98 accepted papers
Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight
Deploying GRPO on Flow Matching models has proven effective for text-to-image generation. However, existing paradigms typically propagate an outcome-based reward to all preceding denoising steps without distinguishing the local effect of each step. Moreover, current group-wise ranking mainly compare…
While previous multimodal slow-thinking methods have demonstrated remarkable success in single-image understanding scenarios, their effectiveness becomes fundamentally constrained when extended to more complex multi-image comprehension tasks. This limitation stems from their predominant reliance on
Effective tool use and reasoning are essential capabilities for large reasoning models (LRMs) to address complex real-world problems. Through empirical analysis, we identify a prevalent "Lazy Reasoning" phenomenon, where LRMs frequently engage in repetitive and meaningless reflective reasoning. This…
Diffusion models have demonstrated remarkable success in image and video generation, yet their practical deployment remains hindered by the substantial computational overhead of multi-step iterative sampling. Among acceleration strategies, caching-based methods offer a training-free and effective so
Autonomous driving requires accurate scene understanding, including road geometry, traffic agents, and their semantic relationships. In online HD map generation scenarios, raster-based representations are well-suited to vision models but lack geometric precision, while graph-based representations re
Recent efforts have successfully scaled plain Vision Transformers (ViTs) to unprecedented sizes, ranging from 6B to 22B parameters. In contrast, their hierarchical counterparts have remained largely constrained to less than 1B parameters. To bridge this gap, we propose EHV, an efficient hierarchical
Upcycling, a strategy that initializes Mixture-of-Experts (MoE) by replicating pre-trained feed-forward or MoE networks to expand model capacity, has become a popular method in continual learning due to its effectiveness in mitigating catastrophic forgetting. However, existing paradigms rely on indi…
Recent unified models have demonstrated that the reasoning capacity of Multimodal Large Language Models (MLLMs) can be leveraged to facilitate diffusion-based image generation with impressive flexibility and performance. However, approaches that rely heavily on MLLMs for high-level semantic encoding
Multimodal large language models (MLLMs) have substantially advanced video misinformation detection through unified multimodal reasoning, but they often rely on fixed-depth inference and place excessive trust in internally generated assumptions, particularly in scenarios where critical evidence is s…
Dynamic 3D reconstruction from monocular videos remains difficult due to the ambiguity inferring 3D motion from limited views and computational demands of modeling temporally varying scenes. While recent sparse control methods alleviate computation by reducing millions of Gaussians to thousands of…
Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via prompt design and generate discrete semantic IDs through item
Large language models (LLMs) are increasingly used in scientific discovery, system modeling, and decision-making, prompting interest in their ability to reason over complex structured data. Existing benchmarks primarily focus on static or local graph reasoning, overlooking the high-order structures …
Learning from Demonstrations (LfD) is an attractive paradigm in robot learning, enabling robots to acquire skills by observing human demonstrations without explicit programming. However, existing LfD approaches typically assume that users provide ideal demonstrations, which rarely holds in practice,
Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhibit an imbalanced exploration–exploitation trade-off, resulting in unstable optimization and sub-optimal performance. We …
As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we
Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Spla
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elicit biased or malicious outputs. In this paper, we demonstrate an underexplored vulnerability via semantic slot filling, w
Diffusion-based trajectory planners can synthesize rich, multimodal robot motions from demonstrations, but their iterative denoising makes online planning and control prohibitively slow. Existing accelerations either modify the sampler or compress the network–sacrificing plan quality or requiring re…
The core of efficient on-demand ride-pooling lies in solving the Ride-Pool Matching Problem (RMP), which involves assigning multiple customer requests to single vehicles under various service constraints (e.g., pickup windows, detour allowances, and vehicle occupancy). A significant missed opportuni
While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge this gap at both the evaluation and data levels, we introduce GUI-RobustEval and propose Robustness-driven Trajectory Synthesis. GUI-RobustEval containi…
As an important research task of human cultural heritage, the restoration of artworks and calligraphy is of great significance. Seldom existing works have taken the multi-source (i.e., fragments are not ensured to be from the same piece of artworks) fragment-oriented restoration task into account. W
Vision-Language Models (VLMs) offer a promising approach to end-to-end autonomous driving due to their human-like reasoning capabilities. However, troublesome gaps remains between current VLMs and real-world autonomous driving applications. One major limitation is that existing datasets with loosely…
Reinforcement learning (RL) has shown promise for enhancing code generation capabilities in large language models (LLMs), yet its effectiveness critically depends on high-quality test suites for reliable reward signals. Current approaches suffer from inadequate test case quantity and quality, leadin
Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a "one-size-fits-all" paradigm and struggle to model user-specific concepts (e.g., generate a photo of \texttt \<maeve> ) in a consis
Text-conditioned human motion in-betweening leverages keyframes for spatio-temporal control, with text providing high-level semantic guidance for the transitions. However, existing methods are unable to establish a coherent alignment between textual semantics and the spatio-temporal constraints prov
Recent advances in Multi-modal Large Language Models (MLLMs), such as LLaVA-series models, are driven by massive machine-generated instruction-following data tuning. Such automatic instruction collection pipelines, however, inadvertently introduce significant variability in data quality. This paper…
As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement. Inspired by the ability of vision foundation models (VFMs) to ext…
MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate reasoning steps, and ORM, which supervises the final results. Recently, DeepSeek-R1 has challenged the traditional view tha…
Large language models have been successfully applied to programming assistance tasks, such as code completion, code insertion, and instructional code editing. However, these applications remain insufficiently automated and struggle to effectively integrate various types of information during the pro…
Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained scenarios. Post-training quantization (PTQ) compresses and acc…
The realization of autonomous driving(AV) is closely linked to the development of intelligent decision-making modules that can operate safely in dynamic, uncertain environments. To address issues such as delayed response and poor coupling in highway scenarios, this paper proposes a hierarchical Coup
The rapidly developing Large Vision Language Models (LVLMs) still face the hallucination phenomena where the generated responses do not align with the given contexts, significantly restricting the usages of LVLMs. Most previous work detects and mitigates hallucination at the coarse-grained level or…
Video question answering plays a vital role in computer vision, and recent advances in large language models have further propelled the development of this field. However, existing video question answering techniques often face limitations in grasping fine-grained video content in spatial dimensions…
Reconstructing dynamic 3D scenes from monocular videos remains a fundamental challenge in 3D vision. While 3D Gaussian Splatting (3DGS) achieves real-time rendering in static settings, extending it to dynamic scenes is challenging due to the difficulty of learning structured and temporally consisten…
We present **HealthGPT**, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm. Our bootstrapping philosophy is to progressively adapt heterogeneous comprehension and generation kno…
We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models ($s$-MLLM) distilling knowledge from large-scale MLLM ($l$-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structu…
Human-aware navigation (HAN) aims to build autonomous agents that robustly and naturally navigate in human-centered environments. Due to the complex and dynamic nature of this task, existing approaches typically rely on sophisticated pipelines that separately process perception and decision-making t
Auto-regressive models have made significant progress in the realm of text-to-image synthesis, yet devising an appropriate model architecture and training strategy to achieve a satisfactory level remains an important avenue of exploration. In this work, we introduce MARS, a novel framework for T2I g…
Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in multi-subject scenarios. However, these advances are hindered b…
Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training stage with a simple image reconstruction task, and they typicall…
Predicting roll call votes through modeling political actors has emerged as a focus in quantitative political science and computer science. Widely used embedding-based methods generate vectors for legislators from diverse data sets to predict legislative behaviors. However, these methods often conte…
Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training with full resolution latent. Despite reducing computational de…
Personalized text-to-image generation methods can generate customized images based on the reference images, which have garnered wide research interest. Recent methods propose a finetuning-free approach with a decoupled cross-attention mechanism to generate personalized images requiring no test-time…
We propose ReKV, a novel training-free approach that enables efficient streaming video question-answering (StreamingVQA), by seamlessly integrating with existing Video Large Language Models (Video-LLMs). Traditional VideoQA systems struggle with long videos, as they must process entire videos before…
Most existing studies on evaluating text-to-image (T2I) models primarily focus on evaluating text-image alignment, image quality, and object composition capabilities, with comparatively fewer studies addressing the evaluation of the factuality of the synthesized images, particularly when the images…
Dynamic graphs evolve continuously, presenting challenges for traditional graph learning due to their changing structures and temporal dependencies. Recent advancements have shown potential in addressing these challenges by developing suitable meta-learning-based dynamic graph neural network models.…
While Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) effectively address resource constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To address this issue, one straightforward solution is to introduce ta…
As a globally celebrated sport, soccer has attracted widespread interest from fans over the world. This paper aims to develop a comprehensive multi-modal framework for soccer video understanding.Specifically, we make the following contributions in this paper:(i) we introduce **SoccerReplay-1988**, t…
Instruction-tuned Code Large Language Models (Code LLMs) have excelled in diverse code-related tasks, such as program synthesis, automatic program repair, and code explanation. To collect training datasets for instruction-tuning, a popular method involves having models autonomously generate instruct…
Genomic selection (GS), as a critical crop breeding strategy, plays a key role in enhancing food production and addressing the global hunger crisis. The predominant approaches in GS currently revolve around employing statistical methods for prediction. However, statistical methods often come with tw…
Vision-assisted container loading of Rubber Tyred Gantry (RTG) cranes are facing two primary challenges. Firstly, the uncertainty inherent in Covolutional Neural Network (CNN) based detection hinders its direct application in the safety-critical operation of such heavy-duty machinery. Secondly, sens…
Image retrieval with composed query (IR-CQ) is a challenging task since it aims to retrieve the target image according to a hybrid-modality query which consists of a reference image and a text modifier. Previous approaches mainly focus on designing various multi-modal fusion modules to fuse the hybr…
Halftoning is a time-honored printing technique that simulates continuous tones using ink dots (halftone dots). The resurgence of deep learning has catalyzed the emergence of innovative technologies in the printing industry fostering the advancement of data-driven halftoning methods. Nevertheless cu…
Integrated sensing and communication (ISAC) within the unlicensed millimeter-wave (mmWave) frequency bands has been emerged as a pivotal technology in the next generation wireless communication era. However, the interference management issue between sensing and communication becomes much severe due…
Concept activation vector (CAV) has attracted broad research interest in explainable AI, by elegantly attributing model predictions to specific concepts. However, the training of CAV often necessitates a large number of high-quality images, which are expensive to curate and thus limited to a predefi…
"Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards eXplanable Artificial Intelligence (XAI). However, the absence of consistent configurations and systematic investigations in prior literature impedes comprehensive evaluat…
The gap between the trepidation of program reliability and the expense of repairs underscore the indispensability for Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering program reliability while simultaneously diminishing the fin…
Customizing diffusion models to generate identity-preserving images from user-provided reference images is an intriguing new problem. The prevalent approaches typically require training on extensive domain-specific images to achieve identity preservation, which lacks flexibility across different use…
Constrained Reinforcement Learning employs trajectory-based cost constraints (such as expected cost, Value at Risk, or Conditional VaR cost) to compute safe policies. The challenge lies in handling these constraints effectively while optimizing expected reward. Existing methods convert such trajecto…
In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further levera…
To complete tasks in dynamic environments, robots need to timely update their plans to react to environment changes. Traditional stripe-like or learning-based planners struggle to achieve this due to their high reliance on meticulously predefined planning rules or labeled data. Fortunately, recent w
In recent years the thriving development of research related to egocentric videos has provided a unique perspective for the study of conversational interactions where both visual and audio signals play a crucial role. While most prior work focus on learning about behaviors that directly involve the…
Video moment localization stands as a crucial task within the realm of computer vision, entailing the identification of temporal moments in untrimmed videos that bear semantic relevance to the supplied natural language queries. This work delves into a relatively unexplored facet of the task: the tra…
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for effective large-scale pre-training due to the modeling of its…
Can conversational videos captured from multiple egocentric viewpoints reveal the map of a scene in a cost-efficient way? We seek to answer this question by proposing a new problem: efficiently building the map of a previously unseen 3D environment by exploiting shared information in the egocentric…
Product Retrieval (PR) and Grounding (PG), aiming to seek image and object-level products respectively according to a textual query, have attracted great interest recently for better shopping experience. Owing to the lack of relevant datasets, we collect two large-scale benchmark datasets from Taoba…
Cell instance segmentation in cytology images has significant importance for biology analysis and cancer screening, while remains challenging due to 1) the extensive overlapping translucent cell clusters that cause the ambiguous boundaries, and 2) the confusion of mimics and debris as nuclei. In thi…
In a noisy conversation environment such as a dinner party, people often exhibit selective auditory attention, or the ability to focus on a particular speaker while tuning out others. Recognizing who somebody is listening to in a conversation is essential for developing technologies that can underst…
User modeling techniques profile users' latent characteristics (e.g., preference) from their observed behaviors, and play a crucial role in decision-making. Unfortunately, traditional user models may unconsciously capture biases related to sensitive attributes (e.g., gender) from behavior data, even…
The popularity of on-demand ride pooling is owing to the benefits offered to customers (lower prices), taxi drivers (higher revenue), environment (lower carbon footprint due to fewer vehicles) and aggregation companies like Uber (higher revenue). To achieve these benefits, two key interlinked challe…
Soft robotic arms have shown great potential toward applications to human daily lives, which is mainly due to their infinite passive degrees of freedom and intrinsic safety. There are tasks in lives that require the motion of the robot to meet some certain pose constraints that have not been impleme
Video-language models suffer from forgetting old/learned knowledge when trained with streaming data. In this work, we thus propose a continual video-language modeling (CVLM) setting, where models are supposed to be sequentially trained on five widely-used video-text datasets with different data dist…
Inverse halftoning is a technique used to recover realistic images from ancient prints (\textit{e.g.}, photographs, newspapers, books). The rise of deep learning has led to the gradual incorporation of neural network designs into inverse halftoning methods. Most of existing inverse halftoning approa…
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countri…
Augmented reality devices have the potential to enhance human perception and enable other assistive functionalities in complex conversational environments. Effectively capturing the audio-visual context necessary for understanding these social interactions first requires detecting and localizing the…
Few-shot learning (FSL) aims to recognize a novel class with very few instances, which is a challenging task since it suffers from a data scarcity issue. One way to effectively alleviate this issue is introducing explicit knowledge summarized from human past experiences to achieve knowledge transfer…
To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the provided upstream signals and the downstream question-passage relev…
Video summarization has recently engaged increasing attention in computer vision communities. However, the scarcity of annotated data has been a key obstacle in this task. To address it, this work explores a new solution for video summarization by transferring samples from a correlated task (i.e., v…
Supersized pre-trained language models have pushed the accuracy of various natural language processing (NLP) tasks to a new state-of-the-art (SOTA). Rather than pursuing the reachless SOTA accuracy, more and more researchers start paying attention to model efficiency and usability. Different from ac…
Deploying large-scale pre-trained models in the prompt-tuning paradigm has demonstrated promising performance in few-shot learning. Particularly, vision-language pre-training models (VL-PTMs) have been intensively explored in various few-shot downstream tasks. However, most existing works only apply…
Estimating camera wearer's body pose from an egocentric view (egopose) is a vital task in augmented and virtual reality. Existing approaches either use a narrow field of view front facing camera that barely captures the wearer, or an extended head-mounted top-down camera for maximal wearer visibilit…
Head-Related Transfer Function (HRTF) individualization is critical for immersive and realistic spatial audio rendering in augmented/virtual reality. Neither measurements nor simulations using 3D scans of head/ear are scalable for practical applications. More efficient machine learning approaches ar…
Recognizing every person's action in a crowded and cluttered environment is a challenging task in computer vision. We propose to tackle this challenging problem using a holistic 4D "scan" of a cluttered scene to include every detail about the people and environment. This leads to a new problem, i.e.…
In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing. We solve this problem by the penalty method and propose the iteratively reweighted alternating minimization algorithm. To speed up the algorithm, we also apply the c…
Soft compliant materials and novel actuation mechanisms ensure flexible motions and high adaptability for soft robots, but also increase the difficulty and complexity of constructing control systems. In this work, we provide an efficient control algorithm for a multi-segment extensible soft arm in 2…
Today's person detection methods work best when people are in common upright poses and appear reasonably well spaced out in the image. However, in many real images, that's not what people do. People often appear quite close to each other, e.g., with limbs linked or heads touching, and their poses ar…
Free-flying robots have the potential to autonomously fulfill a wide range of tasks involving manipulation of objects in space. In this paper we study the design of a wrist mechanism for free-flying robots that are equipped with an adhesive gripper for attaching to objects and surfaces. The wrist an…
We present work on incipient slip sensing and recovery for controllable gecko-inspired adhesives. The approach is based on the relationship between changes in real contact area and maximum shear force. Using signals from an on-board tactile sensor, we detect the onset of adhesive failure and execute
Most control methods of soft manipulators are developed based on physical models derived from mathematical analysis or learning methods. However, due to internal nonlinearity and external uncertain disturbances, it is difficult to build an accurate model, further, these methods lack robustness and p…
Soft manipulators have been a rising focus of soft robotics research. Taking advantage of soft materials and flexible, continuous movements, they have promising applicable prospect. However, their highly internal nonlinearity and unpredictable deformation caused by environmental effects make it diff…
Understanding the camera wearer's activity is central to egocentric vision, yet one key facet of that activity is inherently invisible to the camera--the wearer's body pose. Prior work focuses on estimating the pose of hands and arms when they come into view, but this 1) gives an incomplete view of…
We present a new palm design that features a dense array of micro-spines for the JPL Robosimian human-scale climbing robot. A linearly-constrained spine mechanism is introduced and analyzed using adhesion and stiffness models. This mechanism achieves a spine density of 19/cm2 and a mean adhesion of…
Nearly all robotic grippers have one trait in common: they grasp objects with normal forces, either directly, or indirectly through friction. This method of grasping is effective for objects small enough for a given gripper to partially encompass. However, to grasp larger objects, significant grip f…
We study the new problem of matching regions between a pair of RGBD images given a large set of overlapping region proposals. These region proposals do not have a tree hierarchy and are treated as bags of regions. Matching RGBD images using bags of region candidates with unstructured relations is a…
Perching on a vertical surface carries the risk of severe damage to the vehicle if the maneuver fails, especially if failure goes undetected. We present a detection method using an onboard 3-axis accelerometer to discriminate between perching success and failure. An analytical model was developed to…
As the number of rocket bodies and other debris in Earth's orbit increases, the need to capture and remove this space junk becomes essential to protect new satellites. A low cost solution may include gecko-inspired directional adhesives, which require almost no compressive preload to generate adhesi…
Adhesion quality sensing is critical to the performance of any robot that utilizes gecko-inspired dry adhesives for climbing, perching, or grasping. We present a 3-axis tactile sensor designed for this application that demonstrates performance on par with a large commercial load cell while being com…