Related papers: EvoStruggle: A Dataset Capturing the Evolution of …

Some of the most severe bottlenecks preventing widespread development of machine learning models for human behavior include a dearth of labeled training data and difficulty of acquiring high quality labels. Active learning is a paradigm for…

Reinforcement learning (RL) has made significant progress in various domains, but scaling it to long-horizon tasks with complex decision-making remains challenging. Skill learning attempts to address this by abstracting actions into…

Learning visual similarity requires to learn relations, typically between triplets of images. Albeit triplet approaches being powerful, their computational complexity mostly limits training to only a subset of all possible training…

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning. Some notable examples include training agents to play Atari games based on raw…

Learning requires the traversal of inherently distinct cognitive states to produce behavioral adaptation. Yet, tools to explicitly measure these states with non-invasive imaging -- and to assess their dynamics during learning -- remain…

Data-driven navigation algorithms are critically dependent on large-scale, high-quality real-world data collection for successful training and robust performance in realistic and uncontrolled conditions. To enhance the growing family of…

Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration…

Dual-arm robotic grasping is crucial for handling large objects that require stable and coordinated manipulation. While single-arm grasping has been extensively studied, datasets tailored for dual-arm settings remain scarce. We introduce a…

Analyzing student actions is an important and challenging task in educational research. Existing efforts have been hampered by the lack of accessible datasets to capture the nuanced action dynamics in classrooms. In this paper, we present a…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

Dense action detection involves detecting multiple co-occurring actions while action classes are often ambiguous and represent overlapping concepts. We argue that handling the dual challenge of temporal and class overlaps is too complex to…

Achieving truly adaptive embodied intelligence requires agents that learn not just by imitating static demonstrations, but by continuously improving through environmental interaction, which is akin to how humans master skills through…

Deep reinforcement learning algorithms typically act on the same set of actions. However, this is not sufficient for a wide range of real-world applications where different subsets are available at each step. In this thesis, we consider the…

Robotic grasping in cluttered environments is often infeasible due to obstacles preventing possible grasps. Then, pre-grasping manipulation like shifting or pushing an object becomes necessary. We developed an algorithm that can learn, in…

Recognizing Video events in long, complex videos with multiple sub-activities has received persistent attention recently. This task is more challenging than traditional action recognition with short, relatively homogeneous video clips. In…

Evaluating visual activity recognition systems is challenging due to inherent ambiguities in verb semantics and image interpretation. When describing actions in images, synonymous verbs can refer to the same event (e.g., brushing vs.…

The extreme fragility of deep neural networks, when presented with tiny perturbations in their inputs, was independently discovered by several research groups in 2013. However, despite enormous effort, these adversarial examples remained a…

A robot deployed in a home over long stretches of time faces a true lifelong learning problem. As it seeks to provide assistance to its users, the robot should leverage any accumulated experience to improve its own knowledge and…

Advances in deep generative modeling have made it increasingly plausible to train human-level embodied agents. Yet progress has been limited by the absence of large-scale, real-time, multi-modal, and socially interactive datasets that…

Continuous adaptation allows survival in an ever-changing world. Adjustments in the synaptic coupling strength between neurons are essential for this capability, setting us apart from simpler, hard-wired organisms. How these changes can be…