30 accepted papers
Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet, despite their perceptual strengths, their reasoning ability across modalities remains underexplored, with conflicting reports on whether additional modalities help…
We study the problem of functional retargeting: learning dexterous manipulation policies to track object states from human hand-object demonstrations. We focus on long-horizon, bimanual tasks with articulated objects, which are challenging due to large action space, spatiotemporal discontinuities, a…
Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models, but their applicability to vision-language models (VLMs) remains unclear. We present a systematic study of TTC for visual reasoning across seven open-source VLMs and six benchmarks,…
Many manipulation tasks require careful force modulation. With insufficient force the task may fail, while excessive force could cause damage. The high cost, bulky size and fragility of commercial force/torque (F/T) sensors have limited large-scale, force-aware policy learning. We introduce UMI-FT, …
Compliance control is essential for safe physical interaction, yet its adoption is limited by hardware requirements such as force/torque sensors. While recent reinforcement learning approaches aim to bypass these constraints, they often suffer from sim-to-real gaps, lack safety guarantees, and add s…
While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting beyond training distributions. In this work, we investigate this extrapolation bottleneck by deconstructing visual counting into three cog…
Compliance plays a crucial role in manipulation, as it balances between the concurrent control of position and force under uncertainties. Yet compliance is often overlooked by today's visuomotor policies that solely focus on position control. This paper introduces Adaptive Compliance Policy (ACP), a
Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images,
We address key challenges in Dataset Aggregation (DAgger) for real-world contact- rich manipulation: how to collect informative human correction data and how to effectively update policies with this new data. We introduce Compliant Residual DAgger (CR-DAgger), which contains two novel components: 1)…
We present DexUMI - a data collection and policy learning framework that uses the human hand as the natural interface to transfer dexterous manipulation skills to various robot hands. DexUMI incorporates hardware and software adaptations to minimize the embodiment gap between the human hand and vari…
Visual language is a system of communication that conveys information through symbols, shapes, and spatial arrangements. Diagrams are a typical example of a visual language depicting complex concepts and their relationships in the form of an image. The symbolic nature of diagrams presents significan…
Reasoning is a central capability of human intelligence. In recent years, with the advent of large-scale datasets, pretrained large language models have emerged with new capabilities, including reasoning. However, these models still struggle with long-term, complex reasoning tasks, such as playing c…
The evolution of text-to-image (T2I) generation techniques has introduced new capabilities for information visualization, with the potential to advance knowledge democratization and education. In this paper, we investigate how T2I models can be adapted to generate educational health knowledge conten
We present Vision in Action (ViA), an active perception system for bimanual robot manipulation. ViA learns task-relevant active perceptual strategies (e.g., searching, tracking, and focusing) directly from human demonstrations. On the hardware side, ViA employs a simple yet effective 6-DoF robotic n…
Crafting an appealing heading is crucial for attracting readers and marketing work or products. A popular way is to summarize the main idea with a refined description and a memorable acronym. However, there lacks a systematic study and a formal benchmark including datasets and metrics. Motivated by…
Large language models (LLMs) exhibit an intriguing ability to learn a novel task from in-context examples presented in a demonstration, termed in-context learning (ICL). Understandably, a swath of research has been dedicated to uncovering the theories underpinning ICL. One popular hypothesis explain…
Various design settings for in-context learning (ICL), such as the choice and order of the in-context examples, can bias the model’s predictions. While many studies discuss these design choices, there have been few systematic investigations into categorizing them and mitigating their impact. In this…
Recent work has shown that language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. However, it is unclear whether LMs perform these tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step reasoning mechanism. In this paper, we try to ans…
Large language models appear to learn facts from the large text corpora they are trained on. Such facts are encoded implicitly within their many parameters, making it difficult to verify or manipulate what knowledge has been learned. Language models have recently been extended to multilingual langua…
This paper presents Contact Mode Guided Manipulation Planning (CMGMP) for 3D quasistatic and quasi-dynamic rigid body motion planning in dexterous manipulation. The CMGMP algorithm generates hybrid motion plans including both continuous state transitions and discrete contact mode switches, without t…
This paper explores a novel approach to dexterous manipulation, aimed at levels of speed, precision, robustness, and simplicity suitable for practical deployment. The enabling technology is a Direct-drive Hand (DDHand) comprising two fingers, two DOFs each, that exhibit high speed and a light touch.…
A number of knowledge integration (KI) methods have recently been proposed to incorporate external knowledge into pretrained language models (LMs). Even though knowledge-enhanced LMs (KELMs) outperform base LMs on knowledge-intensive tasks, the inner-workings of these KI methods are not well-underst…
This paper derives a closed-form method for computing hybrid force-velocity control. The key idea is to maximize the kinematic conditioning of the mechanical system, which includes a robot, free objects, a rigid environment and contact constraints. The method is complete, in that it always produces…
NLP has a rich history of representing our prior understanding of language in the form of graphs. Recent work on analyzing contextualized text representations has focused on hand-designed probe models to understand how and to what extent do these representations encode a particular linguistic phenom…
The discontinuities and multi-modality introduced by contacts make manipulation planning challenging. Many previous works avoid this problem by pre-designing a set of high-level motion primitives like grasping and pushing. However, such motion primitives are often not adequate to describe dexterous…
A shared grasp is a grasp formed by contacts between the manipulated object and both the robot hand and the environment. By trading off hand contacts for environmental contacts, a shared grasp requires fewer contacts with the hand, and enables manipulation even when a full grasp is not possible. Pre…
Graph neural networks (GNNs) have been widely used for representation learning on graph data. However, there is limited understanding on how much performance GNNs actually gain from graph data. This paper introduces a context-surrounding GNN framework and proposes two smoothness metrics to measure t…
In robotic manipulation, finding a feasible motion plan doesn't guarantee a successful execution. The real world could bring all kinds of unexpected changes to the planned motion, the most deadly ones are usually marked by or caused by unexpected changes of contacts (object slipping away between fin…
In hybrid force-velocity control, the robot can use velocity control in some directions to follow a trajectory, while performing force control in other directions to maintain contacts with the environment regardless of positional errors. We call this way of executing a trajectory hybrid servoing. We…
In this paper, we consider reorienting 3D objects on a table using a two-finger pinch gripper. Given the 3D mesh model of the object, our algorithm solves for the gripper motions that are required to transit between arbitrary object poses, grasping positions and gripper poses. The two motion primiti…