16 accepted papers
Despite the central role of attention heads in Transformers, we lack tools to understand why a model attends to a particular token. To address this, we study the query-key (QK) space -- the bilinear joint embedding space between queries and keys. We present a contrastive covariance method to decompo…
DINOv2 sees the world well enough to guide robots and segment images, but we still do not know what it sees. We conduct the first comprehensive analysis of DINOv2’s representational structure using overcomplete dictionary learning, extracting over 32,000 visual concepts in what constitutes the large…
Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing. In contrast, robot learning systems typically rely on passive, uniform processing of raw camera images. In this work, we explore how in…
Conventional flow matching and diffusion-based policies sample through iterative denoising from standard noise distributions (e.g., Gaussian), and require conditioning modules to repeatedly incorporate visual information during the generative process, incurring substantial time and memory overhead.…
Imitation learning has demonstrated significant potential in performing high-precision manipulation tasks using visual feedback. However, it is common practice in imitation learning for cameras to be fixed in place, resulting in issues like occlusion and limited field of view. Furthermore, cameras a
Large Language Models (LLMs) have been previously explored for mental healthcare training and therapy client simulation, but they still fall short in authentically capturing diverse client traits and psychological conditions. We introduce Eeyore , an 8B model optimized for realistic depression simul…
Safety fine-tuning algorithms reduce harmful outputs in language models, yet their mechanisms remain under-explored. Direct Preference Optimization (DPO) is a popular choice of algorithm, but prior explanations—attributing its effects solely to dampened toxic neurons in the MLP layers—are incomplete
Recent work demonstrates that structured patterns in pretraining data influence how representations of different concepts are organized in a large language model’s (LLM) internals, with such representations then driving downstream abilities. Given the open-ended nature of LLMs, e.g., their ability t…
While alignment algorithms are commonly used to tune pre-trained language models towards user preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain phenomena like jailbreaks. In this work we study a popular algorithm,…
Modern generative models demonstrate impressive capabilities, likely stemming from an ability to identify and manipulate abstract concepts underlying their training data. However, fundamental questions remain: what determines the concepts a model learns, the order in which it learns them, and its ab…
This work proposes a new learning-to-search benchmark and uses AI to discover new mathematical knowledge related to an open conjecture of Erdos (1975) in extremal graph theory. The problem is to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-…
Recent progress in large language models (LLMs) has enabled the deployment of many generative NLP applications. At the same time, it has also led to a misleading public discourse that “it’s all been solved.” Not surprisingly, this has, in turn, made many NLP researchers – especially those at the beg…
Synthetic data generation has the potential to impact applications and domains with scarce data. However, before such data is used for sensitive tasks such as mental health, we need an understanding of how different demographics are represented in it. In our paper, we analyze the potential of produc…
Finding an occluded object in a lateral access environment such as a shelf or cabinet is a problem that arises in many contexts such as warehouses, retail, healthcare, shipping, and homes. While this problem, known as mechanical search, is well-studied in overhead access environments, lateral access…
Many statistical models have high accuracy on test benchmarks, but are not explainable, struggle in low-resource scenarios, cannot be reused for multiple tasks, and cannot easily integrate domain expertise. These factors limit their use, particularly in settings such as mental health, where it is di…
The ability to segment unknown objects in depth images has potential to enhance robot skills in grasping and object tracking. Recent computer vision research has demonstrated that Mask R-CNN can be trained to segment specific categories of objects in RGB images when massive hand-labeled datasets are…