25 accepted papers
Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories -- typically collected from human demonstrations -- conditioned on task-defining parameters such as vision or language inputs. While recent methods based on the motion manifold hypothesis, wh…
In this letter, we propose a novel reinforcement learning framework that enables zero-shot policy adaptation in environments with unseen, dynamically changing obstacles. Adopting the idea that learning a policy capable of generating diverse actions is key to achieving such adaptability, our primary
Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches interleave two models, but via fundamentally distinct mechanisms: deferral rule that invokes the larger model only for “hard” inputs, while speculative decoding uses spec…
Effective movement primitives should be capable of encoding and generating a rich repertoire of trajectories conditioned on task-defining parameters such as vision or language inputs. While recent methods based on the motion manifold hypothesis, which assumes that a set of trajectories lies on a low
Autonomous navigation in mobile robots has made significant advancements; however, traditional methods often struggle to adapt in real-time to dynamic or unstructured environments. This paper presents the Online Planner's Parameter Adaptation (OPPA) framework, which enhances both adaptability and sa
Large language models (LLMs) are expensive to deploy. Parameter sharing offers a possible path towards reducing their size and cost, but its effectiveness in modern LLMs remains fairly limited. In this work, we revisit "layer tying" as form of parameter sharing in Transformers, and introduce novel m…
Articulated object recognition -- the task of identifying both the geometry and kinematic joints of objects with movable parts -- is essential for enabling robots to interact with everyday objects such as doors and laptops. However, existing approaches often rely on strong assumptions, such as a kno…
In text generation, hallucinations refer to the generation of seemingly coherent text that contradicts established knowledge. One compelling hypothesis is that hallucinations occur when a language model is given a generation task outside its parametric knowledge (due to rarity, recency, domain, etc.…
Recognizing and manipulating transparent tableware from partial view RGB image observations is made challenging by the difficulty in obtaining reliable depth measurements of transparent objects. In this paper we present the Transparent Tableware SuperQuadric Network (T$^2$SQNet), a neural network m…
Modern information retrieval (IR) systems consists of multiple stages like retrieval and ranking, with Transformer-based models achieving state-of-the-art performance at each stage. In this paper, we challenge the tradition of using separate models for different stages and ask if a single Transforme…
As compliant joints not only compensate for the lack of actuated degrees of freedom of an under-actuated system and improve grasp stability but also prevent system failure from unexpected contacts, various types of compliant joints have been applied to end-effectors. Although joint compliance increa
Large deep learning models have achieved state-of-the-art performance across various natural language processing (NLP) tasks and demonstrated remarkable few-shot learning performance. However, training them is often challenging and resource-intensive. In this paper, we study an efficient approach to…
Existing movement primitive models for the most part focus on representing and generating a single trajectory for a given task, limiting their adaptability to situations in which unforeseen obstacles or new constraints may arise. In this work we propose Motion Manifold Primitives (MMP), a movement p…
Finding and grasping a target object on a cluttered shelf, especially when the target is occluded by other unknown objects and initially invisible, remains a significant challenge in robotic manipulation. While there have been advances in finding the target object by rearranging surrounding objects…
Despite the popularity and efficacy of knowledge distillation, there is limited understanding of why it helps. In order to study the generalization behavior of a distilled student, we propose a new theoretical framework that leverages supervision complexity: a measure of alignment between teacher-pr…
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient deployment also necessitates a large amount of (labeled or unlabeled)…
Many problems in machine learning involve data sets in which each data point is a point cloud in $\mathbb{R}^D$. A growing number of applications require a means of measuring not only distances between point clouds, but also angles, volumes, derivatives, and other more advanced concepts. To formulat…
Recently, the robotic assembly has been expanded into an unstructured environment. This environment includes uncertainties that may cause unexpected situations such as a failure of the assembly. Such problems can be prevented or monitored by a robust contact state (CS) estimation method. In that sen
Transformer-based models such as BERT have proven successful in information retrieval problem, which seek to identify relevant documents for a given query. There are two broad flavours of such models: cross-attention (CA) models, which learn a joint embedding for the query and document, and dual-enc…
For tabletop object manipulation tasks, learning an accurate pushing dynamics model, which predicts the objects' motions when a robot pushes an object, is very important. In this work, we claim that an ideal pushing dynamics model should have the SE(2)-equivariance property, i.e., if tabletop object…
Knowledge distillation is a technique for improving a “student” model by replacing its one-hot training labels with a label distribution obtained from a “teacher” model. Despite its broad success, several basic questions — e.g., Why does distillation help? Why do more accurate teachers not necessari…
Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis. In contrast to e…
Knowledge distillation is an approach to improve the performance of a student model by using the knowledge of a complex teacher. Despite its success in several deep learning applications, the study of distillation is mostly confined to classification settings. In particular, the use of distillation…
Electric motors, with a fixed reduction ratio, have a large unused operating region when mimicking muscle movements owing to the difference between the force-velocity curves of electric motors and muscles. This unused region can be reduced by changing the reduction ratio according to the external fo
While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to adaptive methods are n…