papers

Publications (12)

cs.AI2025

HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation

Feng Xiong, Hongling Xu, Yifei Wang +3

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies…

cs.AI2026

Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis

Yongxian Wei, Yilin Zhao, Zixuan Hu +7

Data synthesis for training large reasoning models offers a scalable alternative to limited, human-curated datasets, enabling the creation of high-quality data. However, existing a…

cs.LG2024

Learn To Learn More Precisely

Runxi Cheng, Yongxian Wei, Xianglong He +5

Meta-learning has been extensively applied in the domains of few-shot learning and fast adaptation, achieving remarkable performance. While Meta-learning methods like Model-Agnosti…

cs.CL2026

Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory

Runxi Cheng, Yuchen Guan, Yongxian Wei +7

Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-trainin…

cs.CV2025

Enhancing Logits Distillation with Plug\&Play Kendall's Ranking Loss

Yuchen Guan, Runxi Cheng, Kang Liu +1

Knowledge distillation typically minimizes the Kullback-Leibler (KL) divergence between teacher and student logits. However, optimizing the KL divergence can be challenging for the…

cs.CL2026

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

Chi Zhang, Mengqi Zhang, Xiaotian Ye +5

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing appr…

cs.CL2025

Mixture of Neuron Experts

Runxi Cheng, Yuchen Guan, Yucheng Ding +6

In this work, we first explore whether the parameters activated by the MoE layer remain highly sparse at inference. We perform a sparsification study on several representative MoE…

cs.LG2025

Multi-Task Model Merging via Adaptive Weight Disentanglement

Feng Xiong, Runxi Cheng, Wang Chen +4

Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For exam…

cs.CV2025

GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splatting

Qianpu Sun, Changyong Shu, Sifan Zhou +6

Weakly-supervised 3D occupancy perception is crucial for vision-based autonomous driving in outdoor environments. Previous methods based on NeRF often face a challenge in balancing…

cs.LG2026

Closed-Form Spectral Regularization for Multi-Task Model Merging

Yongxian Wei, Runxi Cheng, Xingxuan Zhang +4

Model merging combines several independently fine-tuned experts into a single multi-task model without any training data, reducing the storage, serving, and decentralized-developme…

cs.LG2025

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors

Runxi Cheng, Feng Xiong, Yongxian Wei +2

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between…

cs.AI2026

OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging

Yongxian Wei, Runxi Cheng, Weike Jin +7

Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert m…