arXiv subjects

Yifeng Zeng

Publications and source records attributed to Yifeng Zeng.

14 recordsLinked to original sources

arXiv2026

Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering

Correctness and readability are key measures of code quality, respectively ensuring functional fidelity and ease of comprehension. While most existing research focuses on improving the correctness of large language models~(LLMs) generated codes, readability remains under-addressed. Enhancing readability through targeted control is challenging due to its subjective nature. In this article, we employ representation engineering~(RepE) as the targeted control method given its characteristics of low data dependency and low computational cost. Prior work on RepE has primarily focused on the targeted control for a single task, but improving the code readability requires the control across multiple tasks. Accordingly we proposes the multitask RepE framework and theoretically discuss the impact of the multitask steering method on the tradeoff between the code readability and correctness. We further provide comprehensive experiments in support. All the relevant implementations are open-source and available upon request.

cs.SE↗

arXiv2026

WeatherSeg: Weather-Robust Image Segmentation using Teacher-Student Dual Learning and Classifier-Updating Attention

WeatherSeg, an advanced semi-supervised segmentation framework, addresses autonomous driving's environmental perception challenges in adverse weather while reducing annotation costs. This framework integrates a Dual Teacher-Student Weight-Sharing Model (DTSWSM) that enables knowledge distillation from weather-affected images, and a Classifier Weight Updating Attention Mechanism (CWUAM) that dynamically adjusts classifier weights based on environmental attributes. Comprehensive evaluations demonstrate that WeatherSeg significantly outperforms baseline models in both accuracy and robustness across various weather conditions, including clear, rainy, cloudy, and foggy scenarios, establishing it as an effective solution for all-weather semantic segmentation in autonomous driving and related applications.

cs.CV↗

arXiv2025

Conceptual Design Report of Super Tau-Charm Facility: The Accelerator

Electron-positron colliders operating in the GeV region of center-of-mass energies or the Tau-Charm energy region, have been proven to enable competitive frontier research, due to its several unique features. With the progress of high energy physics in the last two decades, a new-generation Tau-Charm factory, Super Tau Charm Facility (STCF) has been actively promoting by the particle physics community in China. STCF holds great potential to address fundamental questions such as the essence of color confinement and the matter-antimatter asymmetry in the universe in the next decades. The main design goals of STCF are with a center-of-mass energy ranging from 2 to 7 GeV and a peak luminosity surpassing 5*10^34 cm^-2s^-1 that is optimized at a center-of-mass energy of 4 GeV, which is about 50 times that of the currently operating Tau-Charm factory - BEPCII. The STCF accelerator is composed of two main parts: a double-ring collider with the crab-waist collision scheme and an injector that provides top-up injections for both electron and positron beams. As a typical third-generation electron-positron circular collider, the STCF accelerator faces many challenges in both accelerator physics and technology. In this paper, the conceptual design of the STCF accelerator complex is presented, including the ongoing efforts and plans for technological R&D, as well as the required infrastructure. The STCF project aims to secure support from the Chinese central government for its construction during the 15th Five-Year Plan (2026-2030) in China.

physics.acc-ph↗

arXiv2025

Content-Aware Foveated Camera for Multi-Target Tracking

Modern image sensors deliver substantial space-time bandwidth, yet indiscriminate acquisition often overwhelms memory, computation, and downstream perception. We present a content-aware, multi-foveated camera that dynamically reallocates sensing and magnification to multiple regions of interest (ROIs). A phase-only spatial light modulator (SLM) serves as a solid-state, inertia-free beam-steering and lens element, enabling per-frame field-of-view (FOV) reconfiguration and content-aware target tracking. By interleaving frames across foveae, our system preserves a wide-FOV situational context while refreshing each ROI at high rates, thereby reducing data volume without degrading task performance. We constructed a prototype employing single-SLM, single-sensor architecture and demonstrated its application in real-time multi-object tracking with dynamic ROI maintenance across multiple viewpoints. The approach offers a general pathway to integrate detection, tracking, and segmentation algorithms in the acquisition loop, shifting workload from post hoc processing to intelligent capture.

physics.optics↗

arXiv2024

Active Legibility in Multiagent Reinforcement Learning

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others' behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms.

cs.AI↗

arXiv2024

Variational Auto-encoder Based Solutions to Interactive Dynamic Influence Diagrams

Addressing multiagent decision problems in AI, especially those involving collaborative or competitive agents acting concurrently in a partially observable and stochastic environment, remains a formidable challenge. While Interactive Dynamic Influence Diagrams~(I-DIDs) have offered a promising decision framework for such problems, they encounter limitations when the subject agent encounters unknown behaviors exhibited by other agents that are not explicitly modeled within the I-DID. This can lead to sub-optimal responses from the subject agent. In this paper, we propose a novel data-driven approach that utilizes an encoder-decoder architecture, particularly a variational autoencoder, to enhance I-DID solutions. By integrating a perplexity-based tree loss function into the optimization algorithm of the variational autoencoder, coupled with the advantages of Zig-Zag One-Hot encoding and decoding, we generate potential behaviors of other agents within the I-DID that are more likely to contain their true behaviors, even from limited interactions. This new approach enables the subject agent to respond more appropriately to unknown behaviors, thus improving its decision quality. We empirically demonstrate the effectiveness of the proposed approach in two well-established problem domains, highlighting its potential for handling multi-agent decision problems with unknown behaviors. This work is the first time of using neural networks based approaches to deal with the I-DID challenge in agent planning and learning problems.

cs.MA↗

arXiv2024

Inducing Individual Students' Learning Strategies through Homomorphic POMDPs

Optimizing students' learning strategies is a crucial component in intelligent tutoring systems. Previous research has demonstrated the effectiveness of devising personalized learning strategies for students by modelling their learning processes through partially observable Markov decision process (POMDP). However, the research holds the assumption that the student population adheres to a uniform cognitive pattern. While this assumption simplifies the POMDP modelling process, it evidently deviates from a real-world scenario, thus reducing the precision of inducing individual students' learning strategies. In this article, we propose the homomorphic POMDP (H-POMDP) model to accommodate multiple cognitive patterns and present the parameter learning approach to automatically construct the H-POMDP model. Based on the H-POMDP model, we are able to represent different cognitive patterns from the data and induce more personalized learning strategies for individual students. We conduct experiments to show that, in comparison to the general POMDP approach, the H-POMDP model demonstrates better precision when modelling mixed data from multiple cognitive patterns. Moreover, the learning strategies derived from H-POMDPs exhibit better personalization in the performance evaluation.

cs.AI↗

arXiv2022

Intention Recognition for Multiple Agents

Intention recognition is an important step to facilitate collaboration among multiple agents. Existing work mainly focuses on intention recognition in a single-agent setting and uses a descriptive model, e.g. Bayesian networks, in the recognition process. In this article, we develop a new approach of identifying intentions for multiple agents through a clustering algorithm. We first define an intention model for multiple agents of interest. We use a prescriptive approach to model agents' behaviours where their intentions are hidden in the implementation of their plans. We introduce landmarks into the behavioural model therefore enhancing informative features to identify common intentions for multiple agents. Subsequently, we further refine the model by focusing only action sequences in their plan and provide a light model for identifying and comparing their intentions. The new models provide a simple approach of grouping agents' common intentions upon partial plans observed in agents' interactions. Then, we transform the intention recognition into an un-supervised learning problem and adapt a clustering algorithm to group intentions of multiple agents through comparing their behavioural models. We conduct the clustering process by measuring similarity of probability distributions over potential landmarks in intention models so as to discover agents' common intentions. Finally, we examine the new intention recognition approaches in two problem domains. We demonstrate importance of recognising common intentions of multiple agents in achieving their goals and provide experimental results to show performance of the new approaches.

cs.AI↗

arXiv2022

Diversifying Agent's Behaviors in Interactive Decision Models

Modelling other agents' behaviors plays an important role in decision models for interactions among multiple agents. To optimise its own decisions, a subject agent needs to model what other agents act simultaneously in an uncertain environment. However, modelling insufficiency occurs when the agents are competitive and the subject agent can not get full knowledge about other agents. Even when the agents are collaborative, they may not share their true behaviors due to their privacy concerns. In this article, we investigate into diversifying behaviors of other agents in the subject agent's decision model prior to their interactions. Starting with prior knowledge about other agents' behaviors, we use a linear reduction technique to extract representative behavioral features from the known behaviors. We subsequently generate their new behaviors by expanding the features and propose two diversity measurements to select top-K behaviors. We demonstrate the performance of the new techniques in two well-studied problem domains. This research will contribute to intelligent systems dealing with unknown unknowns in an open artificial intelligence world.

cs.AI↗

arXiv2020

Tensor Decomposition for Multi-agent Predictive State Representation

Predictive state representation~(PSR) uses a vector of action-observation sequence to represent the system dynamics and subsequently predicts the probability of future events. It is a concise knowledge representation that is well studied in a single-agent planning problem domain. To the best of our knowledge, there is no existing work on using PSR to solve multi-agent planning problems. Learning a multi-agent PSR model is quite difficult especially with the increasing number of agents, not to mention the complexity of a problem domain. In this paper, we resort to tensor techniques to tackle the challenging task of multi-agent PSR model development problems. By first focusing on a two-agent setting, we construct the system dynamics matrix as a high order tensor for a PSR model, learn the prediction parameters and deduce state vectors directly through two different tensor decomposition methods respectively, and derive the transition parameters via linear regression. Subsequently, we generalize the PSR learning approaches in a multi-agent setting. Experimental results show that our methods can effectively solve multi-agent PSR modelling problems in multiple problem domains.

cs.LG↗

arXiv2019

Modelling Cooperation in a Dynamic Healthcare System

Our research is concerned with studying behavioural changes within a dynamic system, i.e. health care, and their effects on the decision-making process. Evolutionary Game theory is applied to investigate the most probable strategy(ies) adopted by individuals in a finite population based on the interactions among them with an eye to modelling behaviour using the following metrics: cost of investment, cost of management, cost of treatment, reputation benefit for the provider(s), and the gained health benefit for the patient.

cs.GT↗

arXiv2019

Pathways to Good Healthcare Services and Patient Satisfaction: An Evolutionary Game Theoretical Approach

Spending by the UK's National Health Service (NHS) on independent healthcare treatment has been increased in recent years and is predicted to sustain its upward trend with the forecast of population growth. Some have viewed this increase as an attempt not to expand the patients' choices but to privatize public healthcare. This debate poses a social dilemma whether the NHS should stop cooperating with Private providers. This paper contributes to healthcare economic modelling by investigating the evolution of cooperation among three proposed populations: Public Healthcare Providers, Private Healthcare Providers and Patients. The Patient population is included as a main player in the decision-making process by expanding patient's choices of treatment. We develop a generic basic model that measures the cost of healthcare provision based on given parameters, such as NHS and private healthcare providers' cost of investments in both sectors, cost of treatments and gained benefits. A patient's costly punishment is introduced as a mechanism to enhance cooperation among the three populations. Our findings show that cooperation can be improved with the introduction of punishment (patient's punishment) against defecting providers. Although punishment increases cooperation, it is very costly considering the small improvement in cooperation in comparison to the basic model.

physics.soc-ph↗

arXiv2014

Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams

Planning for ad hoc teamwork is challenging because it involves agents collaborating without any prior coordination or communication. The focus is on principled methods for a single agent to cooperate with others. This motivates investigating the ad hoc teamwork problem in the context of individual decision making frameworks. However, individual decision making in multiagent settings faces the task of having to reason about other agents' actions, which in turn involves reasoning about others. An established approximation that operationalizes this approach is to bound the infinite nesting from below by introducing level 0 models. We show that a consequence of the finitely-nested modeling is that we may not obtain optimal team solutions in cooperative settings. We address this limitation by including models at level 0 whose solutions involve learning. We demonstrate that the learning integrated into planning in the context of interactive dynamic influence diagrams facilitates optimal team behavior, and is applicable to ad hoc teamwork.

cs.MA↗

arXiv2014

Exploiting Model Equivalences for Solving Interactive Dynamic Influence Diagrams

We focus on the problem of sequential decision making in partially observable environments shared with other agents of uncertain types having similar or conflicting objectives. This problem has been previously formalized by multiple frameworks one of which is the interactive dynamic influence diagram (I-DID), which generalizes the well-known influence diagram to the multiagent setting. I-DIDs are graphical models and may be used to compute the policy of an agent given its belief over the physical state and others models, which changes as the agent acts and observes in the multiagent setting. As we may expect, solving I-DIDs is computationally hard. This is predominantly due to the large space of candidate models ascribed to the other agents and its exponential growth over time. We present two methods for reducing the size of the model space and stemming its exponential growth. Both these methods involve aggregating individual models into equivalence classes. Our first method groups together behaviorally equivalent models and selects only those models for updating which will result in predictive behaviors that are distinct from others in the updated model space. The second method further compacts the model space by focusing on portions of the behavioral predictions. Specifically, we cluster actionally equivalent models that prescribe identical actions at a single time step. Exactly identifying the equivalences would require us to solve all models in the initial set. We avoid this by selectively solving some of the models, thereby introducing an approximation. We discuss the error introduced by the approximation, and empirically demonstrate the improved efficiency in solving I-DIDs due to the equivalences.

cs.AI↗