7 papers
What Do Latent Action Models Actually Learn?
Chuheng Zhang, Tim Pearce, Pushi Zhang +5
Latent action models (LAMs) aim to learn action-relevant changes from unlabeled videos by compressing changes between frames as latents. However, differences between video frames c…
Policy Filtration for RLHF to Mitigate Noise in Reward Models
Chuheng Zhang, Wei Shen, Li Zhao +4
While direct policy optimization methods exist, pioneering LLMs are fine-tuned with reinforcement learning from human feedback (RLHF) to generate better responses under the supervi…
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Yuliang Liu, Junjie Lu, Zhaoling Chen +10
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefin…
Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction
Wei Shen, Xiaonan He, Chuheng Zhang +3
Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, thi…
IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
Xiaoyu Chen, Junliang Guo, Tianyu He +5
We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically consistent action space across human and various robots. Through this unified latent action…
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL
Yunseon Choi, Sangmin Bae, Seonghyun Ban +6
With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning reg…