相关论文: NExT-Guard: Training-Free Streaming Safeguard with…

Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe…

Speech self-supervised pre-training can effectively improve the performance of downstream tasks. However, previous self-supervised learning (SSL) methods for speech, such as HuBERT and BEST-RQ, focus on utilizing non-causal encoders with…

With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms. Current video guardrails, however, are either overly…

Hosted large language models are increasingly accessed through remote APIs, but the API boundary still offers little direct evidence that a returned output actually corresponds to the client-visible request. Recent audits of shadow APIs…

Video Large Language Models (Video-LLMs) excel at understanding videos in-context, provided they have full access to the video when answering queries. However, these models face challenges in streaming scenarios where hour-long videos must…

With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are either based on text blacklists, which can be easily…

The rapid development of large language models (LLMs) has yielded impressive success in various downstream tasks. However, the vast potential and remarkable capabilities of LLMs also raise new security and privacy concerns if they are…

Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like GPT have revolutionized NLP, most visual generative…

In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on fully observed text, whereas streaming response moderation requires safety decisions to be made over…

While Large Language Models (LLMs) have catalyzed progress in embodied intelligence, a fundamental gap between their inherent probabilistic uncertainty and the strict determinism and verifiable safety required in the physical world. To…

Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these gains have often come with increased model complexity and high computational demands,…

Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of…

Recent advancements in Deep Neural Network (DNN) models have significantly improved performance across computer vision tasks. However, achieving highly generalizable and high-performing vision models requires expansive datasets, resulting…

Protecting speaker identity is crucial for online voice applications, yet streaming speaker anonymization (SA) remains underexplored. Recent research has demonstrated that neural audio codec (NAC) provides superior speaker feature…

This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T trained from scratch usually performs worse than…

Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. Existing approaches for mitigating privacy leakage in action recognition require privacy labels…

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) tasks but also pose ethical and societal risks due to their propensity to generate harmful content. Existing methods have limitations, including the…

Text-to-image models have recently made significant advances in generating realistic and semantically coherent images, driven by advanced diffusion models and large-scale web-crawled datasets. However, these datasets often contain…

We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks…

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…