12 papers
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
Siyuan Li, Youyuan Zhang, Ruitong Liu +2
Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and mini…
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
Zhuo Li, Guodong Du, Zesheng Shi +5
Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities with strict memory and inferen…
Modality-Decoupled Online Recursive Editing
Siyuan Li, Youyuan Zhang, Fangming Liu +1
Online model editing for multimodal large language models (MLLMs) requires assimilating a stream of corrections under tight compute and memory budgets. Yet editors developed for te…
Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
Yucong Huang, Xiucheng Li, Kaiqi Zhao +1
Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General Preference Model (GPM) address…
Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
Zhuoyuan Hao, Zhuo Li, Wu Li +3
Test-time compute allocation in large reasoning models (LRMs) is widely used and has applications in mathematical problem solving, code synthesis, and planning. Recent work has add…
FP=xINT:Representing Neural Networks via Low-Bit Series Basis Functions
Boyang Zhang, Daning Cheng, Yunquan Zhang +3
Post-Training Quantization (PTQ) converts pre-trained Full-Precision (FP) models into quantized versions without training. While existing methods reduce size and computational cost…