3 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…