arXiv subjects

Boda Li

Publications and source records attributed to Boda Li.

6 recordsLinked to original sources

arXiv2026

ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation

Modern recommendation models gain prediction quality by scaling feature-interaction and sequence modules, but production cost constraints cap how far systems can scale. In this work, we propose Request-Oriented Compute Sharing (ROCS), a modeling and inference paradigm that exploits a unique property of recommendation inference: each user request is evaluated against many candidates, while request-side features are shared across candidates. ROCS defers request-candidate interactions as late as possible, isolates candidate-dependent representations, and evaluates substantial portions of the model once per request rather than once per candidate, significantly improving inference efficiency while maintaining or improving prediction quality. To realize this paradigm, we develop Generalized Layer Masking (GLM) to enforce candidate isolation in feature-interaction architectures, and Deep Cross Attention (DCA) to extend request-oriented sharing to sequence architectures. To support efficient GPU deployment, we co-design In-Kernel Broadcast Optimization (IKBO) that significantly accelerates ROCS model execution. Experiments on public benchmarks show that ROCS consistently improves the quality-efficiency tradeoff across recommendation backbones. On production-scale workloads, ROCS achieves up to a 3x QPS improvement on retrieval models without quality degradation and a 0.5% relative LogLoss improvement with a 50% QPS gain on a short-form video ranking model. ROCS has been deployed across large-scale recommendation systems spanning ads and organic surfaces, retrieval and ranking stages, and more than two orders of magnitude in inference complexity, delivering significant online gains at reduced infrastructure cost.

cs.LG↗

arXiv2025

Robustness Requirement Coverage using a Situation Coverage Approach for Vision-based AI Systems

AI-based robots and vehicles are expected to operate safely in complex and dynamic environments, even in the presence of component degradation. In such systems, perception relies on sensors such as cameras to capture environmental data, which is then processed by AI models to support decision-making. However, degradation in sensor performance directly impacts input data quality and can impair AI inference. Specifying safety requirements for all possible sensor degradation scenarios leads to unmanageable complexity and inevitable gaps. In this position paper, we present a novel framework that integrates camera noise factor identification with situation coverage analysis to systematically elicit robustness-related safety requirements for AI-based perception systems. We focus specifically on camera degradation in the automotive domain. Building on an existing framework for identifying degradation modes, we propose involving domain, sensor, and safety experts, and incorporating Operational Design Domain specifications to extend the degradation model by incorporating noise factors relevant to AI performance. Situation coverage analysis is then applied to identify representative operational contexts. This work marks an initial step toward integrating noise factor analysis and situational coverage to support principled formulation and completeness assessment of robustness requirements for camera-based AI perception.

cs.RO↗

arXiv2024

Physics-Informed Neural Network Based Digital Image Correlation Method

Digital Image Correlation (DIC) is a key technique in experimental mechanics for full-field deformation measurement, traditionally relying on subset matching to determine displacement fields. However, selecting optimal parameters like shape functions and subset size can be challenging in non-uniform deformation scenarios. Recent deep learning-based DIC approaches, both supervised and unsupervised, use neural networks to map speckle images to deformation fields, offering precise measurements without manual tuning. However, these methods require complex network architectures to extract speckle image features, which does not guarantee solution accuracy This paper introduces PINN-DIC, a novel DIC method based on Physics-Informed Neural Networks (PINNs). Unlike traditional approaches, PINN-DIC uses a simple fully connected neural network that takes the coordinate domain as input and outputs the displacement field. By integrating the DIC governing equation into the loss function, PINN-DIC directly extracts the displacement field from reference and deformed speckle images through iterative optimization. Evaluations on simulated and real experiments demonstrate that PINN-DIC maintains the accuracy of deep learning-based DIC in non-uniform fields while offering three distinct advantages: 1) enhanced precision with a simpler network by directly fitting the displacement field from coordinates, 2) effective handling of irregular boundary displacement fields with minimal parameter adjustments, and 3) easy integration with other neural network-based mechanical analysis methods for comprehensive DIC result analysis.

eess.IV↗

arXiv2023

Alternating mixed-integer programming and neural network training for approximating stochastic two-stage problems

The presented work addresses two-stage stochastic programs (2SPs), a broadly applicable model to capture optimization problems subject to uncertain parameters with adjustable decision variables. In case the adjustable or second-stage variables contain discrete decisions, the corresponding 2SPs are known to be NP-complete. The standard approach of forming a single-stage deterministic equivalent problem can be computationally challenging even for small instances, as the number of variables and constraints scales with the number of scenarios. To avoid forming a potentially huge MILP problem, we build upon an approach of approximating the expected value of the second-stage problem by a neural network (NN) and encoding the resulting NN into the first-stage problem. The proposed algorithm alternates between optimizing the first-stage variables and retraining the NN. We demonstrate the value of our approach with the example of computing operating points in power systems by showing that the alternating approach provides improved first-stage decisions and a tighter approximation between the expected objective and its neural network approximation.

math.OC↗

arXiv2023

A mixed-integer approximation of robust optimization problems with mixed-integer adjustments

In the present article we propose a mixed-integer approximation of adjustable-robust optimization (ARO) problems, that have both, continuous and discrete variables on the lowest level. As these trilevel problems are notoriously hard to solve, we restrict ourselves to weakly-connected instances. Our approach allows us to approximate, and in some cases exactly represent, the trilevel problem as a single-level mixed-integer problem. This allows us to leverage the computational efficiency of state-of-the-art mixed-integer programming solvers. We demonstrate the value of this approach by applying it to the optimization of power systems, particularly to the control of smart converters.

math.OC↗

arXiv2022

The Design of By-product Hydrogen Supply Chain Considering Large-scale Storage and Chemical Plants: A Game Theory Perspective

Hydrogen, an essential resource in the decarbonized economy, is commonly produced as a by-product of chemical plants. To promote the use of by-product hydrogen, this paper proposes a supply chain model among chemical plants, hydrogen-storage salt caverns, and end users, considering time-of-use (TOU) hydrogen price, coalition strategies of suppliers, and road transportation of liquefied and compressed hydrogen. The transport route planning problem among multiple chemical plants is modeled through a cooperative game, while the hydrogen market among the salt cavern and chemical plants is modeled through a Stackelberg game. The equilibrium of the supply chain model gives the transportation and trading strategies of individual stakeholders. Simulation results demonstrate that the proposed method can provide useful insights on by-product hydrogen market design and analysis.

eess.SY↗