37 accepted papers
Robots operating alongside people, particularly in sensitive scenarios such as aiding the elderly with daily tasks or collaborating with workers in manufacturing, must guarantee safety and cultivate user trust. Continuum soft manipulators promise safety through material compliance, but as designs ev…
Autonomous driving systems require a comprehensive understanding of the environment, achieved by extracting visual features essential for perception, planning, and control. However, models trained solely on single-task objectives or generic datasets often lack the contextual information needed for r…
A fundamental challenge in multi-task reinforcement learning (MTRL) is achieving sample efficiency in visual domains where tasks exhibit significant heterogeneity in both observations and dynamics. Model-based RL (MBRL) offers a promising path to sample efficiency through world models, but standard…
Swarmalator studies have enabled self-organized collective behaviors that emerge from dual spatial and temporal coupling, without relying on external inputs. These behaviors arise solely from attractive and repulsive interactions modulated by a few global parameters. Here, we treat the swarmalator m
Swarmalator studies have enabled self-organized collective behaviors that emerge from dual spatial and temporal coupling, without relying on external inputs. These behaviors arise solely from attractive and repulsive interactions modulated by a few global parameters. Here, we treat the swarmalator m…
Imitation learning (IL) enables efficient skill acquisition from demonstrations but often struggles with long-horizon tasks and high-precision control due to compounding errors. Residual policy learning offers a promising, model-agnostic solution by refining a base policy through closed-loop correct…
The disaggregated Prefill-Decode (PD) architecture has emerged as a prominent paradigm for efficient Large Language Model inference serving. However, resource management remains a critical challenge, particularly under the dual burstiness of real-world scenarios—characterized by volatile fluctuation
In offline-to-online (O2O) reinforcement learning, achieving efficient performance improvement while maintaining training stability remains a critical challenge for effective fine-tuning. Existing O2O methods usually focus on the balance between policy improvement and policy constraint during online
Recent Vision-Language-Action (VLA) models show potential to generalize across embodiments but struggle to quickly align with a new robot’s action space when high-quality demonstrations are scarce, especially for bipedal humanoids. We present TrajBooster, a cross-embodiment framework that leverages …
Safe learning is central to AI-enabled robots where a single failure may lead to catastrophic results. Existing safe learning methods are not scalable, inefficient and hard to train, and tend to generate unstable signals under noisy inputs that are challenging to be deployed for robots. To address t…
As the tenth part of the third-generation AVS standard series for real-time speech coding, AVS3P10 is the recent standard completed in the Audio Video Coding Standards Workgroup of China (AVS). Combining the state-of-the-art deep generative networks and signal processing methods, AVS3P10 targets def…
Recent advances in differentiable score-based methods for Directed Acyclic Graph (DAG) structure learning have revolutionized the problem of combinatorial structure learning, transforming it into a continuous optimization task. Despite their remarkable success, these methods rely on a key assumption…
Robots operating alongside people, particularly in sensitive scenarios such as aiding the elderly with daily tasks or collaborating with workers in manufacturing, must guarantee safety and cultivate user trust. Continuum soft manipulators promise safety through material compliance, but as designs ev
A critical bottleneck in deep reinforcement learning (DRL) is sample inefficiency, as training high-performance agents often demands extensive environmental interactions. Model-based reinforcement learning (MBRL) mitigates this by building world models that simulate environmental dynamics and genera…
Jumping constitutes an essential component of quadruped robots’ locomotion capabilities, which includes dynamic take-off and adaptive landing. Existing quadrupedal jumping studies mainly focused on the stance and flight phase by assuming a flat landing ground, which is impractical in many real world
Open domain question answering systems frequently rely on information retrieved from large collections of text (such as the Web) to answer questions. However, such collections of text often contain conflicting information, and indiscriminately depending on this information may result in untruthful a…
Quantifying uncertainty in black-box LLMs is vital for reliable responses and scalable oversight. Existing methods, which gauge a model’s uncertainty through evaluating self-consistency in responses to the target query, can be misleading: an LLM may confidently provide an incorrect answer to a targe
Safe motion planning is essential for autonomous vessel operations, especially in challenging spaces such as narrow inland waterways. However, conventional motion planning approaches are often computationally intensive or overly conservative. This paper proposes a safe motion planning strategy combi
Diffusion models have shown promise in data-driven planning. While these planners are commonly employed in applications where decisions are critical, they still lack established safety guarantees. In this paper, we address this limitation by introducing SafeDiffuser, a method to equip diffusion mode…
Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context. Although many studies have investigated contextual hallucinati…
As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning. However, existing systems grapple with challenges such as unexpected open set environments and the complexity of black-b…
Natural and robotic swarms often exhibit nonreciprocal interactions; agents do not exhibit equal and opposite forces on each other. By studying the effects of reciprocal and non-reciprocal interactions we are better able to design emergent behaviors in robot collectives composed of agents that exert…
In autonomous robot navigation, the trajectories from path planners are considered to be safe regions, and deviations could endanger vessels. Model Predictive Control (MPC) stands as a popular choice for trajectory tracking problems as it naturally addresses operational constraints, such as dynamics…
Diffusion models have risen a promising approach to data-driven planning, and have demonstrated impressive robotic control, reinforcement learning, and video planning performance. Given an effective planner, an important question to consider is replanning -- when given plans should be regenerated du…
Multi-agent reinforcement learning (MARL) research is faced with a trade-off: it either uses complex environments requiring large compute resources, which makes it inaccessible to researchers with limited resources, or relies on simpler dynamics for faster execution, which makes the transferability…
Game-theoretic motion planners are a potent solution for controlling systems of multiple highly interactive robots. Most existing game-theoretic planners unrealistically assume <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a priori</i> objective fu
We present Learned Risk Metric Maps (LRMM) for real-time estimation of coherent risk metrics of high-dimensional dynamical systems operating in unstructured, partially observed environments. LRMM models are simple to design and train-requiring only procedural generation of obstacle sets, state and c…
Game-theoretic motion planners are a powerful tool for the control of interactive multi-agent robot systems. Indeed, contrary to predict-then-plan paradigms, game-theoretic planners do not ignore the interactive nature of the problem, and simultaneously predict the behaviour of other agents while co…
The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since robots are mostly safety-critical systems. This urges a forma…
We propose a new method to ensure neural ordinary differential equations (ODEs) satisfy output specifications by using invariance set propagation. Our approach uses a class of control barrier functions to transform output specifications into constraints on the parameters and inputs of the learning s…
Traditional face-to-face subjective listening test has become a challenge due to the COVID-19 pandemic. We developed a remote assessment system with Tencent Meeting, a video conferencing application, to address this issue. This paper presents our work on evaluating the reliability of the remote asse…
Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence Embedding (DSE), a self-supervised contrastive learning method tha…
Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that deviates from what the PTLM was initially trained on. In this…
Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain-specific knowledge. This challenge is magnified in natural language processing, where no general rules exist for data augmentation due to the discrete nature of natural langua…
Many recent successes in sentence representation learning have been achieved by simply fine-tuning on the Natural Language Inference (NLI) datasets with triplet loss or siamese loss. Nevertheless, they share a common weakness: sentences in a contradiction pair are not necessarily from different sema…
Ultrasound scanning plays an important role in modern clinical examinations. Thanks to its small footprint, low cost, and popularity, it has been widely used in annual physical examinations and many other diagnosis and intervention procedures. However, the scanning results depend heavily on the clin
Noise reduction technologies have been applied to enhance the intelligibility of voice communications. However, existing methods are vulnerable to complex non-stationary noisy conditions, which are commonly encountered in real world hands-free scenarios. Additionally, the existing methods do not ful…