Zobrazeno 1 - 10
of 3 641
pro vyhledávání: '"Pang, Bo"'
Recovering dense and uniformly distributed point clouds from sparse or noisy data remains a significant challenge. Recently, great progress has been made on these tasks, but usually at the cost of increasingly intricate modules or complicated network
Externí odkaz:
http://arxiv.org/abs/2410.17001
The discrete Laplacian operator holds a crucial role in 3D geometry processing, yet it is still challenging to define it on point clouds. Previous works mainly focused on constructing a local triangulation around each point to approximate the underly
Externí odkaz:
http://arxiv.org/abs/2409.06506
Autor:
Zhang, Kexun, Yao, Weiran, Liu, Zuxin, Feng, Yihao, Liu, Zhiwei, Murthy, Rithesh, Lan, Tian, Li, Lei, Lou, Renze, Xu, Jiacheng, Pang, Bo, Zhou, Yingbo, Heinecke, Shelby, Savarese, Silvio, Wang, Huan, Xiong, Caiming
Large language model (LLM) agents have shown great potential in solving real-world software engineering (SWE) problems. The most advanced open-source SWE agent can resolve over 27% of real GitHub issues in SWE-Bench Lite. However, these sophisticated
Externí odkaz:
http://arxiv.org/abs/2408.07060
Autor:
Dong, Hanze, Xiong, Wei, Pang, Bo, Wang, Haoxiang, Zhao, Han, Zhou, Yingbo, Jiang, Nan, Sahoo, Doyen, Xiong, Caiming, Zhang, Tong
We present the workflow of Online Iterative Reinforcement Learning from Human Feedback (RLHF) in this technical report, which is widely reported to outperform its offline counterpart by a large margin in the recent large language model (LLM) literatu
Externí odkaz:
http://arxiv.org/abs/2405.07863
Autor:
Kong, Deqian, Xu, Dehong, Zhao, Minglu, Pang, Bo, Xie, Jianwen, Lizarraga, Andrew, Huang, Yuhao, Xie, Sirui, Wu, Ying Nian
In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of step-wise rewa
Externí odkaz:
http://arxiv.org/abs/2402.04647
Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. However, generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. Recent research suggests that Mixture of Experts (Mo
Externí odkaz:
http://arxiv.org/abs/2312.00968
Autor:
David, Patricia, Rundle-Thiele, Sharyn, Pang, Bo, Knox, Kathy, Parkinson, Joy, Hussenöder, Felix
Introduction: This article outlines a dog owner–focused social marketing pilot program implemented in 2017, which aimed to reduce koala and domestic dog interactions in one local city council in Australia. Literature: Dog attacks and predation are
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A87081
https://ul.qucosa.de/api/qucosa%3A87081/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A87081/attachment/ATT-0/
Autor:
Yun, Tian, Zeng, Zilai, Handa, Kunal, Thapliyal, Ashish V., Pang, Bo, Pavlick, Ellie, Sun, Chen
Decision making via sequence modeling aims to mimic the success of language models, where actions taken by an embodied agent are modeled as tokens to predict. Despite their promising performance, it remains unclear if embodied sequence modeling leads
Externí odkaz:
http://arxiv.org/abs/2311.02171
Autor:
Wang, Yaqing, Wu, Jialin, Dabral, Tanmaya, Zhang, Jiageng, Brown, Geoff, Lu, Chun-Ta, Liu, Frederick, Liang, Yi, Pang, Bo, Bendersky, Michael, Soricut, Radu
Large language models (LLMs) and vision language models (VLMs) demonstrate excellent performance on a wide range of tasks by scaling up parameter counts from O(10^9) to O(10^{12}) levels and further beyond. These large scales make it impossible to ad
Externí odkaz:
http://arxiv.org/abs/2310.12100
We present GeGnn, a learning-based method for computing the approximate geodesic distance between two arbitrary points on discrete polyhedra surfaces with constant time complexity after fast precomputation. Previous relevant methods either focus on c
Externí odkaz:
http://arxiv.org/abs/2309.05613