Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Shi, Javen"'
Autor:
Cao, Haiyao, Zou, Jinan, Liu, Yuhang, Zhang, Zhen, Abbasnejad, Ehsan, Hengel, Anton van den, Shi, Javen Qinfeng
Accurately predicting stock returns is crucial for effective portfolio management. However, existing methods often overlook a fundamental issue in the market, namely, distribution shifts, making them less practical for predicting future markets or ne
Externí odkaz:
http://arxiv.org/abs/2409.00671
Autor:
Cao, Haiyao, Zhang, Zhen, Cai, Panpan, Liu, Yuhang, Zou, Jinan, Abbasnejad, Ehsan, Huang, Biwei, Gong, Mingming, Hengel, Anton van den, Shi, Javen Qinfeng
One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical support for ensuring that the underlying states can be uniquely recovered
Externí odkaz:
http://arxiv.org/abs/2408.13498
As Large Language Models (LLMs) grow dramatically in size, there is an increasing trend in compressing and speeding up these models. Previous studies have highlighted the usefulness of gradients for importance scoring in neural network compressing, e
Externí odkaz:
http://arxiv.org/abs/2407.11681
The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object fea
Externí odkaz:
http://arxiv.org/abs/2406.01256
Reinforcement Learning (RL) algorithms often suffer from low training efficiency. A strategy to mitigate this issue is to incorporate a model-based planning algorithm, such as Monte Carlo Tree Search (MCTS) or Value Iteration (VI), into the environme
Externí odkaz:
http://arxiv.org/abs/2405.11727
Autor:
Liu, Yuhang, Zhang, Zhen, Gong, Dong, Gong, Mingming, Huang, Biwei, Hengel, Anton van den, Zhang, Kun, Shi, Javen Qinfeng
Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. It is particularly good at predictions under unseen distribution shifts, because these shifts can generally be interpreted as cons
Externí odkaz:
http://arxiv.org/abs/2403.15711
Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training, recent efforts have shown that it's possible to accomplish this
Externí odkaz:
http://arxiv.org/abs/2403.01418
Autor:
Liu, Yuhang, Zhang, Zhen, Gong, Dong, Huang, Biwei, Gong, Mingming, Hengel, Anton van den, Zhang, Kun, Shi, Javen Qinfeng
Multimodal contrastive representation learning methods have proven successful across a range of domains, partly due to their ability to generate meaningful shared representations of complex phenomena. To enhance the depth of analysis and understandin
Externí odkaz:
http://arxiv.org/abs/2402.06223
Contrastive vision-language models, such as CLIP, have garnered considerable attention for various dowmsteam tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often blend conten
Externí odkaz:
http://arxiv.org/abs/2311.16445
Autor:
Liu, Yuhang, Zhang, Zhen, Gong, Dong, Gong, Mingming, Huang, Biwei, Hengel, Anton van den, Zhang, Kun, Shi, Javen Qinfeng
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability. A rece
Externí odkaz:
http://arxiv.org/abs/2310.15580