Institution profile

Zuoyebang Education Technology

Industry researchasia · cn
Official website
Research library10linked papers
Opportunities0open roles
Selected work

Representative Papers

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Jun 30, 2026

Flow Matching in speech synthesis suffers from high inference latency and timbre leakage. This work proposes a unified guidance framework that, for the first time, jointly integrates data-level and model-level guidance. By leveraging heterogeneous data augmentation to disentangle linguistic content from acoustic residuals, and combining trajectory correction with an intrinsic guidance objective, the method distills conditional information directly into network weights to optimize the inference trajectory. Notably, it eliminates the need for Classifier-Free Guidance, substantially reducing computational overhead. The approach achieves nearly threefold faster inference while preserving high timbre fidelity and significantly outperforms state-of-the-art baselines in speaker similarity.

0 citationsRead paper

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning

May 27, 2026

This work addresses the challenge that large language models struggle to reliably self-verify their solutions in mathematical reasoning, and existing approaches suffer from high training costs and low efficiency. The authors propose a unified training framework that integrates problem solving and verification into a single generation process, introducing a Dynamic Reference Model Update (DRMU) mechanism combined with reward-based reinforcement learning for joint optimization. This approach significantly enhances self-verification performance, outperforming state-of-the-art methods across multiple mathematical benchmarks while reducing training time to only 51%–71% of prior approaches. The study also reveals the critical role of model scale in verification capability.

0 citationsRead paper
Recent publications

Latest Papers

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Jun 30, 2026

Flow Matching in speech synthesis suffers from high inference latency and timbre leakage. This work proposes a unified guidance framework that, for the first time, jointly integrates data-level and model-level guidance. By leveraging heterogeneous data augmentation to disentangle linguistic content from acoustic residuals, and combining trajectory correction with an intrinsic guidance objective, the method distills conditional information directly into network weights to optimize the inference trajectory. Notably, it eliminates the need for Classifier-Free Guidance, substantially reducing computational overhead. The approach achieves nearly threefold faster inference while preserving high timbre fidelity and significantly outperforms state-of-the-art baselines in speaker similarity.

0 citationsRead paper

FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning

May 27, 2026

This work addresses the challenge that large language models struggle to reliably self-verify their solutions in mathematical reasoning, and existing approaches suffer from high training costs and low efficiency. The authors propose a unified training framework that integrates problem solving and verification into a single generation process, introducing a Dynamic Reference Model Update (DRMU) mechanism combined with reward-based reinforcement learning for joint optimization. This approach significantly enhances self-verification performance, outperforming state-of-the-art methods across multiple mathematical benchmarks while reducing training time to only 51%–71% of prior approaches. The study also reveals the critical role of model scale in verification capability.

0 citationsRead paper