arXiv subjects

Jingyue Yang

Publications and source records attributed to Jingyue Yang.

6 recordsLinked to original sources

arXiv2026

Improving Code Translation with Syntax-Guided and Semantic-aware Preference Optimization

LLMs have shown immense potential for code translation, yet they often struggle to ensure both syntactic correctness and semantic consistency. While preference-based learning offers a promising alignment strategy, it is hindered by unreliable semantic rewards derived from sparse test cases or restrictive reference translations. We argue that a robust semantic reward for code translation must be derived directly from the source code. In this paper, we propose CTO to improve code translation with syntax-guided and semantic-aware preference optimization. Through contrastive learning, we train a cross-lingual semantic model to directly assess functional equivalence between source and translated code. By formulating code translation as a multi-objective optimization problem, this robust semantic signal is seamlessly unified with compiler-based syntactic feedback within the direct preference optimization framework. Extensive experiments on C++, Java, and Python translations demonstrate that CTO significantly outperforms existing baselines and alternative preference optimization strategies.

cs.AI↗

arXiv2026

Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks

The proficiency of Large Language Models (LLMs) in coding tasks is often a reflection of their extensive pre-training corpora, which typically collapses when confronted with previously unfamiliar programming languages. Departing from data-intensive finetuning, we investigate the paradigm of Inference-time Language Acquisition (ILA), where an LLM masters an unfamiliar language through dynamic interaction with limited external resources. In this paper, we propose ILA-agent, a general ILA framework that equips LLMs with a set of behavioral primitives. By modeling essential human-like behaviors as a suite of tools, ILA-agent enables LLMs to incrementally explore, apply, and verify language knowledge through structured interactions with the official documentation and execution environment. To provide a rigorous evaluation in a low-resource setting, we construct Cangjie-bench, a multi-task benchmark based on the novel statically-typed language Cangjie. We instantiate ILA-agent for Cangjie and evaluate its performance across code generation, translation, and program repair tasks. Results using diverse LLMs demonstrate that ILA-agent significantly outperforms retrieval-augmented baselines. Further analysis of agent trajectories characterizes the emergent behavior patterns while highlighting persisting performance gaps.

cs.CL↗

arXiv2026

Bootstrapping Code Translation with Weighted Multilanguage Exploration

Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual reinforcement learning (RL) training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablation studies validating the effectiveness of both bootstrapping and weighting components.

cs.SE↗

arXiv2019

Global well-posedness of advective Lotka-Volterra competition systems with nonlinear diffusion

This paper investigates the global well-posedness of a class of reaction-advection-diffusion models with nonlinear diffusion and Lotka-Volterra dynamics. We prove the existence and uniform boundedness of the global-in-time solutions to the fully parabolic systems under certain growth conditions on the diffusion and sensitivity functions. Global existence and uniform boundedness of the corresponding parabolic-elliptic system are also obtained. Our results suggest that attraction (positive taxis) inhibits blowups in Lotka-Volterra competition systems.

math.AP↗

arXiv2017

Time-periodic and stable patterns of a two-competing-species Keller-Segel chemotaxis model: effect of cellular growth

This paper investigates the formation of time--periodic and stable patterns of a two--competing--species Keller--Segel chemotaxis model with a focus on the effect of cellular growth. We carry out rigorous Hopf bifurcation analysis to obtain the bifurcation values, spatial profiles and time period associated with these oscillating patterns. Moreover, the stability of the periodic solutions is investigated and it provides a selection mechanism of stable time--periodic mode which suggests that only large domains support the formation of these periodic patterns. Another main result of this paper reveals that cellular growth is responsible for the emergence and stabilization of the oscillating patterns observed in the $3\times3$ system, while the system admits a Lyapunov functional in the absence of cellular growth. Global existence and boundedness of the system in 2D are proved thanks to this Lyapunov functional. Finally, we provide some numerical simulations to illustrate and support our theoretical findings.

math.AP↗

arXiv2015

Global existence and steady states of a two competing species Keller-Segel chemotaxis model

We study an one{dimensional quasilinear system proposed by J. Tello and M. Winkler [19] which models the population dynamics of two competing species attracted by the same chemical. The kinetics terms of the interacting species are chosen to be the Lotka{Volterra type. We prove the existence of global bounded and classical solutions for all chemoattraction rates. Under homogeneous Neumann boundary conditions, we establish the existence of nonconstant steady states by local bifurcation theory. The stability of the bifurcating solutions is also obtained when the diffusivity of both species is large. Finally, we perform extensive numerical studies to demonstrate the formation of stable positive steady states with various interesting spatial structures.

math.AP↗