Related papers: Learning from the Best: Smoothness-Driven Metrics …
We propose and analyze a novel framework for learning sparse representations, based on two statistical techniques: kernel smoothing and marginal regression. The proposed approach provides a flexible framework for incorporating feature…
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously…
Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora. However, small, high-quality subsets, known as coresets, can deliver comparable or superior…
Imitation learning (IL) has shown great success in learning complex robot manipulation tasks. However, there remains a need for practical safety methods to justify widespread deployment. In particular, it is important to certify that a…
Learning robust visuomotor policies for robotic manipulation remains a challenge in real-world settings, where visual distractors can significantly degrade performance and safety. In this work, we propose an effective and scalable…
Psychiatric neuroscience is increasingly aware of the need to define psychopathology in terms of abnormal neural computation. The central tool in this endeavour is the fitting of computational models to behavioural data. The most prominent…
The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajectories obtained from running a solver…
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…
Physics-based motion imitation is central to humanoid control, yet current evaluation metrics (e.g., joint position error) only measure how well a policy imitates but not how difficult the motion itself is. This conflates policy performance…
Consider the task of estimating a 3-order $n \times n \times n$ tensor from noisy observations of randomly chosen entries in the sparse regime. We introduce a similarity based collaborative filtering algorithm for estimating a tensor from…
Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs). One major limitation of most existing Reinforcement Finetuning (RFT) methods is that they are on-policy RL in…
This paper proposes a novel formulation for reinforcement learning (RL) with large language models, explaining why and under what conditions the true sequence-level reward can be optimized via a surrogate token-level objective in policy…
Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization,…
Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practices beyond those observed during training. We introduce MetaLint, a meta-learning framework that…
The aim in imitation learning is to learn effective policies by utilizing near-optimal expert demonstrations. However, high-quality demonstrations from human experts can be expensive to obtain in large numbers. On the other hand, it is…
Multimodal Large Language Models have demonstrated remarkable capabilities in video understanding, yet face prohibitive computational costs and performance degradation from ''context rot'' due to massive visual token redundancy. Existing…
Recently, self-play fine-tuning (SPIN) has been proposed to adapt large language models to downstream applications with scarce expert-annotated data, by iteratively generating synthetic responses from the model itself. However, SPIN is…
Learning to play table tennis is a challenging task for robots, as a wide variety of strokes required. Recent advances have shown that deep Reinforcement Learning (RL) is able to successfully learn the optimal actions in a simulated…
Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with respect to the…
Semi-supervised learning (SSL) algorithms have had great success in recent years in limited labeled data regimes. However, the current state-of-the-art SSL algorithms are computationally expensive and entail significant compute time and…