63 accepted papers
Despite significant advances in talking avatar generation, existing methods face critical challenges: insufficient text-following capability for diverse actions, lack of temporal alignment between actions and audio content, and dependency on additional control signals such as pose skeletons. We pres
Adjuvants play a critical role in modulating immune responses and are central to the development of vaccines and immunotherapies. Yet progress in this field is constrained by data scarcity and incomplete understanding of mechanisms of action, which limit the transition from experience-based design t…
Multi-contrast magnetic resonance imaging (MRI) super-resolution intends to reconstruct high-resolution (HR) images from low-resolution (LR) scans by leveraging structural information present in HR reference images acquired with different contrasts. This technique enhances anatomical detail and soft
Federated Learning (FL) faces a fundamental dilemma: existing defenses against gradient leakage attacks (GLAs) invariably sacrifice model performance for privacy protection through noise injection or gradient clip. We introduce Federated Learning with Momentum-Based Orthogonal Projection (FedMOP), a
Large Vision Language Models (LVLMs) have achieved remarkable success in a wide range of downstream tasks that require multimodal interaction, but their powerful capabilities come with substantial computational and memory overhead, which hinders practical deployment. Among numerous acceleration tech
Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover
In retrieval-augmented generation, language models can generate incorrect responses if they fail to utilize query-relevant content from the retrieved evidence. This shifts the focus of uncertainty quantification (UQ) toward assessing contextual grounding, i.e., whether predictions are supported by q…
Robotic manipulation in complex 3D environments requires unifying spatial reasoning with intuitive visual perception, which is a capability that current Vision-Language-Action paradigms address separately. While 3D VLAs excel in geometric and physical reasoning, they lack intuitive, image-level unde
Timely and accurate forecasts of severe weather events are essential for early warning and for constraining downstream analysis and decision-making. Since severe weather events prediction still depends on subjective, time-consuming expert interpretation, end-to-end "AI weather station" systems are e
Diffusion-based motion generation has advanced rapidly, but current methods still struggle with long-horizon consistency, style control, and multi-condition guidance. A major reason is the fused-conditioning design, where semantic, stylistic, and temporal signals share a single pathway, causing inte
Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP’s text encoder, risking overfitting. In this work, we propose C
Real-world visual signals are inherently variable in resolution, and it is natural to endow multimodal large language models (MLLMs) with such native-resolution perception capabilities. In principle, for general and straightforward multimodal understanding, low-resolution images are sufficient. Whil…
Recent advances in vision-language models (VLMs) have garnered substantial attention in open-vocabulary semantic and part segmentation (OSPS). However, existing methods extract image-text alignment cues from cost volumes through a serial structure of spatial and class aggregations, leading to knowle
Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation, allowing robots to search for arbitrary objects without fine-tunin…
Recent generative unlearning models synthesize high quality samples while protecting private information by unlearning the identity. However, existing generative identity unlearning methods face two challenges in multi-identity unlearning: 1) identity conflicts, which cause conflicts of model parame
Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remarkable success, their non-causal architecture and high computational costs make them unsuitable for streaming. Moreover,
Due to the lack of effective cross-modal modeling, existing open-source audio-video generation methods often exhibit compromised lip synchronization and insufficient semantic consistency. To mitigate these drawbacks, we propose UniAVGen, a unified framework for human-centric joint audio and video ge
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities and generalization in embodied manipulation. However, their decision-making relies on a fast, instinctive process that lacks deliberation. This strategy often leads to suboptimal or catastrophic actions when facing complex…
Aerodynamic coefficient prediction is pivotal in aircraft and vehicles' design, performance evaluation, and motion control. Integrating artificial neural networks into aerodynamic coefficient prediction offers a promising alternative to traditional numerical methods burdened by extensive computation…
The Segment Anything Model (SAM) is a powerful foundation model for image segmentation, showing robust zero-shot generalization through prompt engineering. However, relying on manual prompts is impractical for real-world applications, particularly in scenarios where rapid prompt provision and resour…
Text plays a crucial role in the transmission of human civilization, and teaching machines to generate online handwritten text in various styles presents an interesting and significant challenge. However, most prior work has concentrated on generating individual Chinese fonts, leaving complete text…
Multi-agent path finding (MAPF) is a safety-critical scenario where the goal is to secure collision-free trajectories from initial to desired locations. However, due to system complexity and uncertainty, integrating learning-based controllers with MAPF is challenging and cannot theoretically guarant…
This paper investigates metric learning in a Reproducing Kernel Hilbert Space (RKHS) based on a set of random triplet comparisons in the form of *"Do you think item h is more similar to item i or item j?"* indicating similarity and differences between various items. The goal is to learn a metric in
Recent developments in Large Language Models (LLMs) pre-trained on extensive corpora have shown significant success in various natural language processing (NLP) tasks with minimal fine-tuning. This success offers new promise for robotics, which has long been constrained by the high cost of action-la…
Foundation models trained on internet-scale data benefit from extensive alignment to human preferences before deployment. However, existing methods typically assume a homogeneous preference shared by all individuals, overlooking the diversity inherent in human values. In this work, we propose a gene…
High-precision dense object detection in retail is crucial for automation, inventory management, and sales optimization. Our experiments revealed that detection models perform significantly better with frontal views than with oblique views, motivating the development of RecNet. RecNet utilizes a Rec…
With the advancement of large-scale language modeling techniques, large multimodal models combining visual encoders with large language models have demonstrated exceptional performance in various visual tasks. Most of the current large multimodal models achieve this by mapping visual features obtain…
Modern semi-supervised learning (SSL) methods rely on pseudolabeling and consistency regularization. Pseudolabeling is typically performed by comparing the model's confidence scores and a predefined threshold. While several heuristics have been proposed to improve threshold selection, the underlyin…
Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels, which are crucial for many downstream applications such as autonomous driving
The study of talking face generation mainly explores the intricacies of synchronizing facial movements and crafting visually appealing, temporally-coherent animations. However, due to the limited exploration of global audio perception, current approaches predominantly employ auxiliary visual and sp…
In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit Q-function for inference.Through this theoretical lens, we demonstr…
Differential-driven wheeled robots (DWR) represent the quintessential type of mobile robots and find extensive applications across the robotic field. Most high-performance control approaches for DWR explicitly utilize the linear and angular velocities of the trajectory as control references. However
3D FMCW lidars return relative velocity measurements via the Doppler effect, which provides a new form of information for motion estimation. In our prior work, we proposed an odometry method that avoids the conventional ICP-based approach and uses the Doppler velocity measurements in a correspondenc
Semi-supervised semantic segmentation has attracted considerable attention for its ability to mitigate the reliance on extensive labeled data. However, existing consistency regularization methods only utilize high certain pixels with prediction confidence surpassing a fixed threshold for training, f…
We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round. Existing algorithms characterize the non-stationarity by the total variation budget $B_K$, which is the summation of the change of the consecutive feature vectors of the linear bandit…
Large language models (LLMs) offer impressive performance across diverse fields, but their increasing complexity raises both design costs and the need for specialized expertise. These challenges are intensified for Neural Architecture Search (NAS) methods reliant on weight-sharing techniques. This p…
Unsupervised Reinforcement Learning (RL) provides a promising paradigm for learning useful behaviors via reward-free per-training. Existing methods for unsupervised RL mainly conduct empowerment-driven skill discovery or entropy-based exploration. However, empowerment often leads to static skills, a…
Numerous works are proposed to align large language models (LLMs) with human intents to better fulfill instructions, ensuring they are trustful and helpful.Nevertheless, some human instructions are often malicious or misleading and following them will lead to untruthful and unsafe responses.Previous…
Ideal point based preference learning using pairwise comparisons of type "Do you prefer a or b?" has emerged as a powerful tool for understanding how we make preferences. Existing preference learning approaches assume homogeneity and focus on learning preference on average over the population or req…
Matching molecular analogues is a computational chemistry and bioinformatics research issue which is used to identify molecules that are structurally or functionally similar to a target molecule. Recent studies on matching analogous molecules have predominantly concentrated on enhancing effectivenes…
Auto-labeling is an important family of techniques that produce labeled training sets with minimum manual annotation. A prominent variant, threshold-based auto-labeling (TBAL), works by finding thresholds on a model's confidence scores above which it can accurately automatically label unlabeled data…
The growing interest in Large Language Models (LLMs) for specialized applications has revealed a significant challenge: when tailored to specific domains, LLMs tend to experience catastrophic forgetting, compromising their general capabilities and leading to a suboptimal user experience. Additionall…
Visual inspection by robotics and automation is widely applied in industry and daily life. Although dynamic coverage of mobile sensors has been developed for various tasks, existing methods are not suitable for visual inspection since sensing model is not taken into account. For this reason, this le
Knowledge distillation is a common method of model compression, which uses large models (teacher networks) to guide the training of small models (student networks). However, the student may find a hard time absorbing the knowledge from a sophisticated teacher due to the capacity and confidence gaps…
In this paper, we present a fast, lightweight odometry method that uses the Doppler velocity measurements from a Frequency-Modulated Continuous-Wave (FMCW) lidar without data association. FMCW lidar is a recently emerging technology that enables per-return relative radial velocity measurements via t…
This paper presents two methods for the computation of the null space velocity command in redundant robots. Both these methods resort to the solution of a constrained optimization problem. The first one is a formalization of the traditional Gradient Projection Method (GPM) which guarantees the respe…
Frequency-Modulated Continuous-Wave (FMCW) lidar is a recently emerging technology that additionally enables per-return instantaneous relative radial velocity measurements via the Doppler effect. In this letter, we present the first continuous-time lidar-only odometry algorithm using these Doppler v
Dialogue models are often enriched with extensive external knowledge to provide informative responses through a retrieval-augmented pipeline. Nevertheless, retrieval-augmented approaches rely on finely annotated retrieval training data and knowledge-grounded response generation data, making it costl…
Continual learning for named entity recognition (CL-NER) aims to enable models to continuously learn new entity types while retaining the ability to recognize previously learned ones. However, the current strategies fall short of effectively addressing the catastrophic forgetting of previously learn…
In this paper, we present a novel algorithm for point cloud registration for range sensors capable of measuring per-return instantaneous radial velocity: Doppler ICP. Existing variants of ICP that solely rely on geometry or other features generally fail to estimate the motion of the sensor correctly…
Spiking Neural Network (SNN) is a promising solution for ultra-low-power hardware. Recent SNNs have reached the performance of Deep Neural Networks (DNNs) in dealing with many tasks. However, these methods often suffer from a long simulation time to achieve the accurate spike train information. In a…
In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance. To this end, we propose to exploit sibling mentions for enhancing the mention representations. Specifically…
We present MCPG: a simple and effectiveapproach for controllable unsupervised paraphrase generation, which is also flexible toadapt to specific domains without extra training. MCPG is controllable in different levels: local lexicons, global semantics, and universal styles. The unsupervised paradigm…
Spiking Neural Networks (SNNs) are receiving increasing attention due to their biological plausibility and the potential for ultra-low-power event-driven neuromorphic hardware implementation. Due to the complex temporal dynamics and discontinuity of spikes, training SNNs directly usually suffers fro…
Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET). However, there lacks a comprehensive understanding about how to make better use of the existing information sources and how they affect the performance of ZFET. In this p…
Deep spiking neural network (DSNN) is a promising computational model towards artificial intelligence. It benefits from both the DNNs and SNNs through a hierarchy structure to extract multiple levels of abstraction and the event-driven computational manner to provide ultra-low-power neuromorphic imp…
Human-robot interactions (HRI) can be modeled as differential games with incomplete information, where each agent holds private reward parameters. Due to the open challenge in finding perfect Bayesian equilibria of such games, existing studies often decouple the belief and physical dynamics by itera…
Human-robot collaborative assembly consists of humans and automated robots, who cooperate with each other to accomplish complex assembly tasks, which are difficult for either humans or robots to accomplish alone. There has been some success in statistics-based and optimization-based approaches to re…
With numerous coding tools adopted in the forthcoming Versatile Video Coding (VVC) standard, much less work has been dedicated to study the corresponding Rate-Distortion (R-D) characteristics. This paper proposes a new quadratic R-D model for Versatile Video Coding. In particular, based on the propo…
This letter proposes a procedure for the rapid prototyping and on-demand manufacturing of thin film flexible electro-adhesive devices (EADs) made with a commercial polyimide dielectric layer, inkjet printed interdigitated silver electrodes and blade coated silicone elastomer encapsulation backing. A
Human-multi-robot collaboration is becoming more and more common in intelligent manufacturing. Optimal assembly scheduling of such systems plays a critical role in their production efficiency. Existing approaches mostly consider humans as agents with assumed or known capabilities, which leads to sub…
Langevin diffusion is a powerful method for nonconvex optimization, which enables the escape from local minima by injecting noise into the gradient. In particular, the temperature parameter controlling the noise level gives rise to a tradeoff between ``global exploration'' and ``local exploitation''…
Learning from pairwise measurements naturally arises from many applications, such as rank aggregation, ordinal embedding, and crowdsourcing. However, most existing models and algorithms are susceptible to potential model misspecification. In this paper, we study a semiparametric model where the pair…