48 accepted papers
Cable routing is a common manipulation task in assembly and manufacturing, yet it remains challenging due to the deformable nature of cables and the constraints of cluttered routing environments. In this paper, we present CRAFT: Cable Routing Around Fixtures using Two grippers, a novel hardware plus…
Training long-context language models to capture long-range dependencies requires specialized data construction. Current approaches, such as generic text concatenation or heuristic-based variants, frequently fail to guarantee genuine long-range dependencies. We propose \textbf{EntropyLong}, a novel…
High-quality long-context data is essential for training large language models (LLMs) capable of processing extensive documents, yet existing synthesis approaches using relevance-based aggregation face challenges of computational efficiency. We present LiteLong, a resource-efficient method for synth
Large language models (LLMs) are increasingly deployed as agents for decision-making (DM) in interactive and dynamic environments. However, since they are not originally designed for DM, recent studies show that LLMs struggle in basic online DM settings. We introduce ITERATIVE REGRET-MINIMIZATION FI…
The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success often reinforce flawed or inefficient reasoning paths, a prob…
Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning. Vision–Language Models (VLMs) offer a promising foundation for general-purpose and interpretable robotic reasoning. Aligning VL…
Suturing is a high-precision task performed at the end of procedures when surgeon fatigue may increase errors, highlighting the need for robot assistance. Previous autonomous suturing works, such as STITCH 1.0 [1], struggle to fully close wounds due to inaccurate needle tracking, thread tangling, an…
Disentangling image content and style is essential for customized image generation. Existing SDXL-based methods struggle to achieve high-quality results, while the recently proposed Flux model fails to achieve effective content-style separation due to its underexplored characteristics. To address th
Federated Learning has been widely adopted in privacy-sensitive distributed machine learning. However, in heterogeneous scenarios where significant differences exist in user data distribution, computational capabilities, or network conditions, existing models often underperform. This paper models ke…
Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibiting the models’ comprehensive perception performance across different levels of granularity. In this work, we propose Pyra…
Open-vocabulary object detection (OVD) is a significant task identifying objects from categories not included in the training set. Our comprehensive analysis reveals two main issues with existing OVD models: poor generalization of localization network to novel categories and poor quality of class em…
We show that the GPS tags contained in photo metadata provide a useful control signal for image generation. We train GPS-to-image models and use them for tasks that require a fine-grained understanding of how images vary within a city. In particular, we train a diffusion model to generate images con…
Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address thi…
Efficiently searching for multiple objects in a partially known environment, where only the names and locations of landmarks are available, presents significant challenges. Existing search algorithms in the literature fail to fully utilize prior knowledge to improve search efficiency, and exhibit si
A primary concern in robotic automation is safety, especially in surgical scenarios. In this paper, we propose a virtual fixture (VF) based safe reinforcement learning framework to ensure safety constraints. The framework ensures that the agent, particularly multi-joint robotic manipulator agents, a
Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual elements. In practice, computational constraints necessitate…
Human-robot interaction plays a critical role in scientific experiments by ensuring efficient and reliable execution of experimental tasks. To achieve successful task completion, robots must adapt in real time to unexpected task variations, external disturbances, and safety constraints. In this work
Surgical suturing is a high-precision task that impacts patient healing and scarring. Suturing skill varies widely between surgeons, highlighting the need for robot assistance. Previous robot suturing works, such as STITCH 1.0 [1], struggle to fully close wounds due to inaccurate needle tracking and
Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations.…
We present a method for learning binaural sound localization from ego-motion in videos. When the camera moves in a video, the direction of sound sources will change along with it. We train an audio model to predict sound directions that are consistent with visual estimates of camera motion, which we…
Knot tying is a fundamental dexterous surgical subtask that is a key step in suturing. One challenge to robot augmentation is limited depth perception due to the small baseline of surgical endoscopic cameras. In this work, we present Surgical D-Knot: an augmented dexterity pipeline combining learned
Tool learning enhances Large Language Models’ (LLMs) dynamic interaction with external tools, improving their ability to solve complex problems. However, current empirical methods, which primarily focus on isolated tools learning, still struggle with accurate multi-tool selection due to issues like…
Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce *MultiFoley*, a model designed for video-guided sound generation that supports multimod…
Reactive planning enables the robots to deal with dynamic events in uncertain environments. However, existing methods heavily rely on the predefined hard-coded robot behaviors, e.g, a pre-coded temporal logic formula that specifies how robot should react. Little attention has been paid for autonomou…
The ability to associate touch with other modalities has huge implications for humans and computational systems. However multimodal learning with touch remains challenging due to the expensive data collection process and non-standardized sensor outputs. We introduce UniTouch a unified tactile model…
Self-supervised learning (SSL) is an efficient pre-training method for medical image analysis. However current research is mostly confined to certain modalities consuming considerable time and resources without achieving universality across different modalities. A straightforward solution is combini…
It is challenging to coordinately allocate and plan the tasks of a heterogeneous multi-agent system in a shared workspace. It can be even more challenging if the agents are subject to limited communication capability (i.e., exchange information with nearby agents only) and complex tasks with tempora
Distribution shift widely exists in medical images acquired from different medical centres and poses a significant obstacle to deploying the pre-trained semantic segmentation model in real-world applications. Test-time adaptation has proven its effectiveness in tackling the cross-domain distribution…
This work develops a fast mission planning framework named planning decision tree (PDT), that can handle large-scale multi-robot systems with temporal logic specifications in real time. Specifically, PDT builds a tree incrementally to represent the task progress. The system states are modeled by bot
Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images…
Learning-based stereo matching techniques have made significant progress. However existing methods inevitably lose geometrical structure information during the feature channel generation process resulting in edge detail mismatches. In this paper the Motif Channel Attention Stereo Matching Network (M…
While reinforcement learning (RL) attracts increasing research attention, maximizing the return while keeping the agent safe at the same time remains an open problem. Motivated to address this challenge, this work proposes a new Fast and Safe Policy Optimization (FSPO) algorithm, which consists of t…
We present a new dataset called Real Acoustic Fields (RAF) that captures real acoustic room data from multiple modalities. The dataset includes high-quality and densely captured room impulse response data paired with multi-view images and precise 6DoF pose tracking data for sound emitters and listen…
This works exploits soft constraints in linear temporal logic task planning to enhance the agent’s capability in handling potentially conflicting or even infeasible tasks. Different from most existing works that focus on sticking to the original plan and trying to find a relaxed plan if the workspac…
In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of inaccurate or misleading responses. This issue mainly arises from their limited ability to handle evolving factual knowl…
How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks…
Lymphadenectomy generally accompanies various oncology surgeries to remove infected cancer cells. However, there are two limitations in robot-assisted lymphadenectomy: 1) lymph nodes are not visible during operation since they are hidden by the superficial fat layer; 2) intra-operative bleeding may…
Fast motion planning is of great significance, espe-cially when a timely mission is desired. However, the complexity of motion planning can grow drastically with the increase of environment details and mission complexity. This challenge can be further exacerbated if the tasks are coupled with the de…
The sound effects that designers add to videos are designed to convey a particular artistic effect and, thus, may be quite different from a scene's true sound. Inspired by the challenges of creating a soundtrack for a video that differs from its true sound, but that nonetheless matches the actions o…
This work develops a fast task allocation framework for heterogeneous multi-robot systems subject to both temporal logic and inter-task constraints. The considered inter-task constraints include unrelated tasks, compatible tasks, and exclusive tasks. To specify such inter-task relationships, we exte
In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals remains a considerable challenge due to the complexities of ch…
Learning-based path planning is becoming a promising robot navigation methodology due to its adaptability to various environments. However, the expensive computing and storage associated with networks impose significant challenges for their deployment on low-cost robots. Motivated by this practical…
Recently, question answering over temporal knowledge graphs (i.e., TKGQA) has been introduced and investigated, in quest of reasoning about dynamic factual knowledge. To foster research on TKGQA, a few datasets have been curated (e.g., CronQuestions and Complex-CronQuestions), and various models hav…
Manipulated videos often contain subtle inconsistencies between their visual and audio signals. We propose a video forensics method, based on anomaly detection, that can identify these inconsistencies, and that can be trained solely using real, unlabeled data. We train an autoregressive model to gen…
The images and sounds that we perceive undergo subtle but geometrically consistent changes as we rotate our heads. In this paper, we use these cues to solve a problem we call Sound Localization from Motion (SLfM): jointly estimating camera rotation and localizing sound sources. We learn to solve the…
We present a method for simultaneously localizing multiple sound sources within a visual scene. This task requires a model to both group a sound mixture into individual sources, and to associate them with a visual signal. Our method jointly solves both tasks at once, using a formulation inspired by…
"Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound’s time delay requires finding correspondences between the signals recorded by each microphone. We propose to learn these correspondences throug…
From whirling ceiling fans to ticking clocks, the sounds that we hear subtly vary as we move through a scene. We ask whether these ambient sounds convey information about 3D scene structure and, if so, whether they provide a useful learning signal for multimodal models. To study this, we collect a d…