critical role in VR interaction. In this report, we present a method that uses multi-view input images and camera extrinsic parameters to estimate both hand shape and pose. To reduce overfitting to the camera layout, we apply crop jittering and extrinsic parameter noise augmentation. Additionally, we propose an offline neural smoothing post-processing method to further improve the accuracy of hand position and pose. Our method achieves 13.92mm MPJPE on the Umetrack dataset and 21.66mm MPJPE on the HOT3D dataset.

The effectiveness of central bank communication is a crucial aspect of monetary policy transmission. While recent research has examined the influence of policy communication by the chairs of the Federal Reserve on various financial variables, much of the literature relies on rule-based or dictionary-based methods in parsing the language of the chairs, leaving nuanced information about policy stance contained in nonverbal emotion out of the analysis. In the current study, we propose the Fine-Grained Monetary Policy Analysis Framework (FMPAF), a novel approach that integrates large language models (LLMs) with regression analysis to provide a comprehensive analysis of the impact of the press-conference communications of chairs of the Federal Reserve on financial markets. We conduct extensive comparisons of model performance under different levels of granularity, modalities, and communication scenarios. Based on our preferred specification, a one-unit increase in the sentiment score is associated with an increase of the price of S\&P 500 Exchange-Traded Fund by approximately 500 basis points, a 15-basis-point decrease in the policy interest rate, while not leading to a significant response in exchange rates.

We introduce a high-performance fingerprint liveness feature extraction technique that secured first place in LivDet 2023 Fingerprint Representation Challenge. Additionally, we developed a practical fingerprint recognition system with 94.68% accuracy, earning second place in LivDet 2023 Liveness Detection in Action. By investigating various methods, particularly style transfer, we demonstrate improvements in accuracy and generalization when faced with limited training data. As a result, our approach achieved state-of-the-art performance in LivDet 2023 Challenges.

Federated edge learning (FEEL) enables privacy-preserving model training through periodic communication between edge devices and the server. Unmanned Aerial Vehicle (UAV)-mounted edge devices are particularly advantageous for FEEL due to their flexibility and mobility in efficient data collection. In UAV-assisted FEEL, sensing, computation, and communication are coupled and compete for limited onboard resources, and UAV deployment also affects sensing and communication performance. Therefore, the joint design of UAV deployment and resource allocation is crucial to achieving the optimal training performance. In this paper, we address the problem of joint UAV deployment design and resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing. We first analyze the impact of UAV deployment on the sensing quality and identify a threshold value for the sensing elevation angle that guarantees a satisfactory quality of data samples. Due to the non-ideal sensing channels, we consider the probabilistic sensing model, where the successful sensing probability of each UAV is determined by its position. Then, we derive the upper bound of the FEEL training loss as a function of the sensing probability. Theoretical results suggest that the convergence rate can be improved if UAVs have a uniform successful sensing probability. Based on this analysis, we formulate a training time minimization problem by jointly optimizing UAV deployment, integrated sensing, computation, and communication (ISCC) resources under a desirable optimality gap constraint. To solve this challenging mixed-integer non-convex problem, we apply the alternating optimization technique, and propose the bandwidth, batch size, and position optimization (BBPO) scheme to optimize these three decision variables alternately.