paper-with-me

Papers

Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning

2025-05-26 · Dutao Zhang, Sergey Kovalchuk, YuLong He

Controllable code generation, the ability to synthesize code that follows a specified style while maintaining functionality, remains a challenging task. We propose a two-stage training framework combining contrastive learning and conditional decoding to enable flexible style control. The first stage aligns code style representations with semantic and structural features. In the second stage, we fine-tune a language model (e.g., Flan-T5) conditioned on the learned style vector to guide generation. Our method supports style interpolation and user personalization via lightweight mixing. Compared to prior work, our unified framework offers improved stylistic control without sacrificing code correctness. This is among the first approaches to combine contrastive alignment with conditional decoding for style-guided code generation.

📄 PDF Abstract BibTeX arXiv:2505.19442

Code (1)

zh19980811/Style2Code 공식 구현 pytorch

Tasks

Code GenerationContrastive LearningLanguage ModelingLanguage ModellingRepresentation Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

2023-01-03 · Yifeng Ma, Suzhen Wang, Zhipeng Hu, Changjie Fan 외

Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they stil…

DecoderFace GenerationTalking Face GenerationTalking Head Generation

Controllable 3D Face Generation with Conditional Style Code Diffusion

2023-12-21 · Xiaolong Shen, Jianxin Ma, Chang Zhou, Zongxin Yang

Generating photorealistic 3D faces from given conditions is a challenging task. Existing methods often rely on time-consuming one-by-one optimization approaches, which are not efficient for modeling the same distribution…

Data AugmentationFace Generation

StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads

2024-09-14 · Suzhen Wang, Yifeng Ma, Yu Ding, Zhipeng Hu 외

Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personalized characteristics and therefore fail t…

Face GenerationTalking Face Generation

ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control

2024-06-03 · Shengpeng Ji, Qian Chen, Wen Wang, Jialong Zuo 외

In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic t…

Speech Synthesistext-to-speechText to Speech

PromptTTS: Controllable Text-to-Speech with Text Descriptions

2022-11-22 · Zhifang Guo, Yichong Leng, Yihan Wu, Sheng Zhao 외

Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utili…

DecoderSpeech Synthesistext-to-speechText to Speech