collaborators

8 papers

cs.AI2025

Revisiting Model Interpolation for Efficient Reasoning

Taiqiang Wu, Runming Yang, Tao Liu +2

Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging me…

cs.CL2025

Timber: Training-free Instruct Model Refining with Base via Effective Rank

Taiqiang Wu, Runming Yang, Tao Liu +3

Post-training, which elicits a pretrained Base model into the corresponding Instruct model, is widely considered to be superficial. In this work, we first reinforce this hypothesis…

cs.LG2025

PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models

He Xiao, Runming Yang, Qingyao Yang +6

Post-training quantization (PTQ) of large language models (LLMs) to extremely low bit-widths remains challenging due to the fundamental trade-off between computational efficiency a…

cs.CL2025

Shadow-FT: Tuning Instruct Model via Training on Paired Base Model

Taiqiang Wu, Runming Yang, Jiayi Li +4

Large language models (LLMs) consistently benefit from further fine-tuning on various tasks. However, we observe that directly tuning the Instruct (i.e., instruction-tuned) models…

cs.LG2025

Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning

Zhen Li, Yupeng Su, Songmiao Wang +8

Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reaso…

cs.CL2025

Quantization Meets Reasoning: Exploring LLM Low-Bit Quantization Degradation for Mathematical Reasoning

Zhen Li, Yupeng Su, Runming Yang +5

Large language models have achieved significant advancements in complex mathematical reasoning benchmarks, such as MATH. However, their substantial computational requirements prese…