9 papers
FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence
Guoan Wan, Tianyu Chen, Fangzheng Feng +2
Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory cost…
Towards Long-window Anchoring in Vision-Language Model Distillation
Haoyi Zhou, Shuo Li, Tianyu Chen +3
While large vision-language models (VLMs) demonstrate strong long-context understanding, their prevalent small branches fail on linguistics-photography alignment for a limited wind…
Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set
Chengwei Wu, Li Du, Hanyu Zhao +4
Scaling the amount of data used for supervied fine-tuning(SFT) does not guarantee the proportional gains in model performance, highlighting a critical need to understand what makes…
OmniArch: Building Foundation Model For Scientific Computing
Tianyu Chen, Haoyi Zhou, Ying Li +5
Foundation models have revolutionized language modeling, while whether this success is replicated in scientific computing remains unexplored. We present OmniArch, the first prototy…
Galaxy Walker: Geometry-aware VLMs For Galaxy-scale Understanding
Tianyu Chen, Xingcheng Fu, Yisen Gao +5
Modern vision-language models (VLMs) develop patch embedding and convolution backbone within vector space, especially Euclidean ones, at the very founding. When expanding VLMs to a…
FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers
Tianyu Chen, Haoyi Zhou, Ying Li +5
Fourier Neural Operators (FNO) have emerged as promising solutions for efficiently solving partial differential equations (PDEs) by learning infinite-dimensional function mappings…