For training ResNet-50 on ImageNet, our 5-bit block Householder quantizer achieves only 0.5% validation accuracy loss relative to QA T, comparable to the existing INT8 baseline.

Abstract--Many robots are not equipped with a manipulator and many objects are not suitable for prehensile manipulation (such as large boxes and cylinders). In these cases, pushing is a simple yet effective non-prehensile skill for robots to interact with and further change the environment. Existing work often assumes a set of predefined pushing modes and fixed-shape objects. This work tackles the general problem of controlling a robotic fleet to push collaboratively numerous arbitrary objects to respective destinations, within complex environments of cluttered and movable obstacles. It incorporates several characteristic challenges for multi-robot systems such as online task coordination under large uncertainties of cost and duration, and for contact-rich tasks such as hybrid switching among different contact modes, and under-actuation due to constrained contact forces. The proposed method is based on combinatorial hybrid optimization over dynamic task assignments and hybrid execution via sequences of pushing modes and associated forces. It consists of three main components: (I) the decomposition, ordering and rolling assignment of pushing subtasks to robot subgroups; (II) the keyframe guided hybrid search to optimize the sequence of parameterized pushing modes for each subtask; (III) the hybrid control to execute these modes and transit among them. Last but not least, a diffusion-based accelerator is adopted to predict the keyframes and pushing modes that should be prioritized during hybrid search; and further improve planning efficiency. The framework is complete under mild assumptions. Its efficiency and effectiveness under different numbers of robots and general-shaped objects are validated extensively in simulations and hardware experiments, as well as generalizations to heterogeneous robots, planar assembly and 6D pushing. Humans often interact with objects via non-prehensile skills such as pushing and rolling, especially when prehensile skills such as stable grasping is infeasible. This aspect is however less exploited in robotic systems. Most existing work treats pushing as a complementary skill to pick-and-place primitives for a single manipulator within simple environments, e.g., [1], [2], [3], [4]. Nonetheless, pushing can be particularly beneficial for low-cost mobile robots that are not equipped with a manipulator, e.g., ground vehicles, quadruped robots, and even underwater vehicles [5]. For instance, obstacles can be pushed out of the path, and target objects can be pushed to desired positions.

Strong reasoning capabilities can now be achieved by large-scale reinforcement learning (RL) without any supervised fine-tuning. Although post-training quantization (PTQ) and quantization-aware training (QAT) are well studied in the context of fine-tuning, how quantization impacts RL in large reasoning models (LRMs) remains an open question. To answer this question, we conducted systematic experiments and discovered a significant gap in reasoning performance on mathematical benchmarks between post-RL quantized models and their quantization-aware RL optimized counterparts. Our findings suggest that quantization-aware RL training negatively impacted the learning process, whereas PTQ and QLoRA led to greater performance.

How to efficiently serve ever-larger trained natural language models in practice has become exceptionally challenging even for powerful cloud servers due to their prohibitive memory/computation requirements.

Abstract-- We study the robustness of an agent decision-making model in finite-population games, with a particular focus on the Kullback-Leibler Divergence Regularized Learning (KLD-RL) model. Specifically, we examine how the model's parameters influence the impact of various sources of noise and modeling inaccuracies--factors commonly encountered in engineering applications of population games--on agents' decision-making. Our analysis provides insights into how these parameters can be effectively tuned to mitigate such effects. Theoretical results are supported by numerical examples and simulation studies that validate the analysis and illustrate practical strategies for parameter selection. The population game and evolutionary dynamics framework provides a powerful foundation for modeling and analyzing repeated strategic interactions among a population of decision-making agents [1].

In an effort to counter the increasing IoT botnet-based attacks, state-of-the-art deep learning methods have been proposed and have achieved impressive detection accuracy. However, their computational intensity restricts deployment on resource-constrained IoT devices, creating a critical need for lightweight detection models. A common solution to this challenge is model compression via quantization. This study proposes a VAE-MLP model framework where an MLP-based classifier is trained on 8-dimensional latent vectors derived from the high-dimensional train data using the encoder component of a pretrained variational autoencoder (VAE). Two widely used quantization strategies--Quantization-Aware Training (QAT) and Post-Training Quantization (PTQ)--are then systematically evaluated in terms of their impact on detection performance, storage efficiency, and inference latency using two benchmark IoT botnet datasets--N-BaIoT and CICIoT2022. The results revealed that, with respect to detection accuracy, the QAT strategy experienced a more noticeable decline,whereas PTQ incurred only a marginal reduction compared to the original unquantized model. Furthermore, PTQ yielded a 6x speedup and 21x reduction in size, while QAT achieved a 3x speedup and 24x compression, demonstrating the practicality of quantization for device-level IoT botnet detection.

Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically overlook the relationship between a well-trained NN and the quantized model, leading to considerable quantization error for PTQ. However, it is unclear how to efficiently train a model-agnostic neural network which is tailored for a predefined precision low-bit model. In this paper, we firstly discover that a flat full precision neural network is crucial for low-bit quantization. To achieve this, we propose a framework that proactively pre-conditions the model by measuring and disentangling the error sources. Specifically, both the Activation Quantization Error (AQE) and the Weight Quantization Error (WQE) are statistically modeled as independent Gaussian noises. We study several noise injection optimization methods to obtain a flat minimum. Experimental results attest to the effectiveness of our approach. These results open novel pathways for obtaining low-bit PTQ models.

Partial differential equations (PDEs) are an essential modeling tool in engineering and physical sciences. The numerical methods used for solving the more descriptive and sophisticated of these models comprise many computationally expensive modules. Machine learning (ML) provides a way of replacing some of these modules by surrogates that are much more efficient at the time of inference. The resulting PDE-ML coupled systems, however, can be highly susceptible to instabilities [1-3]. Efforts towards ameliorating these have mostly concentrated on improving the accuracy of the surrogates, imbuing them with additional structure, or introducing problem-specific stabilizers, and have garnered limited success [4-7]. In this article, we study a prototype problem to understand the mathematical subtleties involved in PDE-ML coupling, and draw insights that can help with more complex systems.

We study a two-sided market, wherein, price-sensitive heterogeneous customers and servers arrive and join their respective queues. A compatible customer-server pair can then be matched by the platform, at which point, they leave the system. Our objective is to design pricing and matching algorithms that maximize the platform's profit, while maintaining reasonable queue lengths. As the demand and supply curves governing the price-dependent arrival rates may not be known in practice, we design a novel online-learning-based pricing policy and establish its near-optimality. In particular, we prove a tradeoff among three performance metrics: $\tilde{O}(T^{1-γ})$ regret, $\tilde{O}(T^{γ/2})$ average queue length, and $\tilde{O}(T^γ)$ maximum queue length for $γ\in (0, 1/6]$, significantly improving over existing results [1]. Moreover, barring the permissible range of $γ$, we show that this trade-off between regret and average queue length is optimal up to logarithmic factors under a class of policies, matching the optimal one as in [2] which assumes the demand and supply curves to be known. Our proposed policy has two noteworthy features: a dynamic component that optimizes the tradeoff between low regret and small queue lengths; and a probabilistic component that resolves the tension between obtaining useful samples for fast learning and maintaining small queue lengths.

Long-term monitoring of numerous dynamic targets can be tedious for a human operator and infeasible for a single robot, e.g., to monitor wild flocks, detect intruders, search and rescue. Fleets of autonomous robots can be effective by acting collaboratively and concurrently. However, the online coordination is challenging due to the unknown behaviors of the targets and the limited perception of each robot. Existing work often deploys all robots available without minimizing the fleet size, or neglects the constraints on their resources such as battery and memory. This work proposes an online coordination scheme called LOMORO for collaborative target monitoring, path routing and resource charging. It includes three core components: (I) the modeling of multi-robot task assignment problem under the constraints on resources and monitoring intervals; (II) the resource-aware task coordination algorithm iterates between the high-level assignment of dynamic targets and the low-level multi-objective routing via the Martin's algorithm; (III) the online adaptation algorithm in case of unpredictable target behaviors and robot failures. It ensures the explicitly upper-bounded monitoring intervals for all targets and the lower-bounded resource levels for all robots, while minimizing the average number of active robots. The proposed methods are validated extensively via large-scale simulations against several baselines, under different road networks, robot velocities, charging rates and monitoring intervals.