Zobrazeno 1 - 10
of 1 072
pro vyhledávání: '"WANG Hanqing"'
3D affordance segmentation aims to link human instructions to touchable regions of 3D objects for embodied manipulations. Existing efforts typically adhere to single-object, single-affordance paradigms, where each affordance type or explicit instruct
Externí odkaz:
http://arxiv.org/abs/2412.01550
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have significantly improved the adaptation of LLMs to downstream tasks in a resource-efficient manner. However, in multi-task scenarios, challenges such as training imbalance and the seesaw eff
Externí odkaz:
http://arxiv.org/abs/2410.22782
Autor:
Wang, Hanqing, Chen, Jiahe, Huang, Wensi, Ben, Qingwei, Wang, Tai, Mi, Boyu, Huang, Tao, Zhao, Siheng, Chen, Yilun, Yang, Sizhe, Cao, Peizhou, Yu, Wenye, Ye, Zichao, Li, Jialun, Long, Junfeng, Wang, Zirui, Wang, Huiling, Zhao, Ying, Tu, Zhongying, Qiao, Yu, Lin, Dahua, Pang, Jiangmiao
Recent works have been exploring the scaling laws in the field of Embodied AI. Given the prohibitive costs of collecting real-world data, we believe the Simulation-to-Real (Sim2Real) paradigm is a crucial step for scaling the learning of embodied mod
Externí odkaz:
http://arxiv.org/abs/2407.10943
Object-oriented embodied navigation aims to locate specific objects, defined by category or depicted in images. Existing methods often struggle to generalize to open vocabulary goals without extensive training data. While recent advances in Vision-La
Externí odkaz:
http://arxiv.org/abs/2407.09016
Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory cost. Previous LoRA-based approaches initialize the low-rank matrices with Gaussian distribution and zero values while keeping the origi
Externí odkaz:
http://arxiv.org/abs/2406.09044
Autor:
Ping, Bowen, Wang, Shuo, Wang, Hanqing, Han, Xu, Xu, Yuzhuang, Yan, Yukun, Chen, Yun, Chang, Baobao, Liu, Zhiyuan, Sun, Maosong
Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary to meet complex demands. Recent studies suggest decompos
Externí odkaz:
http://arxiv.org/abs/2406.08903
LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills. Combining existing LoRAs to address new tasks can enhance the reusabil
Externí odkaz:
http://arxiv.org/abs/2402.11455
Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users. As style-specific article-headline pairs are scarce, previous researches focus
Externí odkaz:
http://arxiv.org/abs/2310.17743
VLN-CE is a recently released embodied task, where AI agents need to navigate a freely traversable environment to reach a distant target location, given language instructions. It poses great challenges due to the huge space of possible strategies. Dr
Externí odkaz:
http://arxiv.org/abs/2308.07498
Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. It becomes increasingly crucial in the field of embodied AI, with potential applications in autonomous navigation, search and rescue, and
Externí odkaz:
http://arxiv.org/abs/2304.03047