相关论文: Guard Vector: Beyond English LLM Guardrails with T…

Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently over-refuse benign queries and degrade user experience. Previous work on jailbreak and prompt…

The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, makes the video captioning task even more challenging. In this paper, we propose an unified…

As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments has become a critical challenge. However, existing multilingual benchmarks largely rely…

Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints. Giving constraints in natural language form has great potential for practical scenarios due to its flexible transfer capability…

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…

Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their robustness against sophisticated adversarial attacks remains poorly characterized. This study…

While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we…

Temporal sentence grounding (TSG) is a highly challenging task aiming to localize the temporal segment within an untrimmed video corresponding to a given natural language description. Benefiting from the design of learnable queries, the…

Safety alignment is critical for LLM-powered systems. While recent LLM-powered guardrail approaches such as LlamaGuard achieve high detection accuracy of unsafe inputs written in English (e.g., ``How to create a bomb?''), they struggle with…

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the…

Ensuring content safety in large language models (LLMs) is essential for their deployment in real-world applications. However, existing safety guardrails are predominantly tailored for high-resource languages, leaving a significant portion…

Large Language Models (LLMs) have shown remarkable effectiveness in various general-domain natural language processing (NLP) tasks. However, their performance in transportation safety domain tasks has been suboptimal, primarily attributed…

We introduce a recurrent neural network language model (RNN-LM) with long short-term memory (LSTM) units that utilizes both character-level and word-level inputs. Our model has a gate that adaptively finds the optimal mixture of the…

Recent advancements in large language models (LLMs) have expanded their role in robotic task planning. However, while LLMs have been explored for generating feasible task sequences, their ability to ensure safe task execution remains…

In this work, we study how vision-language models (VLMs) can be utilized to enhance the safety for the autonomous driving system, including perception, situational understanding, and path planning. However, existing research has largely…

Models for streaming speech translation (ST) can achieve high accuracy and low latency if they're developed with vast amounts of paired audio in the source language and written text in the target language. Yet, these text labels for the…

Attribute-based Controlled Text Generation (CTG) refers to generating sentences that satisfy desirable attributes (e.g., emotions and topics). Existing works often utilize fine-tuning or resort to extra attribute classifiers, yet suffer…