# Towards General Language-Conditioned Latent Safety Filters

arXiv: https://arxiv.org/abs/2608.00315 · HTML: https://mlsanity.com/paper/2608.00315/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Safety and adversarial attacks, one of 13 directions in Vision-language-action models.
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Placed in

- Vision-language-action models / [Safety and adversarial attacks](https://mlsanity.com/vla/safety-and-adversarial-attacks/)

## Builds on (most cited first, 27 of 27)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Control Barrier Function Based Quadratic Programs for Safety Critical Systems](https://mlsanity.com/paper/1609.06408/) (2016)
- [Hamilton-Jacobi Reachability: A Brief Overview and Recent Advances](https://mlsanity.com/paper/1709.07523/) (2017)
- [Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers](https://mlsanity.com/paper/2409.20537/) (2024)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis](https://mlsanity.com/paper/2502.00935/) (2025)
- [RoboBrain 2.5: Depth in Sight, Time in Mind](https://mlsanity.com/paper/2601.14352/) (2026)
- [VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer](https://mlsanity.com/paper/2512.11891/) (2025)
- [ConformalNL2LTL: Translating Natural Language Instructions into Temporal Logic Formulas with Conformal Correctness Guarantees](https://mlsanity.com/paper/2504.21022/) (2025)
- [AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge](https://mlsanity.com/paper/2602.13476/) (2026)
- [Updating Robot Safety Representations Online from Natural Language Feedback](https://mlsanity.com/paper/2409.14580/) (2024)
- [Grammar-Forced Translation of Natural Language to Temporal Logic using LLMs](https://mlsanity.com/paper/2512.16814/) (2025)
- [From Words to Safety: Language-Conditioned Safety Filtering for Robot Navigation](https://mlsanity.com/paper/2511.05889/) (2025)
- [Hamilton-Jacobi Based Policy-Iteration via Deep Operator Learning](https://mlsanity.com/paper/2406.10920/) (2024)
- [Geometry-Aware Predictive Safety Filters on Humanoids: From Poisson Safety Functions to CBF Constrained MPC](https://mlsanity.com/paper/2508.11129/) (2025)
- [Bellman Value Decomposition for Task Logic in Safe Optimal Control](https://mlsanity.com/paper/2602.19532/) (2026)
- [HJRNO: Hamilton-Jacobi Reachability with Neural Operators](https://mlsanity.com/paper/2504.19989/) (2025)
- [Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters](https://mlsanity.com/paper/2604.21189/) (2026)
- [Risk-Aware Safety Filters with Poisson Safety Functions and Laplace Guidance Fields](https://mlsanity.com/paper/2510.25913/) (2025)
- [Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions](https://mlsanity.com/paper/2603.05497/) (2026)

## Built on by (most cited first, 1 of 1)

- [CrossSafe: Towards Cross-Embodiment Latent Safety Filters](https://mlsanity.com/paper/2609.28984/) (2026)

## Abstract (arXiv)

Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language. Safe deployment, however, requires adapting not only to new tasks but also to varying safety requirements across users, environments, and applications. Existing safety filters remain largely constraint-specific and thus must be redesigned or relearned when safety requirements change. In this paper, we investigate language-conditioned safety filtering, in which a Hamilton-Jacobi safety actor and critic are conditioned on language-specified constraints. We evaluate this formulation across pick-and-place, table-wiping, and block-stacking tasks in the vision-based setting, examining its ability to enforce language-specified constraints and transfer to unseen constraint instances within the evaluated constraint families. Our experiments provide evidence that language-conditioned safety filters reduce constraint violations and exhibit partial transfer to unseen constraint instances.