57 accepted papers
Training LLM agents for complex multi-turn decision-making tasks requires extensive exploration within their environment, with reinforcement learning (RL) as a natural way. However, the open-source community currently lacks a unified RL framework capable of training agents from scratch across divers…
Visual simultaneous localization and mapping (SLAM) is of great significance for flapping-wing flying robots (FWFRs) to enhance their autonomous navigation capabilities in complex environments. However,during the motion of FWFRs, there are intense image vibrations accompanied by significant illumina…
Reinforcement learning has become a cornerstone for enhancing the reasoning capabilities of Large Language Models, where group-based approaches such as GRPO have emerged as efficient paradigms that optimize policies by leveraging intra-group performance differences. However, these methods typically …
Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classification task as the generation of brief textual descriptions to improve cross-domain generalization. However, their generali
Hand-Object Interaction (HOI) remains a core challenge in digital human video synthesis, where models must generate physically plausible contact and preserve object identity across frames. Although recent HOI reenactment approaches have achieved progress, they are typically trained and evaluated in-
High-quality geometric diagram generation presents both a challenge and an opportunity: it demands strict spatial accuracy while offering well-defined constraints to guide generation. Inspired by recent advances in geometry problem solving that employ formal languages and symbolic solvers for enhanc…
Recently, multimodal large language models (MLLMs) have achieved remarkable success in general multimodal tasks. Increasing attention has been given to leveraging MLLMs for fine-grained visual understanding, such as region-level captioning and pixel-level grounding. However, most existing approaches
Deep unfolding networks (DUNs) have achieved remarkable success and become the mainstream paradigm for spectral compressive imaging (SCI) reconstruction. Existing DUNs are derived from full-HSI imaging models, where each stage operates directly on the high-dimensional HSI, refining the entire data c
Motivated from pigeons flying in flocks, this paper delves into the outdoor flocking flight using pigeon-inspired flapping-wing robots (FWRs). Current research and implementation of cooperative flight for FWRs is scarce, generally exhibiting constrained operational environments, small number of indi
Training critique models to provide useful feedback for actor models is an effective approach in scalable oversight, especially for complex tasks like math reasoning. However, current research lacks suitable datasets for effectively training critique models and integrating them in a principled way a
Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set recognition problem. State-of-the-art approaches for GCD are usually built on multi-modality representation learning, which
Multi-step theorem prediction is a central challenge in automated reasoning. Existing neural–symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work, we explore training-free theorem prediction through the len…
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek-R1) have led to remarkable improvements through long Chain-of-Thought (CoT). However, existing benchmarks mainly focus on immediate, single-horizon tasks, failing to adequately evaluate models’ ability to understand a…
The rapid evolution of Large Language Models (LLMs) has accelerated the transition from conversational chatbots to general agents. However, effectively balancing empathetic communication with budget-aware decision-making remains an open challenge. Since existing methods fail to capture these complex…
This letter presents a saturation-triggered adaptive fault-tolerant control framework for underwater vehicles to handle concurrent thruster failures and environmental disturbances. Unlike existing methods that suffer from performance degradation when disturbances exceed predefined bounds, this paper
MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo--solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However, trajectory-based memory suffers from brevity bias, gradually los
As LLMs with agentic abilities are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging diverse resources, and managing dynamic user interactions. To address this gap, we introduce VitaBench, a chall…
Large language models (LLMs) have emerged as a promising foundation to build generally-capable agents (LLM-based agents) that can handle multi-turn decision-making tasks across various environments. However, the community lacks a unified interactive framework that covers diverse environments for com…
Process supervision, i.e., evaluating each step, is critical for complex large language model (LLM) reasoning and test-time searching with increased inference compute. Existing approaches, represented by process reward models (PRMs), primarily focus on rewarding signals up to the current step, exhib…
Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assess…
The rapid advancement of Large Vision-Language Models (VLMs), both general-domain models and those specifically tailored for remote sensing, has demonstrated exceptional perception and reasoning capabilities in Earth observation tasks. However, a benchmark for systematically evaluating their capabil…
Large language models (LLMs) face a significant challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture. While state space model (SSM) is a new type of foundational network architecture offering lower computational complexity, their performa…
Solving complex chart Q&A tasks requires advanced visual reasoning abilities in multimodal large language models (MLLMs), including recognizing key information from visual inputs and conducting reasoning over it. While fine-tuning MLLMs for reasoning is critical, collecting and annotating charts and
Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheless, the real-world data are often deviating from the UoS assumption. To address this challenge, state-of-the-art deep sub…
Visual simultaneous localization and mapping (SLAM) is of great significance for flapping-wing flying robots (FWFRs) to enhance their autonomous navigation capabilities in complex environments. However, during the motion of FWFRs, there are intense image vibrations accompanied by significant illumin
Recent research has shown an increasing interest in utilizing pre-trained large language models (LLMs) for a variety of time series applications. However, there are three main challenges when using LLMs as foundational models for time series forecasting: (1) Cross-domain generalization. (2) Cross-mo…
Hyperspectral images (HSIs) often suffer from diverse and unknown degradations during imaging, leading to severe spectral and spatial distortions. Existing HSI restoration methods typically rely on specific degradation assumptions, limiting their effectiveness in complex scenarios. In this paper, we…
Evaluating massive-scale point cloud maps in Simultaneous Localization and Mapping (SLAM) still remains challenging due to three limitations: lack of unified standards, poor robustness to noise, and computational inefficiency. We propose MapEval, a novel framework for point cloud map assessment. Our
Self-improvement methods enable large language models (LLMs) to generate solutions themselves and iteratively train on filtered, high-quality rationales. This process proves effective and reduces the reliance on human supervision in LLMs’ reasoning, but the performance soon plateaus. We delve into t…
In this article, a biomimetic rope-driven soft robotic arm (RDSRA) is designed with its kinematic and dynamic modeling, incorporating the bending and adsorption structures of an elephant trunk and the lamellar structure of a gecko toe to grasp objects of various shapes and materials. Then, a state a
Aerial robots have demonstrated significant potential in suspended cargo transportation, especially in industries such as logistics and food delivery. Due to the underactuated and nonlinear dynamics of the cable-suspended system, directly tracking a given trajectory with a multicopter without modify
Experience Replay (ER) allows Deep Reinforcement Learning (RL) agent to reuse past experience, as though recall the same Experience repeatedly. ER enables RL algorithm to be trained by reusing previous states, so that RL agent can obtain more accurate value estimations and action selections. Current…
Space-limited U-shape bend is a safety-critical scenario that requires the high maneuverability of vehicles. However, due to the non-holonomic nature of the vehicle, it is difficult to perform flexible U-turns without intricate adjustments, which is detrimental to the efficient execution of tasks. T
The incredibly efficient and agile flight abilities of butterflies have become the inspiration for the design of butterfly-inspired flapping-wing robots, but their intricate flight mechanisms bring challenges to the flight control of these robots. Aerodynamic simulation emerges as an effective tool
For aerial swarms, formation flight has been applied in various scenes. However, most existing works do not consider balancing the conflicting requirements among keeping formation, keeping the smoothness of trajectories, and obstacle avoidance within the limited time. To address this issue, we propo…
Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words, but also due to the scarcity of relevant data resources, and…
Flexible sensors for joint angle measurement play a crucial role in various human-robot interaction applications. In previous studies, sensors with various sensing mechanisms have been developed. Among them, optical waveguide sensors exhibit high resistance to environmental factors (such as temperat…
Large language models (LLMs) have achieved tremendous success in understanding language and processing text. However, question-answering (QA) on lengthy documents faces challenges of resource constraints and a high propensity for errors, even for the most advanced models such as GPT-4 and Claude2.In…
Large-scale high-resolution (HR) land-cover mapping is a vital task to survey the Earth's surface and resolve many challenges facing humanity. However it is still a non-trivial task hindered by complex ground details various landforms and the scarcity of accurate training labels over a wide-span geo…
Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention’s quadratic computational demands. Many sought to mitigate this by restricting the attenti…
This paper proposes a LiDAR-based goal-seeking and exploration framework, addressing the efficiency of online obstacle avoidance in unstructured environments populated with static and moving obstacles. This framework addresses two significant challenges associated with traditional dynamic control ba…
This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a…
Large language models (LLMs) have shown promising abilities of in-context learning (ICL), adapting swiftly to new tasks with only few-shot demonstrations. However, current few-shot methods heavily depend on high-quality, query-specific demos, which are often lacking. When faced with out-of-demonstra…
In this paper, we propose **R**$^3$: Learning **R**easoning through **R**everse Curriculum **R**einforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models. The core challenge in applying RL to complex reas…
As Large Language Models (LLMs) become increasingly influential in reasoning tasks, ensuring their trustworthiness and introspective self-awareness is critical. This research introduces the Think-Solve-Verify (TSV) framework, an innovative strategy tailored to explore LLMs’ trustworthiness, introspe…
In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by modifying the architecture, augmenting data and designing new losses. However, we find previous models still suffer from in…
The development of foundation vision models has pushed the general visual recognition to a high level, but cannot well address the fine-grained recognition in specialized domain such as invasive species classification. Identifying and managing invasive species has strong social and ecological value.…
"Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues. To make up for the absence of source data,…
The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing sequential recommendation methods only exploit the local context information of an individual interaction sequence and learn model parameters solely based on the…
Endowing robots with human-like abilities to perform motor skills smoothly and naturally is one of the important goals of robotics. Learning from demonstration (LfD) has been successfully applied for learning tasks on robots, for which the human tutor can demonstrate a successful execution. Learning
"Convolutional neural networks have been widely developed for hyperspectral image (HSI) restoration. However, making full use of the spatial-spectral information of HSIs still remains a challenge. In this work, we disentangle the 3D convolution into lightweight 2D spatial and spectral convolutions,…
The fusion of input and guidance images that have a tradeoff in their information (e.g., hyperspectral and RGB image fusion or pansharpening) can be interpreted as one general problem. However, previous studies applied a task-specific handcrafted prior and did not address the problems with a unified…
This paper proposed an adaptive neural admittance control strategy for collision avoidance in human-robot collaborative tasks. In order to ensure that the robot end-effector can avoid collisions with surroundings, robot should be operated compliantly by human within a constrained task space. An impe…
Low-rank matrix completion (LRMC) is a classical model in both computer vision (CV) and machine learning, and has been successfully applied to various real applications. In the recent CV tasks, the completion is usually employed on the variants of data, such as "non-local" or filtered, rather than t…
Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, while their denoising performance benefits little from more spectral bands, the running time of these methods significantly increases. In this paper, we cla…
In recent studies, tensor ring (TR) decomposition has shown to be effective in data compression and representation. However, the existing TR-based completion methods only exploit the global low-rank property of the visual data. When applying them to remote sensing (RS) image processing, the spatial…
To represent a text as a bag of properly identified “phrases” and use the representation for processing the text is proved to be useful. The key question here is how to identify the phrases and represent them. The traditional method of utilizing n-grams can be regarded as an approximation of the app…