collaborators

6 papers

cs.CL2026

InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning

Junyou Su, He Zhu, Xiao Luo +6

Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data se…

cs.CL2025

Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

Zhiwen Ruan, Yixia Li, He Zhu +4

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. How…

cs.LG2025

Anchored Supervised Fine-Tuning

He Zhu, Junyou Su, Peng Lai +4

Post-training of large language models involves a fundamental trade-off between supervised fine-tuning (SFT), which efficiently mimics demonstrations but tends to memorize, and rei…

cs.CL2025

TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation

He Zhu, Zhiwen Ruan, Junyou Su +4

High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG…

cs.CL2025

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models

He Zhu, Junyou Su, Minxin Chen +4

In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze and evaluate planning maps, despite the critical importance of these v…

cs.CL2025

LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy

Zhiwen Ruan, Yixia Li, He Zhu +5

Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages. Recent approaches have leveraged multilingu…