Related papers: $\texttt{AVROBUSTBENCH}$: Benchmarking the Robustn…

Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains richer and more reliable semantic information, which remains more robust under…

We introduce the MNIST-C dataset, a comprehensive suite of 15 corruptions applied to the MNIST test set, for benchmarking out-of-distribution robustness in computer vision. Through several experiments and visualizations we demonstrate that…

With the rapid integration of advanced reasoning capabilities into spoken dialogue models, the field urgently demands benchmarks that transcend simple interactions to address real-world complexity. However, current evaluations predominantly…

Recent unified multi-modal encoders align a wide range of modalities into a shared representation space, enabling diverse cross-modal tasks. Despite their impressive capabilities, the robustness of these models under adversarial…

Advanced Audio-Visual Speech Recognition (AVSR) systems have been observed to be sensitive to missing video frames, performing even worse than single-modality models. While applying the dropout technique to the video modality enhances…

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments…

Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires…

Audio-visual speaker extraction has attracted increasing attention, as it removes the need for pre-registered speech and leverages the visual modality as a complement to audio. Although existing methods have achieved impressive performance,…

Bangla, one of the most widely spoken languages, remains underrepresented in state-of-the-art automatic speech recognition (ASR) research, particularly under noisy and speaker-diverse conditions. This paper presents BanglaRobustNet, a…

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity…

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite…

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal…

Safety is a long-standing and the final pursuit in the development of autonomous driving systems, with a significant portion of safety challenge arising from perception. How to effectively evaluate the safety as well as the reliability of…

The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. This paper offers the first comprehensive study on robust PVOS…

In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length…

Long-form multimodal video understanding requires integrating vision, speech, and ambient audio with coherent long-range reasoning. Existing benchmarks emphasize either temporal length or multimodal richness, but rarely both and while some…

Despite their strong performance in embodied tasks, recent Vision-Language-Action (VLA) models remain highly fragile under multimodal perturbations, where visual corruption and linguistic noise jointly induce distribution shifts that…

Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual…