collaborators

6 papers

cs.RO2026

VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness

Zihao Zheng, Zhihao Mao, Xingyue Zhou +9

Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising…

cs.RO2026

FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching

Zihao Zheng, Xingyue Zhou, Zhihao Mao +7

Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a promising training-free strategy…

cs.RO2026

HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

Zihao Zheng, Zhihao Mao, Sicheng Tian +8

Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative Decoding (SD) is a promising accelerat…

cs.RO2026

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

Zihao Zheng, Zhihao Mao, Maoliang Li +6

Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization strategy that can boost inf…

cs.MM2026

2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness

Zihao Zheng, Sicheng Tian, Zhihao Mao +8

Vision-Language-Action (VLA) models have emerged as the mainstream of embodied intelligence. Recent VLA models have expanded their input modalities from 2D-only to 2D+3D paradigms,…

cs.LG2026

MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search

Minkyoung Cho, Insu Jang, Shuowei Jin +5

Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training d…