arXiv:2610.19563v1 Announce Type: new Abstract: Safety alignment of text-to-image diffusion models aims to suppress harmful content without compromising useful generation capabilities. However, prefe...
arXiv:2607. 00402v1 Announce Type: cross Abstract: Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.
Decoupled Safety Control (DSC) is a plug‑in algorithm that improves training‑free safety guidance for diffusion models by separating the unsafe condition from the intervention process. Unlike existing coupled safety‑control chains, DSC determines the intervention based on the current generation state, reducing residual unsafe content and preserving benign‑generation quality. Experiments on standard safety benchmarks demonstrate that DSC achieves stronger unsafe‑content suppression while maintaining efficient inference.
arXiv:2606. 17257v1 Announce Type: cross Abstract: Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning that degrades general capability, or apply external filters that are trivially bypassed by adversarial prompts.
The paper examines the limitations of global unsafety signals used in training‑free safeguards for text‑to‑image generation, showing a trade‑off between coverage and selectivity. It introduces CALM, a counterfactual adaptive local modulation method that locally corrects unsafe token representations while preserving benign content. Experiments demonstrate that CALM outperforms global removal approaches in suppressing unsafe content without compromising utility.
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
arXiv:2608. 19598v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences.
arXiv:2511. 19558v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can emit copyrighted, unsafe, or private content.
arXiv:2606. 31876v1 Announce Type: new Abstract: To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space.
arXiv:2608.29997v1 Announce Type: new Abstract: We propose Discrete Diffusion Bridges (DDB), a novel framework designed to resolve the fundamental spatiotemporal misalignment of standard discrete dif...
arXiv:2605. 08116v2 Announce Type: replace-cross Abstract: Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored.
Aligned vision‑language models (VLMs) are designed to combine grounded visual reasoning with safe generation. The study finds that when safety constraints are applied, these models often abstain from answering questions that they could answer under default instruction, yet visual evidence continues to influence the decoding process. The authors show that safety‑induced abstention alters late‑stage hidden‑state dynamics, and that targeted interventions can restore grounded answering without retraining or changing visual inputs.