Zobrazeno 1 - 10
of 13 397
pro vyhledávání: '"Weiyu An"'
Autor:
Jin, Emily, Huang, Zhuoyi, Fränken, Jan-Philipp, Liu, Weiyu, Cha, Hannah, Brockbank, Erik, Wu, Sarah, Zhang, Ruohan, Wu, Jiajun, Gerstenberg, Tobias
Reconstructing past events requires reasoning across long time horizons. To figure out what happened, we need to use our prior knowledge about the world and human behavior and draw inferences from various sources of evidence including visual, languag
Externí odkaz:
http://arxiv.org/abs/2410.01926
Ambiguities are common in human-robot interaction, especially when a robot follows user instructions in a large collocated space. For instance, when the user asks the robot to find an object in a home environment, the object might be in several place
Externí odkaz:
http://arxiv.org/abs/2409.17004
Multi-stage amplifiers are widely applied in analog circuits. However, their large number of components, complex transfer functions, and intricate pole-zero distributions necessitate extensive manpower for derivation and param sizing to ensure their
Externí odkaz:
http://arxiv.org/abs/2409.14739
Autor:
Chen, Weiyu, Kwok, James
Model merging, which combines multiple models into a single model, has gained increasing popularity in recent years. By efficiently integrating the capabilities of various models without their original training data, this significantly reduces the pa
Externí odkaz:
http://arxiv.org/abs/2408.12105
Autor:
Chen, Weiyu, Kwok, James T.
Multi-task learning, which optimizes performance across multiple tasks, is inherently a multi-objective optimization problem. Various algorithms are developed to provide discrete trade-off solutions on the Pareto front. Recently, continuous Pareto fr
Externí odkaz:
http://arxiv.org/abs/2407.20734
The tremendous success of Large Language Models (LLMs) across various complex tasks relies heavily on their substantial scale, which raises challenges during model deployment due to their large memory consumption. Recently, numerous studies have atte
Externí odkaz:
http://arxiv.org/abs/2407.20584
Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse range of m
Externí odkaz:
http://arxiv.org/abs/2406.17092
In this paper, we study the adversarial robustness of deep neural networks for classification tasks. We look at the smallest magnitude of possible additive perturbations that can change the output of a classification algorithm. We provide a matrix-th
Externí odkaz:
http://arxiv.org/abs/2406.16200
Urban spatial interactions are a complex aggregation of routine visits and random explorations by individuals. The inherent uncertainty of these random visitations poses significant challenges to understanding urban structures and socioeconomic devel
Externí odkaz:
http://arxiv.org/abs/2406.15185
Pair interaction potentials between atoms in a crystal are in general non-monotonic in distance, with a local minimum whose position gives the lattice constant of the crystal. A temporal analogue of this idea of crystal formation is still pending des
Externí odkaz:
http://arxiv.org/abs/2406.15017