Siyu Wang

Siyu Wang, Jianfei Chen, Chongxuan Li et al.

By applying entropy codecs with learned data distributions, neural compressors have significantly outperformed traditional codecs in terms of compression ratio. However, the high inference latency of neural networks hinders the deployment of neural compressors in practical applications. In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic. Our work is built upon integer discrete flows, which consists of invertible transformations between discrete random variables. We propose efficient invertible transformations with integer-only arithmetic based on 8-bit quantization. Our invertible transformation is equipped with learnable binary gates to remove redundant filters during inference. We deploy IODF with TensorRT on GPUs, achieving 10x inference speedup compared to the fastest existing neural compressors, while retaining the high compression rates on ImageNet32 and ImageNet64.

Fuwen Luo, Chi Chen, Zihao Wan et al. · tsinghua

Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS.

Siyu Wang, Xiaocong Chen, Lina Yao

In offline reinforcement learning-based recommender systems (RLRS), learning effective state representations is crucial for capturing user preferences that directly impact long-term rewards. However, raw state representations often contain high-dimensional, noisy information and components that are not causally relevant to the reward. Additionally, missing transitions in offline data make it challenging to accurately identify features that are most relevant to user satisfaction. To address these challenges, we propose Policy-Guided Causal Representation (PGCR), a novel two-stage framework for causal feature selection and state representation learning in offline RLRS. In the first stage, we learn a causal feature selection policy that generates modified states by isolating and retaining only the causally relevant components (CRCs) while altering irrelevant components. This policy is guided by a reward function based on the Wasserstein distance, which measures the causal effect of state components on the reward and encourages the preservation of CRCs that directly influence user interests. In the second stage, we train an encoder to learn compact state representations by minimizing the mean squared error (MSE) loss between the latent representations of the original and modified states, ensuring that the representations focus on CRCs. We provide a theoretical analysis proving the identifiability of causal effects from interventions, validating the ability of PGCR to isolate critical state components for decision-making. Extensive experiments demonstrate that PGCR significantly improves recommendation performance, confirming its effectiveness for offline RL-based recommender systems.

Xiaocong Chen, Siyu Wang, Tong Yu et al.

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various actions and environmental stochasticity. Traditional approaches primarily emphasize mitigating epistemic uncertainty by learning risk-averse policies, often overlooking environmental stochasticity. In this study, we propose an uncertainty-aware distributional offline RL method to simultaneously address both epistemic uncertainty and environmental stochasticity. We propose a model-free offline RL algorithm capable of learning risk-averse policies and characterizing the entire distribution of discounted cumulative rewards, as opposed to merely maximizing the expected value of accumulated discounted returns. Our method is rigorously evaluated through comprehensive experiments in both risk-sensitive and risk-neutral benchmarks, demonstrating its superior performance.

Siyu Wang, Shengran Dai, Jianhui Jiang et al.

Synchrotron radiation sources play a crucial role in fields such as materials science, biology, and chemistry. The beamline, a key subsystem of the synchrotron, modulates and directs the radiation to the sample for analysis. However, the alignment of beamlines is a complex and time-consuming process, primarily carried out manually by experienced engineers. Even minor misalignments in optical components can significantly affect the beam's properties, leading to suboptimal experimental outcomes. Current automated methods, such as bayesian optimization (BO) and reinforcement learning (RL), although these methods enhance performance, limitations remain. The relationship between the current and target beam properties, crucial for determining the adjustment, is not fully considered. Additionally, the physical characteristics of optical elements are overlooked, such as the need to adjust specific devices to control the output beam's spot size or position. This paper addresses the alignment of beamlines by modeling it as a Markov Decision Process (MDP) and training an intelligent agent using RL. The agent calculates adjustment values based on the current and target beam states, executes actions, and iterates until optimal parameters are achieved. A policy network with action attention is designed to improve decision-making by considering both state differences and the impact of optical components. Experiments on two simulated beamlines demonstrate that our algorithm outperforms existing methods, with ablation studies highlighting the effectiveness of the action attention-based policy network.

Siyu Wang, Bo Yang, Zhiwen Yu et al.

In this paper, we investigate a multi-user offloading problem in the overlapping domain of a multi-server mobile edge computing system. We divide the original problem into two stages: the offloading decision making stage and the request scheduling stage. To prevent the terminal from going out of service area during offloading, we consider the mobility parameter of the terminal according to the human behaviour model when making the offloading decision, and then introduce a server evaluation mechanism based on both the mobility parameter and the server load to select the optimal offloading server. In order to fully utilise the server resources, we design a double deep Q-network (DDQN)-based reward evaluation algorithm that considers the priority of tasks when scheduling offload requests. Finally, numerical simulations are conducted to verify that our proposed method outperforms traditional mathematical computation methods as well as the DQN algorithm.

Le Ma, Dong Wang, Zixu Hao et al.

This paper addresses design, modeling and dynamic-compensation PID (dc-PID) control of a novel type of fully-actuated aerial manipulation (AM) system. Firstly, design of novel mechanical structure of the AM is presented. Secondly, kinematics and dynamics of AM are modeled using Craig parameters and recursion Newton-Euler equations respectively, which give rise to a more accurate dynamic relationship between aerial platform and manipulator. Then, the dynamic-compensation PID control is proposed to solve the problem of fully-actuated control of AM. Finally, uniform coupled matrix equations between driving forces/moments and rotor speeds are derived, which can support design and analysis of parameters and decoupling theoretically. It is taken into account practical problems including noise and perturbation, parameter uncertainty, and power limitation in simulations, and results from simulations shows that the AM system presented can be fully-actued controlled with advanced control performances, which can not achieved theoretically in traditional AM. And with compared to backstepping control dc-PID has better control accuracy and capability to disturbance rejection in two simulations of aerial operation tasks with motion of joint. The experiment of dc-pid proves the availability and effectiveness of the method proposed.