Zobrazeno 1 - 10
of 164
pro vyhledávání: '"Liang Yitao"'
Vision-language models (VLMs) have excelled in multimodal tasks, but adapting them to embodied decision-making in open-world environments presents challenges. A key issue is the difficulty in smoothly connecting individual entities in low-level obser
Externí odkaz:
http://arxiv.org/abs/2410.17856
Low-Dimension-to-High-Dimension (LDHD) generalization is a special case of Out-of-Distribution (OOD) generalization, where the training data are restricted to a low-dimensional subspace of the high-dimensional testing space. Assuming that each instan
Externí odkaz:
http://arxiv.org/abs/2410.08898
Large Language Models (LLMs) trained on massive corpora have shown remarkable success in knowledge-intensive tasks. Yet, most of them rely on pre-stored knowledge. Inducing new general knowledge from a specific environment and performing reasoning wi
Externí odkaz:
http://arxiv.org/abs/2410.08126
Quantum computing is an emerging field recognized for the significant speedup it offers over classical computing through quantum algorithms. However, designing and implementing quantum algorithms pose challenges due to the complex nature of quantum m
Externí odkaz:
http://arxiv.org/abs/2410.07961
Autor:
Ye, Haotian, Lin, Haowei, Han, Jiaqi, Xu, Minkai, Liu, Sheng, Liang, Yitao, Ma, Jianzhu, Zou, James, Ermon, Stefano
Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing methods, t
Externí odkaz:
http://arxiv.org/abs/2409.15761
Autor:
Wang, Zihao, Cai, Shaofei, Mu, Zhancun, Lin, Haowei, Zhang, Ceyao, Liu, Xuejie, Li, Qing, Liu, Anji, Ma, Xiaojian, Liang, Yitao
This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control command directl
Externí odkaz:
http://arxiv.org/abs/2407.00114
Autor:
Zhang, Haotian, Zhou, Junting, Lin, Haowei, Ye, Hang, Zhu, Jianhua, Wang, Zihao, Gao, Liangcai, Wang, Yizhou, Liang, Yitao
Continual Learning (CL) poses a significant challenge in Artificial Intelligence, aiming to mirror the human ability to incrementally acquire knowledge and skills. While extensive research has focused on CL within the context of classification tasks,
Externí odkaz:
http://arxiv.org/abs/2406.04584
Autor:
Ahmed, Kareem, Teso, Stefano, Morettin, Paolo, Di Liello, Luca, Ardino, Pierfrancesco, Gobbi, Jacopo, Liang, Yitao, Wang, Eric, Chang, Kai-Wei, Passerini, Andrea, Broeck, Guy Van den
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the independence of the outputs. These outputs, however, jointly encode an o
Externí odkaz:
http://arxiv.org/abs/2405.07387
We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In pa
Externí odkaz:
http://arxiv.org/abs/2403.05313
Causality has been combined with machine learning to produce robust representations for domain generalization. Most existing methods of this type require massive data from multiple domains to identify causal features by cross-domain variations, which
Externí odkaz:
http://arxiv.org/abs/2402.18910