paper-with-me

홈 › Papers

Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline

2026-02-26 · Wenxuan Song, Jiayi Chen, Xiaoquan Sun, Huashuo Lei, Yikai Qin, Wei Zhao, Pengxiang Ding, Han Zhao, Tongxin Wang, Pengxu Hou, Zhide Zhong, Haodong Yan, Donglin Wang, Jun Ma, Haoang Li arxiv

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To improve the practicality of VLAs, we propose a comprehensive benchmark and an improved baseline. First, we propose CEBench, a new benchmark spanning diverse embodiments in both simulation and the real world with consideration of domain randomization. We collect 14.4k simulated trajectories and 1.6k real-world expert-curated trajectories to support training on CEBench. Second, using CEBench as our testbed, we study three critical aspects of VLAs' practicality and offer several key findings. Informed by these findings, we introduce LLaVA-VLA, a lightweight yet powerful VLA designed for practical deployment on consumer-grade GPUs. Architecturally, it integrates a compact VLM backbone with multi-view perception, proprioceptive tokenization, and action chunking. To eliminate reliance on costly pre-training, LLaVA-VLA adopts a two-stage training paradigm including post-training and fine-tuning. Furthermore, LLaVA-VLA extends the action space to unify navigation and manipulation. Experiments across embodiments demonstrate the capabilities of generalization and versatility of LLaVA-VLA , while real-world mobile manipulation experiments establish it as the first end-to-end VLA model for mobile manipulation. We will open-source all datasets, codes, and checkpoints upon acceptance to foster reproducibility and future research.

📄 PDF Abstract BibTeX arXiv:2602.22663

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality

2024-06-13 · Tianle Zhang, Langtian Ma, Yuchen Yan, Yuchen Zhang 외

Recent text-to-video (T2V) technology advancements, as demonstrated by models such as Gen2, Pika, and Sora, have significantly broadened its applicability and popularity. Despite these strides, evaluating these models po…

DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition

2024-04-23 · Haozhe Cheng, Cheng Ju, Haicheng Wang, Jinxiang Liu 외

As one of the fundamental video tasks in computer vision, Open-Vocabulary Action Recognition (OVAR) recently gains increasing attention, with the development of vision-language pre-trainings. To enable generalization of …

Action RecognitionDenoisingOpen Vocabulary Action Recognition

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

2025-04-03 · Mateusz Pach, Shyamgopal Karthik, Quentin Bouniot, Serge Belongie 외

Sparse Autoencoders (SAEs) have recently been shown to enhance interpretability and steerability in Large Language Models (LLMs). In this work, we extend the application of SAEs to Vision-Language Models (VLMs), such as …

Judging Chemical Reaction Practicality From Positive Sample only Learning

2019-04-22 · Shu Jiang, Zhuosheng Zhang, Hai Zhao, Jiangtong Li 외

Chemical reaction practicality is the core task among all symbol intelligence based chemical information processing, for example, it provides indispensable clue for further automatic synthesis route inference. Considerin…

Labels Matter More Than Models: Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection

2025-11-20 · Zhijie Zhong, Zhiwen Yu, Kaixiang Yang, Yongheng Liu 외 arxiv

Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity. Consequently, current research predominantly focuses on Unsupervised Time-series Anomaly Detection (UTAD), relying …

Time Series Anomaly Detection