DriveMA shows that one-step meta-actions derived from trajectories can replace verbose reasoning in Driving VLAs, achieving new state-of-the-art Rater Feedback Scores of 8.060 (2B model) and 8.079 (4B model) on the Waymo End-to-End Driving Challenge.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active sampling curriculum, matching expert human teleoperation performance.
DeepImagine trains LLMs on counterfactual pairs from clinical trials using supervised fine-tuning and reinforcement learning to improve outcome prediction by approximating causal mechanisms.
citing papers explorer
-
DriveMA: Rethinking Language Interfaces in Driving VLAs with One-Step Meta-Actions
DriveMA shows that one-step meta-actions derived from trajectories can replace verbose reasoning in Driving VLAs, achieving new state-of-the-art Rater Feedback Scores of 8.060 (2B model) and 8.079 (4B model) on the Waymo End-to-End Driving Challenge.
-
SigLoMa: Learning Open-World Quadrupedal Loco-Manipulation from Ego-Centric Vision
SigLoMa enables dynamic loco-manipulation on quadrupeds from ego-centric 5 Hz vision alone by using Sigma Points for scalable exteroception, an ego-centric Kalman Filter for high-rate state estimation, and an active sampling curriculum, matching expert human teleoperation performance.
-
DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
DeepImagine trains LLMs on counterfactual pairs from clinical trials using supervised fine-tuning and reinforcement learning to improve outcome prediction by approximating causal mechanisms.
- ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems