1 citations · 1 across the 10 of their papers we have counts for
11 papers
Refining Open-Vocabulary Semantic Segmentation via Regional Semantics and Visual Prototypes
Aijing Yu, Zhengbo Wang, Lijun Sheng +2
Contrastive Language-Image Pre-training (CLIP) has shown superior performance in the image-level open-vocabulary classification task, benefiting from its powerful alignment of visu…
ABot-N1: Toward a General Visual Language Navigation Foundation Model
Ruiyan Gong, Yingnan Guo, Junjun Hu +43
Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse embodied tasks. Current approaches typica…
AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation
Kai Yang, Zedong Chu, Yingnan Guo +6
While Vision-Language-Action (VLA) models have been demonstrated possessing strong zero-shot generalization for robot control, their massive parameter sizes typically necessitate c…
Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation
Zhengbo Wang, Jian Liang, Ran He +2
Modern optimizers like Adam and Muon are central to training large language models, but their reliance on first- and second-order momenta introduces significant memory overhead, wh…
ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation
Zedong Chu, Shichao Xie, Xiaolong Wu +41
Embodied navigation has long been fragmented by task-specific architectures. We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a ``Grand U…
A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation
Haonan He, Jingqi Ye, Minglei Li +4
Low-Rank Adaptation (LoRA) is a fundamental parameter-efficient fine-tuning method that balances efficiency and performance in large-scale neural networks. However, the proliferati…
CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
Kai Yang, Tianlin Zhang, Zhengbo Wang +4
Generalizing local navigation policies across diverse robot morphologies is a critical challenge. Progress is often hindered by the need for costly and embodiment-specific data, th…
Towards Compatible Fine-tuning for Vision-Language Model Updates
Zhengbo Wang, Jian Liang, Lijun Sheng +3
So far, efficient fine-tuning has become a popular strategy for enhancing the capabilities of foundation models on downstream tasks by learning plug-and-play modules. However, exis…
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
Zhengbo Wang, Jian Liang, Ran He +2
Low-rank adaptation, also known as LoRA, has emerged as a prominent method for parameter-efficient fine-tuning of foundation models. Despite its computational efficiency, LoRA stil…
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Zhengbo Wang, Jian Liang, Lijun Sheng +3
Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods,…
Self-training solutions for the ICCV 2023 GeoNet Challenge
Lijun Sheng, Zhengbo Wang, Jian Liang
GeoNet is a recently proposed domain adaptation benchmark consisting of three challenges (i.e., GeoUniDA, GeoImNet, and GeoPlaces). Each challenge contains images collected from th…