12 papers
Adaptive Bregman Proximal Stochastic Gradient with a Stabilized Barzilai--Borwein Step Size
Chenhan Jin, Shengze Xu, Binghui Xie +4
Bregman proximal stochastic gradient (BPSG) methods bring variance-reduced composite optimization to objectives whose geometry is poorly captured by Euclidean smoothness. Their per…
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
Zichao Yu, Chengzhi Yu, Shengze Xu +4
On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repet…
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
Junkai Lin, Junkai Chen, Siqi Hou +5
Multimodal large language models (MLLMs) exhibit strong vision--language capabilities but may also memorize and disclose sensitive information. Machine unlearning seeks to remove d…
OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
Chenhan Jin, Shengze Xu, Qingsong Wang +3
Data pruning (DP), as an oft-stated strategy to alleviate heavy training burdens, reduces the volume of training samples according to a well-defined pruning method while striving f…
Relative Score Policy Optimization for Diffusion Language Models
Zichao Yu, Shengze Xu, Bingqing Jiang +2
Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. R…
EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
Xavier Hu, Jinxiang Xia, Shengze Xu +13
Long-horizon planning is widely recognized as a core capability of autonomous LLM-based agents; however, current evaluation frameworks suffer from being largely episodic, domain-sp…