Showing 2026Show all
2 papers · 1 filter
cs.LG2026
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…
cs.CV2026
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.…