Related papers: STAND: Self-Aware Precondition Induction for Inter…

Autonomous open-ended learning is a relevant approach in machine learning and robotics, allowing the design of artificial agents able to acquire goals and motor skills without the necessity of user assigned tasks. A crucial issue for this…

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The…

Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot…

Pretrained visual-language models have extensive world knowledge and are widely used in visual and language navigation (VLN). However, they are not sensitive to indoor scenarios for VLN tasks. Another challenge for VLN is how the agent…

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

Interactive reinforcement learning has allowed speeding up the learning process in autonomous agents by including a human trainer providing extra information to the agent in real-time. Current interactive reinforcement learning research has…

Semi-supervised learning provides a solution to reduce the dependency of machine learning on labeled data. As one of the efficient semi-supervised techniques, self-training (ST) has received increasing attention. Several advancements have…

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL)…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Conditional Imitation learning is a common and effective approach to train autonomous driving agents. However, two issues limit the full potential of this approach: (i) the inertia problem, a special case of causal confusion where the agent…

We tackle the question of how to scale more efficiently across the many, ever-growing stages of current LLM training pipelines. Our guiding intuition stems from the fact that the dynamics of later stages of the pipeline, e.g. post-training,…

This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…

Robotic manipulation holds the potential to replace humans in the execution of tedious or dangerous tasks. However, control-based approaches are not suitable due to the difficulty of formally describing open-world manipulation in reality,…

Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level…

Mechanism-targeted synthetic data is increasingly proposed as a way to steer pretraining toward desirable capabilities, but it remains unclear how such interventions should be evaluated. We study this question for in-context learning (ICL)…

The ability to infer pre- and postconditions of an action is vital for comprehending complex instructions, and is essential for applications such as autonomous instruction-guided agents and assistive AI that supports humans to perform…

The task of Stance Detection involves discerning the stance expressed in a text towards a specific subject or target. Prior works have relied on existing transformer models that lack the capability to prioritize targets effectively.…