25 accepted papers
Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce AVI-Bench, a …
Real-world multivariate time series are inherently in flux: different variables evolve asynchronously and interact in complex, time-varying ways, yet accurate forecasting requires these dispersed signals to converge into a single unified prediction. This structural mismatch between dynamic, heteroge…
We introduce FrontierCS, a benchmark of 240 open-ended problems across diverse areas of computer science, designed and reviewed by experts, including CS PhDs and top-tier competitive programming participants and problem setters. Unlike existing benchmarks that focus on tasks with known optimal solut…
Soft growing robots, as highly mobile pneumatic membrane robots, are limited in control performance due to their soft structure and nonlinear mechanical properties, especially under dynamic conditions. Therefore, developing reliable control strategies for the robot is essential. This study proposes …
Spiking Neural Networks (SNNs) offer promising energy efficiency and temporal sparsity for edge intelligence, but their training remains difficult due to gradient mismatch, membrane potential drift, and discretization errors. In this paper, we propose a membrane potential-guided surrogate optimizati
Diffusion generative models have demonstrated remarkable empirical success in the recent years and are now considered the state-of-the-art generative models in modern AI. These models consist of a forward process, which gradually diffuses the data distribution to a noise distribution spanning the wh…
Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consisten
Vertical federated learning (VFL) trains models by splitting computation across clients and a server that only exchange intermediate embeddings. Recent work shows that a server even if honest-but-curious can steal a client's bottom model by querying the system and regressing on the returned embeddin
The Dialogue Topic Segmentation task aims to divide a dialogue into different topic paragraphs in order to better understand the structure and content of the dialogue. Due to the short sentences, serious references and non-standard language in the dialogue, it is difficult to determine the boundarie…
Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs). However, the misuse of AIGTs could have profound implications for public opinion, such as spreading misinformation and manipulating narratives. Despite its importance, it remains unclear how prevalent AIGTs are…
Multimodal Large Language Models (MLLMs) have become powerful and widely adopted in some practical applications.However, recent research has revealed their vulnerability to multimodal jailbreak attacks, whereby the model can be induced to generate harmful content, leading to safety risks. Although m
Soft growing robots, as highly mobile pneumatic membrane robots, are limited in control performance due to their soft structure and nonlinear mechanical properties, especially under dynamic conditions. Therefore, developing reliable control strategies for the robot is essential. This study proposes
We study the problem of learning to stabilize unknown noisy Linear Time-Invariant (LTI) systems on a single trajectory. The state-of-the-art guarantees that the system is stabilized before the system state reaches $2^{O(k \log n)}$ in $L^2$-norm, where $n$ is the state dimension, and $k$ is the dime
In recent years, Transformers have achieved significant success in image fusion. These methods utilize self-attention mechanism across different spatial or channel dimensions and have demonstrated impressive performance. However, existing methods only optimize along a single dimension and struggle t…
We study the problem of stabilizing an unknown partially observable linear time-invariant (LTI) system. For fully observable systems, leveraging an unstable/stable subspace decomposition approach, state-of-art sample complexity is independent from system dimension $n$ and only scales with respect to…
Superpixel segmentation with deep learning has been proposed in recent years and is widely employed to reduce the input image primitives for subsequent computer vision tasks. In this paper, we propose a Triple Multi-Scale Attention based Network (TMANet) for superpixel segmentation. First, aiming to…
Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative workflows. While optimizing downstream reward models has emerged as a promising alignment strategy, concerns arise regarding the risk of excessive optimization with learned rewa…
Learning-based simulators show great potential for simulating particle dynamics when 3D groundtruth is available, but per-particle correspondences are not always accessible. The development of neural rendering presents a new solution to this field to learn 3D dynamics from 2D images by inverse rende…
With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmenta…
Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is difficult because event data is sparse and does not carry absolute c…
This paper introduces a novel paradigm for the generalizable neural radiance field (NeRF). Previous generic NeRFs combine multiview stereo techniques with image-based neural rendering, yielding impressive results, while suffering from three issues. First, occlusions often result in inconsistent feat…
3D neural implicit representations play a significant component in many robotic applications. However, reconstructing neural radiance fields (NeRF) from realistic event data remains a challenge due to the sparsities and the lack of information when only event streams are available. In this paper, we…
Learning with noisy labels (LNL) is one of the most important and challenging problems in weakly-supervised learning. Recent advances adopt the sample selection strategy to mitigate the interference of noisy labels and use small-loss criteria to select clean samples. However, the one-dimensional los…
A high-resolution network exhibits remarkable capability in extracting multi-scale features for human pose estimation, but fails to capture long-range interactions between joints and has high computational complexity. To address these problems, we present a Dynamic lightweight High-Resolution Networ…
We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global align…