29 accepted papers
Long-form books are among the most information-rich and structurally complex forms of written content, often exceeding 100,000 words. While recent methods have enabled basic long-text generation, they remain limited in two key aspects: the inability to generate ultra-long content at book scale, and
Active 3D reconstruction relies on active view selection to maximize reconstruction fidelity under limited capture budgets. However, most existing methods rely on surrogate signals—such as parameter uncertainty or geometric heuristics—which are often misaligned with the ultimate goal: the fidelity o…
Visual relocalization is a fundamental task in the field of 3D computer vision, estimating a camera's pose when it revisits a previously known scene. While point-based hierarchical relocalization methods have shown strong scalability and efficiency, they are often limited by sparse image observation
Reinforcement Learning from Human Feedback (RLHF) has advanced alignment capabilities significantly but remains hindered by two core challenges: reward hacking and stable optimization. Current solutions independently address these issues through separate regularization strategies, specifically a KL-…
To enhance the social navigation performance of mobile robots in crowded environments, we propose a novel framework—Prediction and Fuzzy Timed Elastic Band (PF-TEB) for robot social navigation. Our framework incorporates predicted pedestrian trajectories into pedestrian proxemics modeling as a socia
Reinforcement learning (RL) is a fundamental and pivotal algorithm in the advancement of autonomous intelligence, including Embodied Intelligence and Physical Intelligence. The performance of RL directly influences the quality and efficiency of a robot’s decision-making and execution during interact
Invasive brain-computer interfaces with Electrocorticography (ECoG) have shown promise for high-performance speech decoding in medical applications, but less damaging methods like intracranial stereo-electroencephalography (sEEG) remain underexplored. With rapid advances in representation learning,…
Pedestrian trajectory prediction is a well-established task with significant recent advancements. However existing datasets are unable to fulfill the demand for studying minute-level long-term trajectory prediction mainly due to the lack of high-resolution trajectory observation in the wide field of…
The recent advancements in transformer-based visual trackers have led to significant progress, attributed to their strong modeling capabilities. However, as performance improves, running latency correspondingly increases, presenting a challenge for real-time robotics applications, especially on edge…
"Neural implicit surface reconstruction has achieved remarkable progress recently. Despite resorting to complex radiance modeling, state-of-the-art methods still struggle with textureless and specular surfaces. Different from RGB images, polarization images can provide direct constraints on the azim…
Robot person following (RPF) is a crucial capability in human-robot interaction (HRI) applications, allowing a robot to persistently follow a designated person. In practical RPF scenarios, the person can often be occluded by other objects or people. Consequently, it is necessary to re-identify the p
Predicting how pedestrians will move in the future is crucial for robot navigation, autonomous driving, and video surveillance. The complex interactions among pedestrians make it difficult to predict their future trajectory. Previous studies have primarily focused on modeling the interaction feature
Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local f…
Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input. In this paper, we propose the AMR-TST, an AMR-based text style transfer (TST) technique. The AMR-TST converts the source text to an AMR graph a…
This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead, the agent is provided with fixed offline trajectories and hum…
In this paper, we present ContExtual Imitation Learning (CEIL), a general and broadly applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight information matching, we derive CEIL by explicitly learning a hindsight embedding function together with a contextual polic…
Offline reinforcement learning (RL) aims to learn an optimal policy from pre-collected and labeled datasets, which eliminates the time-consuming data collection in online RL. However, offline RL still bears a large burden of specifying/handcrafting extrinsic rewards for each transition in the offlin…
Although link prediction on graphs has achieved great success with the development of graph neural networks (GNNs), the potential robustness under the edge noise is still less investigated. To close this gap, we first conduct an empirical study to disclose that the edge noise bilaterally perturbs bo…
Visual relocalization is a fundamental problem in computer vision and robotics. Recently, regression-based methods become popular and they can be categorized into two classes: absolute pose regression and scene coordinate regression. In this work, we present a combined regression network that jointl…
Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible attacks followed by a trigger batch. Due to the limited data-…
Robot person following (RPF) is a capability that supports many useful human-robot-interaction (HRI) applications. However, existing solutions to person following often as-sume full observation of the tracked person. As a consequence, they cannot track the person reliably under partial occlusion whe…
Loop closure detection is a key technology for long-term robot navigation in complex environments. In this paper, we present a global descriptor, named Normal Distribution Descriptor (NDD), for 3D point cloud loop closure detection. The descriptor encodes both the probability density score and entro…
"Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption. In the case of a large field of view, however, this assumption does not hold and may result in significant reco…
Semantic simultaneous localization and mapping (SLAM) can provide the foundation for robots to perform more advanced tasks than traditional geometric SLAM. Object association is a crucial factor in semantic SLAM. Previous work utilizes observations at the current moment and a single geometric featur
Recent works on semantic Simultaneous Localization and Mapping (SLAM) utilizing object landmarks have shown superiority in terms of robustness and accuracy in tracking and localization. 3D object landmarks represented by a cubic or quadric surface are inferred from 2D object bounding boxes which are…
Keypoint matching is an important operation in computer vision and its applications such as visual simultaneous localization and mapping (SLAM) in robotics. This matching operation heavily depends on the descriptors of the keypoints, and it must be performed reliably when images undergo conditional…
Keypoint matching is an important operation in computer vision and its applications such as visual simultaneous localization and mapping (SLAM) in robotics. This matching operation heavily depends on the descriptors of the keypoints, and it must be performed reliably when images undergo condition ch…
Motivated by the need to improve the performance of visual loop closure verification via multi-view geometry (MVG) under significant illumination and viewpoint changes, we propose a keypoint matching method that uses landmarks as an intermediate image representation in order to leverage the power of…
In this paper, we present a novel global descriptor M2DP for 3D point clouds, and apply it to the problem of loop closure detection. In M2DP, we project a 3D point cloud to multiple 2D planes and generate a density signature for points for each of the planes. We then use the left and right singular…