arXiv subjects

Yuxin Ye

Publications and source records attributed to Yuxin Ye.

8 recordsLinked to original sources

arXiv2026

Stochastic Optimal Control Problem under Inside Information

This paper is concerned with a stochastic optimal control problem under inside information. The control process depends on an $\mathcal{F}_{T_0}$-measurable random variable $Y$, representing the static inside information, and is adapted to the enlarged filtration generated by the underlying Brownian motion and the random variable $Y$. Accordingly, the traditional stochastic integral fails to be well-defined in this non-adapted setting; we adopt forward integrals to formulate the stochastic integral terms in the system. By means of the Donsker delta function, the original controlled system is transformed into a $y$-parameterized system. We further establish the existence of solutions to forward \textit{stochastic differential equations} (SDEs), and prove the uniqueness of solutions via flow transformation techniques. Under a Gaussian assumption on $Y$, we derive both necessary and sufficient optimality conditions for the aforementioned control problem. Subsequently, we formulate the \textit{linear-quadratic} (LQ) optimal control problem under inside information. Through the $y$-parameterized transformation, the original problem is converted into an LQ control problem with random coefficients. A numerical example for the LQ case is provided at the end to validate our theoretical findings.

math.OC↗

arXiv2026

CMI-RewardBench: Evaluating Music Reward Models with Compositional Multimodal Instruction

While music generation models have evolved to handle complex multimodal inputs mixing text, lyrics, and reference audio, evaluation mechanisms have lagged behind. In this paper, we bridge this critical gap by establishing a comprehensive ecosystem for music reward modeling under Compositional Multimodal Instruction (CMI), where the generated music may be conditioned on text descriptions, lyrics, and audio prompts. We first introduce CMI-Pref-Pseudo, a large-scale preference dataset comprising 110k pseudo-labeled samples, and CMI-Pref, a high-quality, human-annotated corpus tailored for fine-grained alignment tasks. To unify the evaluation landscape, we propose CMI-RewardBench, a unified benchmark that evaluates music reward models on heterogeneous samples across musicality, text-music alignment, and compositional instruction alignment. Leveraging these resources, we develop CMI reward models (CMI-RMs), a parameter-efficient reward model family capable of processing heterogeneous inputs. We evaluate their correlation with human judgment scores on musicality and alignment on CMI-Pref along with previous datasets. Further experiments demonstrate that CMI-RM not only correlates strongly with human judgments, but also enables effective inference-time scaling via top-k filtering. Code is available at GitHub (https://github.com/Haiwen-Xia/CMI-RewardBench). Model weights: CMI-RM (https://huggingface.co/HaiwenXia/CMI-RM). Datasets: CMI-Pref-Pseudo (https://huggingface.co/datasets/HaiwenXia/cmi-pref-pseudo) and CMI-Pref (https://huggingface.co/datasets/HaiwenXia/cmi-pref)

cs.SD↗

arXiv2025

Linear-Quadratic Non-zero Sum Differential Game with Asymmetric Delayed Information

This paper is concerned with a linear-quadratic non-zero sum differential game with asymmetric delayed information. To be specific, two players exist time delays simultaneously which are different, leading the dynamical system being an asymmetric information structure. By virtue of stochastic maximum principle, the stochastic Hamiltonian system is given which is a delayed forward-backward stochastic differential equation. Utilizing discretisation approach and backward iteration technique, we establish the relationship between forward and backward processes under asymmetric delayed information structure and obtain the state-estimate feedback Nash equilibrium of our problem.

math.OC↗

arXiv2025

Banishing LLM Hallucinations Requires Rethinking Generalization

Despite their powerful chat, coding, and reasoning abilities, Large Language Models (LLMs) frequently hallucinate. Conventional wisdom suggests that hallucinations are a consequence of a balance between creativity and factuality, which can be mitigated, but not eliminated, by grounding the LLM in external knowledge sources. Through extensive systematic experiments, we show that these traditional approaches fail to explain why LLMs hallucinate in practice. Specifically, we show that LLMs augmented with a massive Mixture of Memory Experts (MoME) can easily memorize large datasets of random numbers. We corroborate these experimental findings with a theoretical construction showing that simple neural networks trained to predict the next token hallucinate when the training loss is above a threshold as it usually does in practice when training on internet scale data. We interpret our findings by comparing against traditional retrieval methods for mitigating hallucinations. We use our findings to design a first generation model for removing hallucinations -- Lamini-1 -- that stores facts in a massive mixture of millions of memory experts that are retrieved dynamically.

cs.CL↗

arXiv2025

Dual-Alignment Knowledge Retention for Continual Medical Image Segmentation

Continual learning in medical image segmentation involves sequential data acquisition across diverse domains (e.g., clinical sites), where task interference between past and current domains often leads to catastrophic forgetting. Existing continual learning methods fail to capture the complex dependencies between tasks. We introduce a novel framework that mitigates forgetting by establishing and enhancing complex dependencies between historical data and the network in the present task. Our framework features a dual-alignment strategy, the cross-network alignment (CNA) module aligns the features extracted from the bottleneck layers of the current and previous networks, respectively, while the cross-representation alignment (CRA) module aligns the features learned by the current network from historical buffered data and current input data, respectively. Implementing both types of alignment is a non-trivial task. To address this, we further analyze the linear and nonlinear forms of the well-established Hilbert-Schmidt Independence Criterion (HSIC) and deliberately design feature mapping and feature pairing blocks within the CRA module. Experiments on medical image segmentation task demonstrate our framework's effectiveness in mitigating catastrophic forgetting under domain shifts.

eess.IV↗

arXiv2024

Propulsion Contribution from Individual Filament in Flagellar Bundle

Flagellated microorganisms overcome the low-Reynolds-number time reversibility by rotating helical flagella. For peritrichous bacteria, such as Escherichia coli, the randomly distributed flagellar filaments align along the same direction to form a bundle, facilitating complex locomotive strategies. To understand the process of flagella bundling, especially the propulsion force, we develop a multi-functional macroscopic experimental system and employ advanced numerical simulations for verification. Flagella arrangements and phase differences between helices are investigated, revealing the variation in propulsion contribution from the individual helix. Numerically, we build a time-dependent model to match the bundling process and study the influence of hydrodynamic interactions. Surprisingly, it is found that the total propulsion generated by a bundle of two filaments is constant at various phase differences between the helices. However, the difference between the propulsion from each helix is significantly affected by the phase difference, and only one of the helices is responsible for the total propulsion at a phase difference equals to pi. Through our experimental and computational results, we provide a new model considering the propulsion contribution of each filament to better understand microbial locomotion mechanisms, especially on the wobbling behavior of the cell. Our work also sheds light on the design and control of artificial microswimmers.

cond-mat.soft↗

arXiv2023

Ontology Revision based on Pre-trained Language Models

Ontology revision aims to seamlessly incorporate a new ontology into an existing ontology and plays a crucial role in tasks such as ontology evolution, ontology maintenance, and ontology alignment. Similar to repair single ontologies, resolving logical incoherence in the task of ontology revision is also important and meaningful, because incoherence is a main potential factor to cause inconsistency and reasoning with an inconsistent ontology will obtain meaningless answers.To deal with this problem, various ontology revision approaches have been proposed to define revision operators and design ranking strategies for axioms in an ontology. However, they rarely consider axiom semantics which provides important information to differentiate axioms. In addition, pre-trained models can be utilized to encode axiom semantics, and have been widely applied in many natural language processing tasks and ontology-related ones in recent years.Therefore, in this paper, we study how to apply pre-trained models to revise ontologies. We first define four scoring functions to rank axioms based on a pre-trained model by considering various information from an ontology. Based on the functions, an ontology revision algorithm is then proposed to deal with unsatisfiable concepts at once. To improve efficiency, an adapted revision algorithm is designed to deal with unsatisfiable concepts group by group. We conduct experiments over 19 ontology pairs and compare our algorithms and scoring functions with existing ones. According to the experiments, our algorithms could achieve promising performance.

cs.AI↗

arXiv2023

LAVSS: Location-Guided Audio-Visual Spatial Audio Separation

Existing machine learning research has achieved promising results in monaural audio-visual separation (MAVS). However, most MAVS methods purely consider what the sound source is, not where it is located. This can be a problem in VR/AR scenarios, where listeners need to be able to distinguish between similar audio sources located in different directions. To address this limitation, we have generalized MAVS to spatial audio separation and proposed LAVSS: a location-guided audio-visual spatial audio separator. LAVSS is inspired by the correlation between spatial audio and visual location. We introduce the phase difference carried by binaural audio as spatial cues, and we utilize positional representations of sounding objects as additional modality guidance. We also leverage multi-level cross-modal attention to perform visual-positional collaboration with audio features. In addition, we adopt a pre-trained monaural separator to transfer knowledge from rich mono sounds to boost spatial audio separation. This exploits the correlation between monaural and binaural channels. Experiments on the FAIR-Play dataset demonstrate the superiority of the proposed LAVSS over existing benchmarks of audio-visual separation. Our project page: https://yyx666660.github.io/LAVSS/.

cs.SD↗