97 accepted papers
We study Sparse Signal Recovery (SSR) methods for multichannel imaging with compressed {forward and backward} operators that preserve reconstruction accuracy. We propose a Compressed Block-Convolutional (C-BC) measurement model based on a low-rank Convolutional Neural Network (CNN) decomposition tha…
Sampling-based path planning algorithms like the Fast Marching Tree (FMT<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">*</sup>) often suffer from redundant exploration and inefficient sampling in complex 3D environments. To tackle these issues, this pa
Large Language Models (LLMs) have been demonstrating strong reasoning capability with their chain-of-thoughts (CoT), which are routinely used by humans to judge answer quality. This reliance creates a powerful yet fragile basis for trust. In this work, we study an underexplored problem: whether LLMs…
Interpreting residual architectures as discretizations of Ordinary Differential Equations characterizes the forward pass as a continuous latent flow. Although this framework defines the mechanics of inference, conventional training paradigms primarily constrain the terminal state, leaving the interm…
Central nervous system (CNS) drug discovery is constrained by an immense and sparse chemical search space. Meanwhile, molecules that simultaneously achieve brain penetration, target efficacy, and synthesizability are extremely scarce. However, existing generative models rarely couple rigorous multi-
As embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex, human-centered social behaviors. We introduce FreeAskWorld, an interactive simulation framework that integrates large l
Recent years have witnessed remarkable progress in multimodal learning within computational pathology. Existing models primarily rely on vision and language modalities; however, language alone lacks molecular specificity and offers limited pathological supervision, leading to representational bottle…
Learning nonlinear dynamical models from data is central to control. Two fundamental challenges exist: (1) how to learn accurate models from limited data, and (2) how to ensure the learned models are suitable for control design of the nominal system. We address both by enforcing a critical \emph{a p…
Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers pro
Accurate detection of offensive content on social media demands high-quality labeled data; however, such data is often scarce due to the low prevalence of offensive instances and the high cost of manual annotation. To address this low-resource challenge, we propose a self-training framework that lev
Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep resear
Leaderboards for large reasoning models (LRMs) have turned evaluation into a competition, incentivizing developers to optimize directly on benchmark suites. A shortcut to achieving higher rankings is to incorporate evaluation benchmarks into the training data, thereby yielding inflated performance,…
Large Language Models (LLMs) can compose poetry, but how far are they from human poets? In this paper, we introduce POEMetric, the first comprehensive framework for poetry evaluation, examining 1) basic instruction-following abilities in generating poems according to a certain form and theme, 2) adv…
Pre-trained models have demonstrated exceptional generalization capabilities in time-series forecasting; however, adapting them to evolving data distributions remains a significant challenge. A key hurdle lies in accessing the original training data, as fine-tuning solely on new data often leads to
Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection
Imitation learning (IL) offers a promising pathway for enabling surgical robots to perform autonomous wound repair. However, existing methods often neglect spatial semantics and wound-shape information, leading to poor generalization and low success rates. This paper presents the <bold>S</bold>patia
Multimodal large language models (MLLMs) are increasingly used for real-world tasks involving multi-step reasoning and long-form generation, where reliability requires grounding model outputs in heterogeneous input sources and verifying individual factual claims. However, existing multimodal groundi…
Policy optimization methods benefit from a simple and tractable policy parametrization, usually the Gaussian for continuous action spaces. In this paper, we consider a broader policy family that remains tractable: the $q$-exponential family. This family of policies is flexible, allowing the specif…
Recently, many studies have demonstrated that exclusively incorporating OCR-derived text and spatial layouts with large language models (LLMs) can be highly effective for document understanding tasks. However, existing methods that integrate spatial layouts with text have limitations, such as produc…
Knowledge conflict arises from discrepancies between information in the context of a large language model (LLM) and the knowledge stored in its parameters. This can hurt performance when using standard decoding techniques, which tend to ignore the context. Existing test-time contrastive methods seek…
This paper presents AlphaOne ( 𝛼1 ), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. 𝛼1 first introduces 𝛼 moment, which represents the scaled thinking phase with a universal parameter 𝛼 .Within this scaled pre- 𝛼 moment phase, it dynamically sc
Recent work has demonstrated the remarkable potential of Large Language Models (LLMs) in test-time scaling. By making models think before answering, they are able to achieve much higher accuracy with extra inference computation.However, in many real-world scenarios, models are used under time constr
Encoding time series into tokens and using language models for processing has been shown to substantially augment the models' ability to generalize to unseen tasks. However, existing language models for time series forecasting encounter several obstacles, including aliasing distortion and prolonged…
As small unmanned aerial vehicles (UAVs) become increasingly prevalent, there is growing concern regarding their impact on public safety and privacy, highlighting the need for advanced tracking and trajectory estimation solutions. In response, this paper introduces a novel framework that utilizes au…
Conformal Prediction (CP) is a powerful statistical machine learning tool to construct uncertainty sets with coverage guarantees, which has fueled its extensive adoption in generating prediction regions for decision-making tasks, e.g., Trajectory Optimization (TO) in uncertain environments. However,…
Detecting and tracking ground objects using earth observation imagery remains a significant challenge in the field of remote sensing. Continuous maritime ship tracking is crucial for applications such as maritime search and rescue, law enforcement, and shipping analysis. However, most current ship t…
Skeleton sequences for action recognition are with complex temporal dynamics due to various factors such as speed variation and different activities. It is crucial and essential to model variation changes in the temporal dimension. In recent years, skeleton sequence is always modeled as a graph stru…
Enabling mobile robots to perform long-term tasks in dynamic real-world environments is a formidable challenge, especially when the environment changes frequently due to human-robot interactions or the robot's own actions. Traditional methods typically assume static scenes, which limits their applic
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image understanding, but there is still a lack of comparable datasets…
In recent years, vision-based end-to-end autonomous driving has emerged as a new paradigm. However, popular end-to-end approaches typically rely on visual feature extraction networks trained under label supervision. This limited supervision framework restricts the generality and applicability of dri…
Sparse continuous policies are distributions that can choose some actions at random yet keep strictly zero probability for the other actions, which are radically different from the Gaussian. They have important real-world implications, e.g. in modeling safety-critical tasks like medicine. The combin…
Video Text Spotting (VTS) is a fundamental visual task that aims to predict the trajectories and content of texts in a video. Previous works usually conduct local associations and apply IoU-based distance and complex post-processing procedures to boost performance, ignoring the abundant temporal inf…
Humor is previously regarded as a gift exclusive to humans for the following reasons. Humor is a culturally nuanced aspect of human language, presenting challenges for its understanding and generation. Humor generation necessitates a multi-hop reasoning process, with each hop founded on proper ratio…
Multidimensional data acquisition often requires extensive time and poses significant challenges for hardware and software regarding data storage and processing. Rather than designing a single compression matrix as in conventional compressed sensing, structured compressed sensing yields dimension-sp…
Effective communication is an essential component in collaborative multi-agent systems. Situations where explicit messaging is not feasible have been common in human society throughout history, which motivate the study of implicit communication. Previous works on learning implicit communication most…
Humans rely on multisensory integration to perceive spatial environments, where auditory cues enable sound source localization in three-dimensional space. Despite the critical role of spatial audio in immersive technologies such as VR/AR, most existing multimodal datasets provide only monaural audi…
In recent years, while generative AI has advanced significantly in image generation, video generation continues to face challenges in controllability, length, and detail quality, which hinder its application. We present MimicMotion, a framework for generating high-quality human videos of arbitrary l…
Off-Policy Evaluation (OPE) aims to estimate the value of a target policy using offline data collected from potentially different policies. In real-world applications, however, logged data often suffers from missingness. While OPE has been extensively studied in the literature, a theoretical underst…
Vision Language Models (VLMs) can produce unintended and harmful content when exposed to adversarial attacks, particularly because their vision capabilities create new vulnerabilities. Existing defenses, such as input preprocessing, adversarial training, and response evaluation-based methods, are of…
Benchmark Data Contamination (BDC)—the inclusion of benchmark testing samples in the training set—has raised increasing concerns in Large Language Model (LLM) evaluation, leading to falsely inflated performance estimates and undermining evaluation reliability. To address this, researchers have propo…
The rapid advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced capabilities in Document Understanding. However, prevailing benchmarks like DocVQA and ChartQA predominantly comprise scanned or digital documents, inadequately reflecting the intricate challenges posed by
In recent years, many fusion algorithms based on multi-scale transform or neural networks have been proposed to improve medical image fusion (MIF) performance. However, there is still enormous potential to explore the combination of different fusion theories. In this paper, we propose a novel MIF fr…
Large Language Models (LLMs) can elicit unintended and even harmful content when misaligned with human values, posing severe risks to users and society. To mitigate these risks, current evaluation benchmarks predominantly employ expert-designed contextual scenarios to assess how well LLMs align with…
In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection. Despite considerable attention to these issues separately,…
A carbon market is a market-based tool that incentivizes economic agents to align individual profits with the global utility, i.e., reducing carbon emissions to tackle climate change. Cap and trade stands as a critical principle based on allocating and trading carbon allowances (carbon emission cred…
In the current environment, psychological issues are prevalent and widespread, with social media serving as a key outlet for individuals to share their feelings. This results in the generation of vast quantities of data daily, where negative emotions have the potential to precipitate crisis situatio…
"Domain Generalization (DG), designed to enhance out-of-distribution (OOD) generalization, is all about learning invariance against domain shifts utilizing sufficient supervision signals. Yet, the scarcity of such labeled data has led to the rise of unsupervised domain generalization (UDG) — a more…
Reinforcement learning (RL) algorithms are typically based on optimizing a Markov Decision Process (MDP) using the optimal Bellman equation. Recent studies have revealed that focusing the optimization of Bellman equations solely on in-sample actions tends to result in more stable optimization, espec…
When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of humans' inference of characters' mental states, *i.e.*, theory-of-…
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theor…
In multi-object stacking scenarios, exploring the relationships among objects and determining the correct sequence of operations are crucial for robotic manipulation. However, previous algorithms inefficiently combine global and local information, often focusing solely on the local features of objec…
Strategic subsampling has become a focal point due to its effectiveness in compressing data, particularly in the Full Matrix Capture (FMC) approach in ultrasonic imaging. This paper introduces the Joint Deep Probabilistic Subsampling (J-DPS) method, which aims to learn optimal selection matrices sim…
In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which possess the potential to transport harmful payloads or independently cause damage, we introduce MMAUD: a comprehensive Multi-Modal Anti-UAV Dataset. MMAUD addresses a critical gap in contemporary threat dete…
We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or ``similar" environments. In contrast, our problem setup allows…
Collision-free navigation is a critical issue in robotic systems as the environment is often dynamic and uncertain. This paper investigates a data-stream-driven motion control problem for mobile robots to avoid randomly moving obstacles when the probability distribution of the obstacle’s movement is…
Semantic segmentation plays a pivotal role in many robotic applications requiring high-level scene understanding, such as smart farming, where the precise identification of trees or plants can aid navigation and crop monitoring tasks. While deep-learning-based semantic segmentation approaches have r…
The surge in Large Language Models (LLMs) has revolutionized natural language processing, but fine-tuning them for specific tasks often encounters challenges in balancing performance and preserving general instruction-following abilities. In this paper, we posit that the distribution gap between tas…
Recently, the real-world applications of reinforcement learning (RL) have seen the problem of taking actions in an out-of-distribution (OOD) state. However, most existing research is limited to take actions to narrow the visited training distribution and OOD, and does not consider the efficiency to…
Generations from large language models (LLMs) can be improved by sampling and scoring multiple solutions to select a final answer. Current “sample and select” methods such as self-consistency (SC) rely on majority voting to score answers. However, when tasks have many distinct and valid answers, sel…
Recent research has focused on using large language models (LLMs) to generate explanations for hate speech through fine-tuning or prompting. Despite the growing interest in this area, these generated explanations' effectiveness and potential limitations remain poorly understood. A key concern is tha…
Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains a critical bottleneck, particularly for natural policy gradient (NPG) methods, which are second-order. To address this…
Offline reinforcement learning (RL) offers an appealing approach to real-world tasks by learning policies from pre-collected datasets without interacting with the environment. However, the performance of existing offline RL algorithms heavily depends on the scale and state-action space coverage of d…
Manipulation relationship detection (MRD) aims to guide the robot to grasp objects in the right order, which is important to ensure the safety and reliability of grasping in object stacked scenes. Previous works infer manipulation relationship by deep neural network trained with data collected from…
Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-le…
Experience replay, which stores transitions in a replay memory for repeated use, plays an important role of improving sample efficiency in reinforcement learning. Existing techniques such as reweighted sampling, episodic learning and reverse sweep update further process the information in the replay…
Structured dropout approaches, such as attention dropout and DropHead, have been investigated to regularize the multi-head attention mechanism in Transformers. In this paper, we propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting. Specifically,…
Reinforcement learning (RL) agents can leverage batches of previously collected data to extract a reasonable control policy. An emerging issue in this offline RL setting, however, is that the bootstrapping update underlying many of our methods suffers from insufficient action-coverage: standard max…
LiDAR SLAM has become one of the major localization systems for ground vehicles since LiDAR Odometry And Mapping (LOAM). Many extension works on LOAM mainly leverage one specific constraint to improve the performance, e.g., information from on-board sensors such as loop closure and inertial state; p
Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a language query. Existing techniques achieve such alignment by exploiting dense boundary and bounding box annotations, which can be prohibitively expensive. To bridge the gap, we investigate the weakly-supervi…
Lifelong language learning aims to stream learning NLP tasks while retaining knowledge of previous tasks. Previous works based on the language model and following data-free constraint approaches have explored formatting all data as “begin token (B) + context (C) + question (Q) + answer (A)” for diff…
Prompt-based learning (i.e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model. In this paper, we propose Automatic Multi-Label Prompting (AMuLaP), a simple yet effective method to automatically select label mappings for few-shot text classification w…
Few-shot object detection (FSOD) has attracted more attention in computer vision, where only very few training examples are presented during model learning process. A commonly-overlooked issue in FSOD is that novel classes are usually classified as background clutters in the pre-training process. An…
Few-shot segmentation aims at segmenting target object areas with only a few labeled samples. Previous methods extract class-specific prototypes to guide segmentation. How-ever, using one or more prototypes to represent the whole object inevitably drops vital spatial information, ignoring many detai…
The joint multiple Intent Detection (ID) and Slot Filling (SF) is a significant challenge in spoken language understanding. Because the slots in an utterance may relate to multi-intents, most existing approaches focus on utilizing task-specific components to capture the relations between intents and…
Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn latent-level interpretable representations of sentences. In this…
Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language models’ pretraining (Radford et al., 2019). Can zero-shot genera…
"Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however, usually lack spatial information from neighboring frames a…
Despite the impressive progress achieved in robotic grasping, robots are not skilled in sophisticated tasks (e.g. search and grasp a specified target in clutter). Such tasks involve not only grasping but the comprehensive perception of the world (e.g. the object relationships). Recently, encouraging
Multi-hop QA requires the machine to answer complex questions through finding multiple clues and reasoning, and provide explanatory evidence to demonstrate the machine’s reasoning process. We propose Relation Extractor-Reader and Comparator (RERC), a three-stage framework based on complex question d…
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest. To improve the relevancy of retrieved knowledge, we propose a neural entity linking (NEL) approach. Different from formal documents, such as news, conversationa…
Simultaneous Localization and Mapping (SLAM) has wide robotic applications such as autonomous driving and unmanned aerial vehicles. Both computational efficiency and localization accuracy are of great importance towards a good SLAM system. Existing works on LiDAR based SLAM often formulate the probl…
Simultaneous Localization And Mapping (SLAM) is a task to estimate the robot location and to reconstruct the environment based on observation from sensors such as LIght Detection And Ranging (LiDAR) and camera. It is widely used in robotic applications such as autonomous driving and drone delivery.
The LIght Detection And Ranging (LiDAR) sensor has become one of the most important perceptual devices due to its important role in simultaneous localization and mapping (SLAM). Existing SLAM methods are mainly developed for mechanical LiDAR sensors, which are often adopted by large scale robots. Re
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved. This may result in intent classification and slot tagging errors. In this work, we propo…
Forecasting future trajectories of multiple pedestrians in a crowded environment is a challenging problem due to the complex interactions among the pedestrians. The interactions can be asymmetric and their influences may vary over time. Moreover, each pedestrian can exhibit different behavior at any…
Loop closure detection is an essential and challenging problem in simultaneous localization and mapping (SLAM). It is often tackled with light detection and ranging (LiDAR) sensor due to its view-point and illumination invariant properties. Existing works on 3D loop closure detection often leverage…
As an essential component of visual simultaneous localization and mapping (SLAM), place recognition is crucial for robot navigation and autonomous driving. Existing methods often formulate visual place recognition as feature matching, which is computationally expensive for many robotic applications…
Estimating the robot's heading is a crucial requirement in odometry systems which are attempting to estimate the movement trajectory of a robot. Small errors in the orientation estimation result in a significant difference between the estimated and real trajectory, and failure of the odometry system
Multi-human tracking in the crowded environment is a challenging problem due to occlusions, pose change, viewpoint variation and cluttered background. In this work, we propose a robust feature learning for tracking-by-detection methods based on second-order attention network that can capture higher-…
Long Short-Term Memory (LSTM) has been proven an efficient way to model sequential data, because of its ability to overcome the gradient diminishing problem during training. However, due to the limited memory capacity in LSTM cells, LSTM is weak in capturing long-time dependency in sequential data.…
Machine learning models are changing the paradigm of molecular modeling, which is a fundamental tool for material science, chemistry, and computational biology. Of particular interest is the inter-atomic potential energy surface (PES). Here we develop Deep Potential - Smooth Edition (DeepPot-SE), an…
Energy has been increasingly generated or collected by different entities on the power grid (e.g., universities, hospitals and households) via solar panels, wind turbines or local generators in the past decade. With local energy, such electricity consumers can be considered as “microgrids” which can…
Drift and scale ambiguity are two main issues which reduce localization accuracy in monocular visual odometry (MVO). It is necessary to propose a unified model to represent these measurement uncertainties. In this paper, we present a geometric map-assisted localization approach for mobile robots equ
Hierarchical dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method to learn a hierarchy of two overcomplete synthesis dictionaries with an image classification goal. The classification objective in some sense…
In this paper, we are interested in modeling the diffusion of information in a multilayer network of agents using a thermodynamic diffusion approach. The state of each agent is viewed as a topic mixture, to describe his/her resources, and represented by a distribution over multiple topics. We observ…
In the pharmaceutical industry, quality is often measured by the impact of a product on a population. Knowledge about the behaviour of mosquitos responding to a repellent is a case in point in helping to improve the effect of insect repellent. It is ideally carried out using 3D videos which require…
Single-carrier with frequency domain equalization (SC-FDE) has been considered for bandwidth efficiency underwater acoustic (UWA) communication recently due to its reduced computational complexity and low peak-to-average power ratio. A multi-channel time-frequency domain equalization method for pseu…