66 accepted papers
Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computation. Management techniques, such as selective token eviction and pruning, have vastly mitigated the issues that have ar…
Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits arrive as long streams, creating a plasticity–stability dilemma: repeated locate-then-edit “hard writes” can accumulate interference over time, while rigi
This paper addresses the challenge of Lidar-Inertial Odometry (LIO) in dynamic environments, where conventional methods often fail due to their static-world assumptions. Traditional LIO algorithms perform poorly when dynamic objects dominate the scenes, particularly in geometrically sparse environme…
Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and artifacts accumulate sharply. We revisit this challenge from a cross-scale distribution transition perspective and propose CASR, a simple y
Novel view synthesis (NVS) under large view deviations remains an underexplored challenge for 3D Gaussian Splatting (3DGS). In urban scenes with limited training coverage, models often fail to maintain geometric consistency when extrapolating to unseen viewpoints, resulting in severe distortions and
In Partial Label Learning (PLL), each instance is associated with a candidate label set, with exactly one label being true. While most studies implicitly assume balanced class distributions, real-world data often exhibit severe class imbalance distributions, leading to the Long-Tailed Partial Label
A cable-driven continuum robot with high redundancy is capable of performing the tip trajectory tracking task while simultaneously satisfying additional safety constraints, such as joint limits or external obstacles in the environment. To address these challenges, efficient motion planning methods a…
Challenges in traversing dynamic clutters lie mainly in the efficient perception of the environmental dynamics and the generation of evasive behaviors considering obstacle movement. Previous solutions have made progress in explicitly modeling the dynamic obstacle motion for avoidance, but this key d
Challenges in traversing dynamic clutters lie mainly in the efficient perception of the environmental dynamics and the generation of evasive behaviors considering obstacle movement. Previous solutions have made progress in explicitly modeling the dynamic obstacle motion for avoidance, but this key d…
Legged robots hold great promise for agile and flexible mobility across diverse and unstructured terrains, inspired by the remarkable adaptability of bipeds and quadrupeds in nature. However, achieving robust autonomous locomotion in cluttered and complex environments remains a significant challenge…
Deep Reinforcement Learning (DRL) controllers for quadrupedal locomotion have demonstrated impressive performance on challenging terrains, allowing robots to execute complex skills such as climbing, running, and jumping. However, existing blind locomotion controllers often struggle to ensure safety …
Enabling robots to walk on yielding terrain is vital for applications ranging from disaster response to planetary exploration. While bipedal robots hold immense potential, their locomotion on deformable surfaces remains limited as current simulators fail to capture the spatiotemporal heterogeneity o
Enabling robots to walk on yielding terrain is vital for applications ranging from disaster response to planetary exploration. While bipedal robots hold immense potential, their locomotion on deformable surfaces remains limited as current simulators fail to capture the spatiotemporal heterogeneity o…
Post-training quantization (PTQ) is widely used to compress large language models without retraining. However, many existing weight-only methods rely on heuristic objectives and greedy rounding, thus leading to noticeable degradation under low-bit quantization In this work, we introduce OJBKQ (Objec
Computed Tomography (CT) is one of the most widely used and diagnostically information-dense imaging modalities, covering critical organs such as the heart, lungs, liver, and colon. Clinical interpretation relies on both \textbf{slice-driven} local features (e.g., sub-centimeter nodules, lesion boun…
In the robotics community, it has been a longstanding challenge for quadrupeds to achieve highly explosive movements similar to their biological counterparts. In this work, we introduce a novel training framework that achieves height-aware and omnidirectional jumping for quadrupedal robots. To facil…
Polarization-aware Neural Radiance Fields (NeRF) enables novel view synthesis of specular scenes but suffers from slow training, inefficient rendering, and material/viewpoint assumptions. 3D Gaussian Splatting (3DGS) supports real-time rendering but struggles with reflection reconstruction due to re
Continuum robots possess intrinsic compliance, high flexibility, and continuously deformable structures, making them well-suited for safe human–robot interaction (HRI). However, their continuous backbone and high degrees of freedom pose significant challenges for real-time trajectory generation: mot…
Transparent objects are common in daily life and industry, necessitating that robots be able to perceive and manipulate them. The physical properties of reflection and refraction pose challenges for accurately reconstructing the 3D geometry of transparent objects. Conventional methods, which rely on
Transparent objects are common in daily life and industry, necessitating that robots be able to perceive and manipulate them. The physical properties of reflection and refraction pose challenges for accurately reconstructing the 3D geometry of transparent objects. Conventional methods, which rely on…
Recent advances have shifted the paradigm of tabular learning toward tabular foundation models, yet their accuracy relies on a heavy inference cost that scales poorly with context size. Deep neural networks remain a highly competitive and more efficient modeling paradigm when equipped with well-desi…
Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability. However, understanding how this impacts confidence calibration for…
With the rapid growth of social media and digital photography, visually appealing images have become essential for effective communication and emotional engagement. Among the factors influencing aesthetic appeal, composition--the arrangement of visual elements within a frame--plays a crucial role. I…
Fall recovery for legged robots remains challenging, particularly on complex terrains where traditional controllers fail due to incomplete terrain perception and uncertain interactions. We present FR-Net, a learning-based framework that enables quadrupedal robots to recover from arbitrary fall poses
Obstacle avoidance for autonomousaerial vehicles like quadrotors is a popular research topic. Most existing research focuses only on static environments, and obstacle avoidance in environments with multiple dynamic obstacles remains challenging. This letter proposes a novel deep-reinforcement learni
Legged robots hold great promise for agile and flexible mobility across diverse and unstructured terrains, inspired by the remarkable adaptability of bipeds and quadrupeds in nature. However, achieving robust autonomous locomotion in cluttered and complex environments remains a significant challenge
Humanoid robot soccer presents several challenges, particularly in maintaining system stability during aggressive kicking motions while achieving precise ball trajectory control. Current solutions, whether traditional position-based control methods or reinforcement learning (RL) approaches, exhibit
The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading architecture, achieving state-of-the-art results across a range of…
Novel view synthesis is a critical task in autonomous driving. Although 3D Gaussian Splatting (3D-GS) has shown success in generating novel views, it faces challenges in maintaining high-quality rendering when viewpoints deviate significantly from the training set. This difficulty primarily stems fr…
In this paper, we employ multiple IMUs into a triple-section continuum manipulator to precisely capture the attitude data of each section’s end disk. Leveraging the sensory and mechanical hardware system, we construct a sophisticated coordinate transformation scheme to accurately identify the detail
In the robotics community, it has been a longstanding challenge for quadrupeds to achieve highly explosive movements similar to their biological counterparts. In this work, we introduce a novel training framework that achieves height-aware and omnidirectional jumping for quadrupedal robots. To facil
Mobile manipulation is a crucial problem in various real-world applications. However, existing methods have demonstrated unsatisfactory training efficiency and sparse rewards, requiring complex coordination strategies between the mobile base and arm. In this paper, we propose RM-Planner, a planning
Recent advancements in Large Language Models (LLMs) have set themselves apart with their exceptional performance in complex language modelling tasks. However, these models are also known for their significant computational and storage requirements, primarily due to the quadratic computation complexi…
Over recent years, the Transformer has become a fundamental building block for sequence modeling architectures. Yet at its core is the use of self-attention, whose memory and computational cost grow quadratically with the sequence length $N$, rendering it prohibitively expensive for long sequences.…
In this letter, a tendon-driven continuum robotic manipulator with three individual continuum sections is developed and manufactured. The main contribution is that we propose a robust and accurate shape estimation method based on the fusion of multi-IMUs for the manipulator, under the PCC (Piecewise
Image colorization is an ill-posed task, as objects within grayscale images can correspond to multiple colors, motivating researchers to establish a one-to-many relationship between objects and colors. Previous work mostly could only create an insufficient deterministic relationship. Normalizing flo…
We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or black-box optimization to generate a fixed draft model, relying instead on simple rules to generate varying draft model…
Multi-Agent Search and Rescue (MASAR) tasks, challenged by unknown environments and the unpredictable movements of unknown dynamic targets, suffer from inefficiencies in traditional map coverage techniques which require repeated sweeps. Addressing this, our study introduces a novel MASAR framework b
Due to the rapid development of the quadruped robot industry in the past decade, various commercial quadruped robots have emerged with distinct physical attributes. Different from the previous work in which the designed controller is robot-specific, this article proposes a learning-based control fra
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance.…
This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with out-of-distribution (OOD) token positions in longer sequences. We introduce…
Objects of daily life are designed to suit the human hand. Without major modifications to these objects and our environments, robots will need end-effectors with human hand-like configuration and dexterity to efficiently operate on them. Tight integration of tactile and proprioceptive sensors are al…
Robots and prostheses are increasingly designed with curvilinear surfaces for functional, aesthetic, aerodynamic, and safety reasons. Electronic skins (e-skins) capable of sensing contact location and pressure across complex, non-developable surfaces are essential for empowering next-generation robo…
This paper addresses the scarcity of large-scale datasets for accurate object-in-hand pose estimation, which is crucial for robotic in-hand manipulation within the "Perception-Planning-Control" paradigm. Specifically, we introduce VinT-6D, the first extensive multi-modal dataset integrating vision,…
Event cameras that asynchronously output low-latency event streams provide great opportunities for state estimation under challenging situations. Despite event-based visual odometry having been extensively studied in recent years, most of them are based on the monocular, while few research on stereo
Transformer-based models have achieved state-of-the-art performance on numerous NLP applications. However, long documents which are prevalent in real-world scenarios cannot be efficiently processed by transformers with the vanilla self-attention module due to their quadratic computation complexity a…
Quadruped robots, in recent years, have been increasingly used in extremely harsh and dangerous conditions. Consequently, diverse severe hardware failures may occur at any time during the working cycle of the robots. In this work, we propose a fault-tolerant (FT) control pipeline based on model-free
Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight decay, dropout, batch/layer normalization to converge faster and generalize. Label Smoothing (LS) is another simple, versati…
This letter addresses the problem of traversing through unknown, tilted, and narrow gaps for quadrotors using Deep Reinforcement Learning (DRL). Previous learning-based methods relied on accurate knowledge of the environment, including the gap's pose and size. In contrast, we integrate onboard sensi
Siamese object tracking has facilitated diversified applications for autonomous unmanned aerial vehicles (UAVs). However, they are typically trained on general images with relatively large objects instead of small objects observed from UAV. The gap on object scale between the training and inference
Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher model for every new dataset.Alternatively, one may directly w…
Event cameras are biologically-inspired vision sensors that capture pixel-level illumination changes instead of the intensity image at a fixed frame rate. They offer many advantages over the standard cameras, such as high dynamic range, high temporal resolution (low latency), no motion blur, etc. Th…
The autonomous navigation of unmanned aerial vehicles in a rapidly changing environment, such as avoiding small fast moving objects with onboard sensing, still remains a challenge. In this letter, we propose a complete system that only relies on a lightweight RGBD camera to achieve fast and accurate
For conventional aerial manipulators, the robotic arm is rigidly attached to the quadrotor. Consequently, the maneuver of the quadrotor will affect the motion of the robotic arm when it is used for tasks such as inspection. In this paper, we propose a novel aerial manipulator with a self-locking gim…
Knowledge Distillation (KD) is extensively used in Natural Language Processing to compress the pre-training and task-specific fine-tuning phases of large neural language models. A student model is trained to minimize a convex combination of the prediction loss over the labels and another over the te…
For accomplishing a variety of missions in challenging environments, the capability of navigating with full autonomy while avoiding unexpected obstacles is the most crucial requirement for UAVs in real applications. In this paper, we proposed such a computationally efficient obstacle avoidance traje…
Correlation filter (CF)-based methods have demonstrated exceptional performance in visual object tracking for unmanned aerial vehicle (UAV) applications, but suffer from the undesirable boundary effect. To solve this issue, spatially regularized correlation filters (SRDCF) proposes the spatial regul…
Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years. However, existing algorithms still face difficulties such as partial occlusion, clutter background, and other challenging visual factors. Inspired by the cutting-edge attention mechanisms, a novel object…
Correlation filter (CF) has recently exhibited promising performance in visual object tracking for unmanned aerial vehicle (UAV). Such online learning method heavily depends on the quality of the training-set, yet complicated aerial scenarios like occlusion or out of view can reduce its reliability.…
This paper presents a novel nonlinear disturbance rejection approach for high precision model-based control of hydraulic robots. While most disturbance rejection approaches make use of observers, we propose a novel adaptive Unscented Kalman Filter to estimate the disturbances in an unbiased minimum-…
Due to implicitly introduced periodic shifting of limited searching area, visual object tracking using correlation filters often has to confront undesired boundary effect. As boundary effect severely degrade the quality of object model, it has made it a challenging task for unmanned aerial vehicles…
Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects. Several approaches to enlarge search regions have been already proposed in the past years to make up for this shortcoming. However, with excessive background information, more background…
We present the first perception-aware model predictive control framework for quadrotors that unifies control and planning with respect to action and perception objectives. Our framework leverages numerical optimization to compute trajectories that satisfy the system dynamics and require control inpu…
A novel unsupervised sparse component extraction algorithm for diagnosing micro defects in thermography imaging system is presented. The approach is optimized under Variational Bayesian framework, which is fully automated and does not require manual selection of the parameters in the solution. An in…
This paper deals with the active fault-tolerant control for quadrotors which are subjected to a total rotor failure. Previous studies assume that the fault has been detected and isolated and then design a fault-tolerant controller. The present paper proposes a complete active fault-tolerant control…