Vision-language models (VLMs) are increasingly deployed in consumer, medical, financial, and enterprise applications. This broad deployment expands the safety surface: risks can arise from multimodal question answering, assistant responses, and cross-modal composition, while moderation policies may vary across products, regions, and deployment stages.
SafeAtlas-VL introduces a large multimodal safety dataset with 1.5 million instances, rating image, request, and response risks on a five‑level ordinal scale across 15 harm categories and 55 subcategories. The accompanying SafeAtlas‑Bench provides 5,000 held‑out cases for evaluating ordinal predictions and continuous risk scores. Models trained on this data, including an 8B Guard model, achieve state‑of‑the‑art performance, outperforming prior benchmarks by about 4% in F1 score.
The paper introduces a new benchmark for evaluating Multi‑Modal Large Language Models (MLLMs) on visual negation understanding, focusing on safety-critical scenarios. It defines the Scene Negation Understanding under Safety Cognition (SNUS) task and presents a high‑fidelity negative caption dataset that maps dense assertions of localized hazards. The authors also propose the Cognitive Expected Scene Graph (CESG) Score, a polarity‑aware, structure‑grounded metric that remains robust under semantic reversals, revealing that existing models and traditional metrics fail on this task.
arXiv:2608. 03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction.
arXiv:2608.21928v1 Announce Type: new Abstract: In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied...
arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.
The paper introduces COLAGUARD, a guardrail model that embeds multi-step safety reasoning into a continuous latent space, allowing efficient hidden-state propagation during inference. Compared to existing methods, COLAGUARD achieves an 8.24‑point macro‑F1 improvement over Llama Guard 3 and matches the explicit reasoning baseline GuardReasoner, while delivering a 12.9× speedup and a 22.4× reduction in token usage across ten moderation settings and eight safety benchmarks.
arXiv:2606. 18988v1 Announce Type: new Abstract: Multimodal deception detection is critical for identifying fraudulent intentions, yet existing approaches predominantly rely on end to end black--box paradigms.
arXiv:2609.39168v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet existing...
Large vision-language models (LVLMs) have recently shown immense potential in automated content moderation, sparking growing interest in developing harmful-video benchmarks. However, we identify two primary limitations in existing works: 1) The multi-layered characteristics of harmful videos are overlooked.
arXiv:2609.22234v1 Announce Type: cross Abstract: Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in...
arXiv:2606. 24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still face a fundamental trade-off between temporal reasoning and spatial precision.