Zobrazeno 1 - 10
of 99 035
pro vyhledávání: '"LI, Yang"'
Training visual reinforcement learning agents in a high-dimensional open world presents significant challenges. While various model-based methods have improved sample efficiency by learning interactive world models, these agents tend to be "short-sig
Externí odkaz:
http://arxiv.org/abs/2410.03618
Autor:
Chang, Ernie, Paltenghi, Matteo, Li, Yang, Lin, Pin-Jie, Zhao, Changsheng, Huber, Patrick, Liu, Zechun, Rabatin, Rastislav, Shi, Yangyang, Chandra, Vikas
Scaling laws in language modeling traditionally quantify training loss as a function of dataset size and model parameters, providing compute-optimal estimates but often neglecting the impact of data quality on model generalization. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2410.03083
Autor:
Zhang, Wenbo, Li, Yang, Qiao, Yanyuan, Huang, Siyuan, Liu, Jiajun, Dayoub, Feras, Ma, Xiao, Liu, Lingqiao
Generalist robot manipulation policies (GMPs) have the potential to generalize across a wide range of tasks, devices, and environments. However, existing policies continue to struggle with out-of-distribution scenarios due to the inherent difficulty
Externí odkaz:
http://arxiv.org/abs/2410.01220
AI foundation models have recently demonstrated impressive capabilities across a wide range of tasks. Fine-tuning (FT) is a method of customizing a pre-trained AI foundation model by further training it on a smaller, targeted dataset. In this paper,
Externí odkaz:
http://arxiv.org/abs/2410.00433
Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-spe
Externí odkaz:
http://arxiv.org/abs/2410.01154
Discovering explicit governing equations of stochastic dynamical systems with both (Gaussian) Brownian noise and (non-Gaussian) L\'evy noise from data is chanllenging due to possible intricate functional forms and the inherent complexity of L\'evy mo
Externí odkaz:
http://arxiv.org/abs/2409.19534
Autor:
Li, Yang, Lalani, Inam, Maron, Matthew, Hixon, William, Wang, Biao, Ghoniem, Nasr, Po, Giacomo
We carry out strain-controlled in situ compression experiments of micron-sized tungsten micropillars (W) in the temperature range 300-900K, together with simulations of three-dimensional discrete dislocation dynamics (DDD) on the same scale. Two dist
Externí odkaz:
http://arxiv.org/abs/2409.16987
Omnidirectional depth estimation has received much attention from researchers in recent years. However, challenges arise due to camera soiling and variations in camera layouts, affecting the robustness and flexibility of the algorithm. In this paper,
Externí odkaz:
http://arxiv.org/abs/2409.14766
Autor:
Chang, Ernie, Lin, Pin-Jie, Li, Yang, Zhao, Changsheng, Kim, Daeil, Rabatin, Rastislav, Liu, Zechun, Shi, Yangyang, Chandra, Vikas
Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. However, there are instances where we desire a model that excels in specific areas without markedly compromising performance in other
Externí odkaz:
http://arxiv.org/abs/2409.14705
We connect the problem of properly PAC learning decision trees to the parameterized Nearest Codeword Problem ($k$-NCP). Despite significant effort by the respective communities, algorithmic progress on both problems has been stuck: the fastest known
Externí odkaz:
http://arxiv.org/abs/2409.13096