ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
Reinforcement learning with augmented data.Advances in neural information processing systems, 33:19884–19895
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.
citing papers explorer
-
Reinforcing Multimodal Reasoning Against Visual Degradation
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
-
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
-
Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
An end-to-end policy learns robust humanoid locomotion directly from noisy depth images via high-fidelity sensor simulation, vision-aware distillation from privileged maps, and terrain-specific multi-critic reward shaping.