4 papers
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
Rongxue Li, Meng Yang, Yiru Mao +6
Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, th…
V-CoLA: Vision Token Compression with Linear Attention
Hao Jiang, Yiru Mao, Tianpeng Bu +9
Vision-language models (VLMs) have demonstrated impressive capabilities but suffer from substantial computational overhead, as vision tokens dominate the input sequence. This motiv…
MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models
Lulu Hu, Wenhu Xiao, Xin Chen +4
Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Larg…
La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
Kai Liu, Bowen Xu, Shaoyu Wu +4
Activation sparsity can reduce the computational overhead and memory transfers during the forward pass of Large Language Model (LLM) inference. Existing methods face limitations, e…