Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
5
4
A single adversarial token can bypass most safety filters.
Don't let shallow-layer cues fool you: SAFE-Pruner uses "future sight" to prune vision-language-action models, achieving 1.89x speedup without sacrificing task success.
A surprisingly simple VLA model, StarVLA-$\alpha$, beats more complex systems on real-world robotics tasks, suggesting that VLM backbones are more critical than intricate architectures.