26 accepted papers
Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range temporal modeling via rigid, predefined sparse patterns. This
Although Vision Language Models (VLMs) exhibit strong perceptual abilities and impressive visual reasoning, they struggle with attention to detail and precise action planning in complex, dynamic environments, leading to subpar performance. Real-world tasks typically require complex interactions, adv
The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised fine-tuning (SFT), a common technique for model specialization. Existing recovery methods rely on data-intensive global p
Large vision-language models (LVLMs) excel at visual understanding but face efficiency challenges due to quadratic complexity when processing long multimodal contexts. While token compression can reduce computational costs, existing approaches are designed for single-view LVLMs and fail to account f
With their high dynamic range and temporal resolution, event cameras are well-suited for object detection, especially under motion blur and extreme illumination. Recent state-of-the-art works for event-based object detection primarily focus on the high-level design of backbones. However, developing
Test-Time Training (TTT) has recently emerged as a promising direction for efficient sequence modeling. TTT reformulates attention operation as an online learning problem, constructing a compact inner model from key-value pairs at test time. This reformulation opens a rich and flexible design space
The advantages of high temporal resolution and high dynamic range provided by event cameras are particularly suitable for moving object detection, especially in scenarios with motion blur and extreme lighting conditions. Current popular methods predominantly focus on designing powerful network archi…
Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning und…
We present Discoverse, the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridgin
Fine-tuning large language models (LLMs) on task-specific data is essential for their effective deployment. As dataset sizes grow, efficiently selecting optimal subsets for training becomes crucial to balancing performance and computational costs. Traditional data selection methods often require fin…
This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with sequential updates, improving computation efficiency markedly w
Parody is an emerging phenomenon on social media, where individuals imitate a role or position opposite to their own, often for humor, provocation, or controversy. Detecting and analyzing parody can be challenging and is often reliant on context, yet it plays a crucial role in understanding cultural…
Spiking neural networks (SNNs) are widely applied in various fields due to their energy-efficient and fast-inference capabilities. Applying SNNs to reinforcement learning (RL) can significantly reduce the computational resource requirements for agents and improve the algorithm's performance under re…
The Cine MRI of the small intestine is a dynamic magnetic resonance imaging technique used to observe and evaluate small intestine motility. It captures sequential images of the organ in motion over time through rapid imaging. The Transformer architecture is highly effective at capturing long-range…
The evaluation of factual accuracy in large vision language models (LVLMs) has lagged behind their rapid development, making it challenging to fully reflect these models’ knowledge capacity and reliability. In this paper, we introduce the first factuality-based visual question-answering benchmark in…
In many scenarios of practical interest, labeled data from a target distribution are scarce while labeled data from a related source distribution are abundant. One particular setting of interest arises when the target label space is a subset of the source label space, leading to the framework of par…
Fine-tuned Large Language Models (LLMs) often demonstrate poor calibration, with their confidence scores misaligned with actual performance. While calibration has been extensively studied in models trained from scratch, the impact of LLMs’ prior knowledge on calibration during fine-tuning remains un…
In numerous real-world applications, it is quite common that sample information is partially available for some views due to machine breakdown or sensor failure, causing the problem of incomplete multi-view clustering (IMVC). While several IMVC approaches using view-shared anchors have successfully…
"Event cameras, with their high dynamic range and temporal resolution, are ideally suited for object detection in scenarios with motion blur and challenging lighting conditions. However, while most existing approaches prioritize optimizing spatiotemporal representations with advanced detection backb…
Integrating Large Language Models (LLMs) into robotics significantly enhances autonomous task planning. However, ensuring that multi-step task plans (action sequence) generated by LLMs comply with pre-defined safety constraints during planning and execution remains a challenge, limiting their adapta…
Given a pair of point clouds, the goal of assembly is to recover a rigid transformation that aligns one point cloud to the other. This task is challenging because the point clouds may be non-overlapped, and they may have arbitrary initial positions. To address these difficulties, we propose a method…
Spiking neural networks (SNNs) with biologically inspired spatio-temporal dynamics demonstrate superior energy efficiency on neuromorphic architectures. Error backpropagation in SNNs is prohibited by the all-or-none nature of spikes. The existing solution circumvents this problem by a relaxation on…
Spiking neural networks (SNNs) have increasingly drawn massive research attention due to biological interpretability and efficient computation. Recent achievements are devoted to utilizing the surrogate gradient (SG) method to avoid the dilemma of non-differentiability of spiking activity to directl…
While exploiting body segmentations for supervision, existing 3D human pose and shape estimation methods are plagued by mismatches between clothed body segmentations and skinned SMPL model reprojections. Moreover, noisy pixels introduced by inaccurate segmentation annotations also prevent the model…
"Point cloud registration aims at estimating the geometric transformation between two point cloud scans, in which accurate correspondence estimation is the key to its success. In addition to previous methods that seek correspondences by hand-crafted or learnt geometric features, recent point cloud r…
Given two point sets, the problem of registration is to recover a transformation that matches one set to the other. This task is challenging due to the presence of large number of outliers, the unknown non-rigid deformations and the large sizes of point sets. To obtain strong robustness against outl…