ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
Self-improving embodied foundation models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
RARM is a lightweight visual comparator trained once on general videos that supplies dense progress rewards to RL by matching rollout clips to a reference demonstration and gating rewards on match confidence.
TSIL mines temporally efficient successful trajectories during RL training to supply configuration-conditioned adaptive targets and efficiency-weighted self-imitation, improving efficiency and robustness across 15 long-horizon manipulation tasks.
Feat2Go uses patch-level similarity from a visual world model and trend-based clustering to create progress targets for training value models that improve reward shaping in embodied RL for VLA policies, yielding large gains on ManiSkill3 and RoboTwin benchmarks.
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
Bimanual VLA coordination strategies, training recipes, and continuous action chunking transfer to unmanned aerial systems; the survey maps 183 works and lists fourteen shared research directions.
WorldSample generates synthetic transitions from a post-trained world model grounded in real rollouts and uses Policy-Paced Learning to improve RL policies, reporting 28% higher success rates and 59% fewer training steps on contact-rich robot tasks.
Embodied reward models systematically over-reward unsafe, suboptimal, and shortcut robot behaviors due to training on successful data only, and modest inclusion of bad behavior data improves alignment with human preferences.
CaB predicts Before/Hit/After boundary tokens to produce auditable switching decisions and boundary-stable control in VLA agents on a Minecraft benchmark under single global calibration.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
-
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
RARM is a lightweight visual comparator trained once on general videos that supplies dense progress rewards to RL by matching rollout clips to a reference demonstration and gating rewards on match confidence.
-
Temporal Self-Imitation Learning
TSIL mines temporally efficient successful trajectories during RL training to supply configuration-conditioned adaptive targets and efficiency-weighted self-imitation, improving efficiency and robustness across 15 long-horizon manipulation tasks.
-
Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement Learning
Feat2Go uses patch-level similarity from a visual world model and trend-based clustering to create progress targets for training value models that improve reward shaping in embodied RL for VLA policies, yielding large gains on ManiSkill3 and RoboTwin benchmarks.
-
RISE: Self-Improving Robot Policy with Compositional World Model
RISE combines a controllable dynamics model and progress value model into a closed-loop self-improving pipeline that updates robot policies entirely in imagination, reporting over 35% absolute gains on three real-world tasks.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
Bimanual VLA coordination strategies, training recipes, and continuous action chunking transfer to unmanned aerial systems; the survey maps 183 works and lists fourteen shared research directions.
-
WorldSample: Closed-loop Real-robot RL with World Modelling
WorldSample generates synthetic transitions from a post-trained world model grounded in real rollouts and uses Policy-Paced Learning to improve RL policies, reporting 28% higher success rates and 59% fewer training steps on contact-rich robot tasks.
-
Position: Good Embodied Reward Models Need Bad Behavior Data
Embodied reward models systematically over-reward unsafe, suboptimal, and shortcut robot behaviors due to training on successful data only, and modest inclusion of bad behavior data improves alignment with human preferences.
-
Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration
CaB predicts Before/Hit/After boundary tokens to produce auditable switching decisions and boundary-stable control in VLA agents on a Minecraft benchmark under single global calibration.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.