Related papers: GuardReasoner-Omni: A Reasoning-based Multi-modal …

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA,…

Radiology report generation is critical for efficiency but current models lack the structured reasoning of experts, hindering clinical trust and explainability by failing to link visual findings to precise anatomical locations. This paper…

Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving into "world simulators." Yet the community still lacks a benchmark that directly tests…

We present Omni-Embed-Nemotron, a unified multimodal retrieval embedding model developed to handle the increasing complexity of real-world information needs. While Retrieval-Augmented Generation (RAG) has significantly advanced language…

While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video understanding. We introduce ReasonAct, a method that enhances video…

While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…

In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships…

Recent studies demonstrate that multimodal large language models (MLLMs) can proficiently evaluate visual quality through interpretable assessments. However, existing approaches typically treat quality scoring and reasoning descriptions as…

While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention,…

Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high…

Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines supervise only the final response. To address this, we present…

Leveraging multimodal large models for image segmentation has become a prominent research direction. However, existing approaches typically rely heavily on manually annotated datasets that include explicit reasoning processes, which are…

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the…

We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs,…

Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to generalize, and…

Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations of…