Generative Large Language Models (LLMs) have achieved remarkable advance...
Offline reinforcement learning (RL) has received considerable attention ...
The prevalent use of benchmarks in current offline reinforcement learnin...
Offline-to-online reinforcement learning (RL), by combining the benefits...
Incorporating language-specific (LS) modules is a proven method to boost...
Mixture-of-experts (MoE) models that employ sparse activation have
demon...
Most offline reinforcement learning (RL) methods suffer from the trade-o...
Multilingual machine translation (MMT) benefits from cross-lingual trans...
Reward function is essential in reinforcement learning (RL), serving as ...
Offline safe RL is of great practical relevance for deploying agents in
...
Offline reinforcement learning (RL) methods can generally be categorized...
We study the problem of offline Imitation Learning (IL) where an agent a...
Offline imitation learning (IL) is a powerful method to solve decision-m...
Recent model pruning methods have demonstrated the ability to remove
red...
In offline reinforcement learning (RL), one detrimental issue to policy
...
The current state-of-the-art for few-shot cross-lingual transfer learnin...
Text Style Transfer (TST) aims to alter the underlying style of the sour...
Although exposure bias has been widely studied in some NLP tasks, it fac...
Most prior approaches to offline reinforcement learning (RL) utilize
beh...
Zero-shot cross-lingual information extraction (IE) describes the
constr...
The success of bidirectional encoders using masked language models, such...
Typically, a linearly orthogonal transformation mapping is learned by
al...
We study the problem of safe offline reinforcement learning (RL), the go...
Offline reinforcement learning (RL) enables learning policies using
pre-...
Linear embedding transformation has been shown to be effective for zero-...
Fine-tuning is known to improve NLP models by adapting an initial model
...
Thermal power generation plays a dominant role in the world's electricit...
Runtime compilation of runtime-constructed code is becoming standard pra...
Modern out-of-order processors have increased capacity to exploit instru...