19 accepted papers
We propose BRIC, a novel test-time adaptation (TTA) framework that enables long-term human motion generation by resolving execution discrepancies between diffusion-based kinematic motion planners and reinforcement learning-based physics controllers. While diffusion models can generate diverse and ex
In sparse-reward, long-horizon domains, reinforcement learning (RL) often suffers from slow convergence and instability, complicating robotic manipulation. Previous heuristic-guided approaches have relied on step-level actions and imitation loss, but struggle to maintain temporal coherence or solve
Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this,
Video Large Language Models (VideoLLMs) extend the capabilities of vision-language models to spatiotemporal inputs, enabling tasks such as video question answering (VideoQA). Despite recent advances in VideoLLMs, their internal mechanisms on where and how they extract and propagate video and textual…
We propose a graph SLAM algorithm for sparse range sensing that incorporates a soft Manhattan world utilizing landmark-landmark constraints. Sparse range sensing is necessary for tiny robots that do not have the luxury of using heavy and expensive sensors. Existing SLAM methods dealing with sparse r…
As chatbots continue to evolve toward human-like, real-world, interactions, multimodality remains an active area of research and exploration. So far, efforts to integrate multimodality into chatbots have primarily focused on image-centric tasks, such as visual dialogue and image-based instructions,…
Knowledge-grounded Question Answering (QA) aims to provide answers to structured queries or natural language questions by leveraging Knowledge Graphs (KGs). Existing approaches are mainly divided into Knowledge Graph Question Answering (KGQA) and Complex Query Answering (CQA). Both approaches have l…
Instruction tuning—supervised fine-tuning using instruction-response pairs—is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring extensive knowledge and capabilities. We hypothesize that the pre-
We present a novel calibration method between single-point LiDAR and camera sensors utilizing an easy-to-build customized calibration board satisfying the Manhattan world (MW). Previous methods for LiDAR-camera (LC) calibration focus on line and plane correspondences. However, they require dense 3D
We propose the San Francisco world (SFW) model, a novel structural model inspired by San Francisco's hilly terrain, enabling 3D inter-floor navigation in urban areas rather than being limited to 2D intra-floor navigation of various robotics platforms. Our SFW consists of a single vertical dominant d
We propose a novel graph SLAM algorithm for sparse range sensing that incorporates a soft Manhattan world utilizing landmark-landmark constraints. Sparse range sensing is necessary for tiny robots that do not have the luxury of using heavy and expensive sensors. Existing SLAM methods dealing with sp
In continuous domains, reinforcement learning policies are often based on Gaussian distributions for their generality. However, the unbounded support of Gaussian policy can cause a bias toward sampling boundary actions in many continuous control tasks that impose action limits due to physical constr…
"We propose a novel framework for video understanding, called (), which leverages essential temporal information through global interactions in a spatio-temporal domain within a video. To be specific, we introduce Temporal Contextualization (TC), a layer-wise temporal information infusion mechanism…
Current robotic hand manipulation narrowly operates with objects in predictable positions in limited environments. Thus, when the location of the target object deviates severely from the expected location, a robot sometimes responds in an unexpected way, especially when it operates with a human. For…
Collage is a creative art form that uses diverse material scraps as a base unit to compose a single image. Although pixel-wise generation techniques can reproduce a target image in collage style, it is not a suitable method due to the solid stroke-by-stroke nature of the collage form. While some p…
We present an automated learning framework for a robotic sketching agent that is capable of learning stroke-based rendering and motor control simultaneously. We formulate the robotic sketching problem as a deep decoupled hierarchical reinforcement learning; two policies for stroke-based rendering an…
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network. The former learns coarse…
"Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is a sequence-level task in its nature; they rely heavily on frame-level training, which inevitably induces inconsistency…
We present a novel systematic design framework for general under-actuated tendon-driven (UATD) robotic systems to exhibit desired behaviors both during the free motion and the contact task. For this, we propose stiffness decomposition, which enables us to completely decompose the configuration space…