collaborators

5 papers

cs.LG2026

Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers

Tianyi Li, Zhiqiang Shen

Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the inte…

cs.LG2026

SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training

Shengkun Tang, Zekun Wang, Bo Zheng +7

Structured pruning and knowledge distillation (KD) are typical techniques for compressing large language models, but it remains unclear how they should be applied at pretraining sc…

cs.CV2026

On the Cultural Anachronism and Temporal Reasoning in Vision Language Models

Mukul Ranjan, Prince Jha, Khushboo Kumari +1

Vision-Language Models (VLMs) are increasingly applied to cultural heritage materials, from digital archives to educational platforms. This work identifies a fundamental issue in h…

cs.LG2023

Initializing Models with Larger Ones

Zhiqiu Xu, Yanjie Chen, Kirill Vishniakov +5

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch.…

cs.CV2023

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy

Kirill Vishniakov, Zhiqiang Shen, Zhuang Liu

Modern computer vision offers a great variety of models to practitioners, and selecting a model from multiple options for specific applications can be challenging. Conventionally,…