activity
20242026
collaborators

9 papers

cs.LG2026

OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers

Siyuan Li, Jiabao Pan, Yumou Liu +9

Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the land…

cs.CE2026

TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA Modeling

Qirong Yang, Yucheng Guo, Zicheng Liu +7

The modeling of genomic sequences presents unique challenges due to their length and structural complexity. Traditional sequence models struggle to capture long-range dependencies…

cs.CV2026

MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding

Xin Jin, Siyuan Li, Siyong Jian +2

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language mo…

cs.LG2025

Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification

Zicheng Liu, Siyuan Li, Zhiyuan Chen +6

The interactions between DNA, RNA, and proteins are fundamental to biological processes, as illustrated by the central dogma of molecular biology. Although modern biological pre-tr…

q-bio.GN2025

MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging

Siyuan Li, Kai Yu, Anna Wang +7

Modeling genomic sequences faces two unsolved challenges: the information density varies widely across different regions, while there is no clearly defined minimum vocabulary unit.…

cs.LG2025

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

Zedong Wang, Siyuan Li, Dan Xu

Despite the promise of Multi-Task Learning in leveraging complementary knowledge across tasks, existing multi-task optimization (MTO) techniques remain fixated on resolving conflic…