62 accepted papers
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inherently vulnerable to knowledge overshadowing—a phenomenon where critical information is overshadowed during generation.
Task and Motion Planning (TAMP) frameworks for bimanual robots are limited by the combinatorial explosion at the task planning level, which can negatively affect human-robot interaction. This work introduces BAG-Learn Planning, an efficient learning-based task planning approach that combines a Bio-I…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key ingredient for unlocking complex reasoning capabilities in large language models. Recent work ProRL \citep{liu2025prorl} has shown promise in scaling RL by increasing the number of training steps. However, performance plateau…
Control Barrier Function (CBF) based quadratic programs (QPs) have become an effective method for enforcing safety in safety-critical systems and robotics. However, these methods often suffer from infeasibility or overly conservative relaxations when handling multiple constraints, potentially compro…
While Large Language Models (LLMs) demonstrate immense potential for automating integrated circuit (IC) development, their practical deployment is fundamentally limited by restricted context windows. Existing context-extension methods struggle to achieve effective semantic modeling and thorough mult
Large Language Models (LLMs) have shown promising results in automating formal verification. However, existing approaches treat proof generation as a static, end-to-end prediction over source code, relying on limited verifier feedback and lacking access to concrete program behaviors. We present EXVE…
We introduce FIXME, the first end-to-end and large-scale benchmark for evaluating Large Language Models (LLMs) in hardware design functional verification (FV). Comprising 747 tasks derived from real-world hardware designs, FIXME spans five core FV sub-sets: specification comprehension, reference mod
In this letter, we propose a safety-critical compliant control strategy designed to strictly enforce interaction force constraints during the physical interaction of robots with environments. The interaction force constraint is interpreted as a new force-constrained control barrier function (FC-CBF)
We propose PRED-MPPI, the first MPPI variant that seamlessly integrates real-time disturbance preview and adaptive discretization for quadrotor tracking control under significant model inaccuracies and time-varying disturbances. Unlike prior MPPI variants (e.g., mathcal{L}_1-MPPI, DA-MPPI), which as…
Visual servoing is fundamental to robotic applications, enabling precise positioning and control. However, applying it to textureless objects remains a challenge due to the absence of reliable visual features. Moreover, adverse visual conditions, such as occlusions, often corrupt visual feedback, le…
The coordinated motion of the trolley and hoisting rope improves crane flexibility but poses challenges in precise trajectory conversion and tracking due to disturbances and inaccessible low-level controllers. This letter proposes a disturbance-aware high-precision trajectory planning method integra
The rubber-tired container gantry crane (RTG) is a type of heavy-duty lifting equipment commonly used in container yards, which is driven by two-side rubber tires and steered via differential drive. While moving along the desired path, the RTG must remain centered of the lane with restricted heading
As the Internet and social media evolve rapidly, distinguishing credible news from a vast amount of complex information poses a significant challenge. Due to the suddenness and instability of news events, the authenticity labels of news can potentially shift as events develop, making it crucial for
This paper proposes a new variable gain sliding mode filter augmented by variable windowing for achieving smooth and reactive response over a broad range of input frequencies. The proposed filter can be seen as a synergistic combination of Kikuuwe et al.'s [1] sliding mode filter with varying gain a
Knowledge Base Question Answering (KBQA) aims to extract accurate answers from the Knowledge Base (KB). Traditional Semantic Parsing (SP)-based methods are widely used but struggle with complex queries. Recently, large language models (LLMs) have shown promise in improving KBQA performance. However,
Model Predictive Path Integral (MPPI) controllers are drawing increasing attention for their ability to efficiently handle complex systems by leveraging GPU acceleration while with flexible prediction models and cost functions. However, their performance generally degrades with low-quality predictio
The parametric array loudspeaker produces highly directional sound via a nonlinear process in air, which also introduces inherent baseband distortions. However, conventional recursive modulators employed to compensate for nonlinearity demand substantially increased bandwidth and are not optimized fo…
Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approac…
Long video understanding with Large Language Models (LLMs) enables the description of objects that are not explicitly present in the training data. However, continuous changes in known objects and the emergence of new ones require up-to-date knowledge of objects and their dynamics for effective unde
A flexible active safety motion (FASM) control approach is proposed for collision avoidance in robot manipulators. The key feature is the use of control barrier functions (CBFs) to design flexible CBF-guided safety criteria (CBFSC) with dynamically optimized decay rates, providing both flexibility a
Temporal graph neural networks (TGNN) have achieved significant momentum in many real-world dynamic graph tasks. While most existing TGNN attack methods assume worst-case scenarios where attackers have complete knowledge of the input graph, the assumption may not always hold in real-world situations…
Ensuring safety is crucial to promote the application of robot manipulators in open workspaces. Factors such as sensor errors or unpredictable collisions make the environment full of uncertainties. In this work, we investigate these potential safety challenges on redundant robot manipulators, and pr
In response to the problems of missed detection, false detection, and slow detection speed in surface defect detection of strip alloy material, this paper proposes an improved YOLOv8 based algorithm for surface defect detection of strip alloy material. To enhance multi-scale feature fusion, we first…
Large Language Models (LLMs) have been increasingly used to optimize code efficiency. Evaluating their effectiveness and further suggesting optimization opportunities often rely on high-quality tests to demonstrate the performance bottlenecks presented in the program. However, existing approaches re…
This paper proposes a task-oriented model predictive control (ToMPC) framework for safe and efficient robotic manipulation in open workspaces. The framework unifies collision-free motion and robot-environment interaction to address diverse scenarios. Additionally, it introduces task-oriented obstacl
Style transfer is an artistic research topic within a series of generative tasks, and it is quite challenging to stably and reliably guide the generation of images with the expected content and style. Early methods followed a predefined style, defined by a reference image, and applied it to another…
6D pose estimation of textureless shiny objects has become an essential problem in many robotic applications. Many pose estimators require high-quality depth data, often measured by structured light cameras. However, when objects have shiny surfaces (e.g., metal parts), these cameras fail to sense c…
Recently, significant progress has been made in employing Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering (KBQA) tasks. Previous work utilize LLMs to generate query statements on Knowledge Bases (KBs) for retrieving answers. However, LLMs often generate…
Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and hindering their applicability in more challenging scenarios. In cont…
To achieve high-accuracy manipulation in the presence of unknown disturbances, we propose two novel efficient and robust motion control schemes for high-dimensional robot manipulators. Both controllers incorporate an unknown system dynamics estimator (USDE) to estimate disturbances without requiring…
Among the remarkable successes of Reinforcement Learning (RL), self-play algorithms have played a crucial role in solving competitive games. However, current self-play RL methods commonly optimize the agent to maximize the expected win-rates against its current or historical copies, resulting in a l…
Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its furthe…
Transformer's recent integration into style transfer leverages its proficiency in establishing long-range dependencies, albeit at the expense of attenuated local modeling. This paper introduces Strips Window Attention Transformer (S2WAT), a novel hierarchical vision transformer designed for style tr…
To mitigate the limitation that the classical reinforcement learning (RL) framework heavily relies on identical training and test environments, Distributionally Robust RL (DRRL) has been proposed to enhance performance across a range of environments, possibly including unknown test environments. As…
One way to personalize chatbot interactions is by establishing common ground with the intended reader. A domain where establishing mutual understanding could be particularly impactful is vaccine concerns and misinformation. Vaccine interventions are forms of messaging which aim to answer concerns ex…
3D object-level mapping is a fundamental problem in robotics, which is especially challenging when object CAD models are unavailable during inference. We propose a framework that can reconstruct high-quality object-level maps for unknown objects. Our approach takes multiple RGB-D images as input and…
6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core idea of our approach is to decouple 6D pose estimation into a s…
Prior research on policy adaptation in multi-agent games has often relied on online interaction with the target agent in training, which can be expensive and impractical in real-world scenarios. Inspired by recent progress in offline reinforcement learn- ing, this paper studies offline policy adapta…
Federated learning (FL) is a privacy-enhanced distributed machine learning framework, in which multiple clients collaboratively train a global model by exchanging their model updates without sharing local private data. However, the adversary can use gradient inversion attacks to reveal the clients'…
Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works have shown that extracting primitive skills from the recurr…
Vision Transformer (ViT) is an attention-based model architecture that has demonstrated superior performance on many computer vision tasks. However, its security properties, in particular, the robustness against adversarial attacks, are yet to be thoroughly studied. Recent works have shown that ViT…
In weakly supervised sound event detection (SED), only coarse-grained labels are available, and thus the supervision information is quite limited. To fully utilize prior knowledge of the time-frequency masks of each sound event, we propose a novel multi-task learning (MTL) method that takes SED as t…
Polyphonic sound event localization and detection (SELD) aims at detecting types of sound events with corresponding temporal activities and spatial locations. In this paper, a trackwise ensemble event independent network with a novel data augmentation method is proposed. The proposed model is based…
Unsupervised pre-training in reinforcement learning enables the agent to gain prior environmental knowledge, which is then fine-tuned in the supervised stage to quickly adapt to various downstream tasks. In the absence of task-related rewards, pre-training aims to acquire policies (i.e., behaviors)
Depth acquisition with the active stereo camera is a challenging task for highly reflective objects. When setup permits, multi-view fusion can provide increased levels of depth completion. However, due to the slow acquisition speed of high-end active stereo cameras, collecting a large number of view…
Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a…
In zero-sum games, an NE strategy tends to be overly conservative confronted with opponents of limited rationality, because it does not actively exploit their weaknesses. From another perspective, best responding to an estimated opponent model is vulnerable to estimation errors and lacks safety guar…
Nowadays, deep-learning based NLP models are usually trained with large-scale third-party data which can be easily injected with malicious backdoors. Thus, BackDoor Attack (BDA) study has become a trending research to help promote the robustness of an NLP system. Text-based BDA aims to train a poiso…
Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as financial related problems, many engineering problems treat f…
Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and a…
Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents. However, such sharing may lead agents to behave similarly and limit their coordination capacity. In this paper, we aim t…
Although previous works for point clouds analysis have achieved remarkable performance, it is difficult for them to achieve a good trade-off between accuracy and complexity. In this paper, we present an efficient and lightweight neural network for point clouds analysis, named HIGCNN, which can achie…
Reinforcement Learning (RL) agents are often fed with large-dimensional observations to achieve the ideal performance in complex environments. Unfortunately, the massive observation space usually contains useless or even adverse features, which leads to low sample efficiency. Existing methods rely o
The reliable fusion of depth maps from multiple viewpoints has become an important problem in many 3D reconstruction pipelines. In this work, we investigate its impact on robotic bin-picking tasks such as 6D object pose estimation. The performance of object pose estimation relies heavily on the qual
In robotic bin-picking applications, the perception of texture-less, highly reflective parts is a valuable but challenging task. The high glossiness can introduce fake edges in RGB images and inaccurate depth measurements, especially in heavily cluttered bin scenarios. In this paper, we present the…
The paper proposes an efficient, robust, and reconfigurable technique to suppress various types of noises for any sampling rate. The theoretical analyses, subjective and objective test results show that the proposed noise suppression (NS) solution significantly enhances the speech transmission index…
The developments of Rademacher complexity and PAC-Bayesian theory have been largely independent. One exception is the PAC-Bayes theorem of Kakade, Sridharan, and Tewari (2008), which is established via Rademacher complexity theory by viewing Gibbs classifiers as linear operators. The goal of this pa…
Automatic speech recognition (ASR), audio quality, and loudness are key performance indicators (KPIs) in smart speakers. To improve all these KPIs, audio dynamics processing is a crucial component in related systems. Unfortunately, single-band and existing multiband dynamics processing (MBDP) scheme…
The paper proposes an efficient signal processing system mainly consisting of an adaptation-based nonlinear echo cancellation (NLEC) layer and a joint perceptual subband residual echo suppression (SBRES) layer and noise reduction (SBNR) layer. The theoretical analyses, subjective and objective test…
Automatic speech recognition is now playing an important role in volume control and adjustment of modern smart speakers. According to the recognition results by using the advanced deep neural network technology, this paper proposes an efficient processing system for automatic volume control (AVC) an…
Based on the signal model of ear canals, a novel method for solving the inverse problem of estimating the unique solution of the ear canal area function and the eardrum reflection coefficient given the acoustic input impedance at the entrance of an ear canal is presented. Up-sampling techniques to i…
Previously, a family of memory proportionate affine projection (MPAP) algorithms has been proposed by taking into account the “history” of the proportionate factors for sparse system identification. This paper presents a low-complexity implementation of this family of MPAP algorithms. Two most impor…