Related papers: NExT-Guard: Training-Free Streaming Safeguard with…

Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications. To mitigate these risks, we present Libra-Guard, a cutting-edge safeguard system designed…

This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this end, we establish a novel open framework, describing a…

As large language models (LLMs) become more capable and widely used, ensuring the safety of their outputs is increasingly critical. Existing guardrail models, though useful in static evaluation settings, face two major limitations in…

Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most video-language models (VideoLLMs) are trained for offline…

Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…

Aligning large language models (LLMs) with human values typically relies on post-training or inference-time steering that directly manipulates the backbone's parameters or representation space. However, a critical gap exists: the model's…

The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing method for adapting pre-trained LLMs to graph learning…

The increasing use of Large Language Models (LLMs) in agentic applications highlights the need for robust safety guard models. While content safety in English is well-studied, non-English languages lack similar advancements due to the high…

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…

Text-speech joint spoken language modeling (SLM) aims at natural and intelligent speech-based interactions, but developing such a system may suffer from modality mismatch: speech unit sequences are much longer than text tokens. Prior work…

Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces…

Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful information from unlabeled…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn,…

The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and…

End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record system-level activities as audit logs and provide deep…

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate under an implicit assumption: Once a target module is selected, every token passing through it contributes equally to the downstream task and requires a parameter…

Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While…

Toxicity detection mitigates the dissemination of toxic content (e.g., hateful comments, posts, and messages within online social actions) to safeguard a healthy online social environment. However, malicious users persistently develop…