arXiv:2607. 05910v1 Announce Type: cross Abstract: Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an intrinsic property of an image.
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.
The paper introduces a visual odometry frontend that automatically and continuously adapts its parameters using an image-conditioned reinforcement learning policy. The policy selects key tuning values—FAST detection threshold, KLT patch size, and RANSAC rejection threshold—based on a lightweight image embedding and frontend statistics, with a privileged critic aiding training. Trained on synthetic data, the approach transfers zero‑shot to real-world benchmarks, improving the tracking‑computation trade‑off by up to 8% in accuracy and 57% in runtime compared to static configurations.
arXiv:2607. 21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens.
arXiv:2608.21748v1 Announce Type: new Abstract: Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds ar...
BCPPO is a new variant of Proximal Policy Optimization that uses Bachelier-inspired cost‑prediction networks to generate a smooth penalty based on disagreement among critics. The method keeps temporal‑difference learning unchanged, applies a saturation‑aware controller to manage cost penalties, and deploys only the policy network. Across extensive experiments, BCPPO outperforms comparators in achieving higher mean returns while maintaining lower or comparable CVaR in all tested tasks.
arXiv:2606. 29887v1 Announce Type: new Abstract: In real-world applications, guardrails are often expected to identify unsafe user-model interactions according to application-specific safety policies, rather than relying on predefined risk taxonomies.
arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.
arXiv:2606. 05805v1 Announce Type: new Abstract: LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categories, and/or explanatory rationales about potential policy violations.
arXiv:2610.02019v1 Announce Type: cross Abstract: The rapid growth of video-based social media has increased users' exposure to harmful content, creating a need for reliable automated video safety de...
arXiv:2607. 08925v1 Announce Type: new Abstract: Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do.
The paper introduces FailBank, a four‑stage self‑evolving framework that transforms runtime feedback from safety shields into lasting policy improvements for vision‑language‑action (VLA) models. By using a counterfactual correction teacher, outcome‑aware admission, and guarded LoRA updates, FailBank converts useful shield proposals into corrective targets while preserving successful actions as anchors. Experiments on the VLA‑Arena benchmark show that FailBank boosts task success rates by up to 8.5 percentage points and reduces cumulative policy cost by up to 35.6%, outperforming both base policies and traditional runtime shielding.
arXiv:2608. 15101v1 Announce Type: new Abstract: Policy evaluation often estimates direct benefits and costs while treating the institutional environment as fixed.