8 papers
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
Liulu He, XuanAng Liu, Juntao Liu +8
Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a ``deployment gap" where Large Language Models cannot be…
Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding
Jianing Li, Zhou Fang, Yijiang Liu +1
Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision.…
MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs
Feilong Chen, Yijiang Liu, Yi Huang +5
We propose MindVL, a multimodal large language model (MLLMs) trained on Ascend NPUs. The training of state-of-the-art MLLMs is often confined to a limited set of hardware platforms…
SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
Hengyu Fang, Yijiang Liu, Yuan Du +2
Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical dep…
BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models
Liulu He, Shenli Zheng, Karwei Sun +6
Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, f…
T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning
Rongyu Zhang, Yijiang Liu, Huanrui Yang +5
Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic arch…