Search Results for author:
Found 6 papers, 5 papers with code
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Recent advances in high-fidelity virtual environments serve as one of the major driving forces for building intelligent embodied agents to perceive, reason and interact with the physical world.
SALMON: Self-Alignment with Instructable Reward Models
Supervised Fine-Tuning (SFT) on response demonstrations combined with Reinforcement Learning from Human Feedback (RLHF) constitutes a powerful paradigm for aligning LLM-based AI agents.
Building Cooperative Embodied Agents Modularly with Large Language Models
In this work, we address challenging multi-agent cooperation problems with decentralized control, raw sensory observations, costly communication, and multi-objective tasks instantiated in various embodied environments.
Bridging the Gap between Decision and Logits in Decision-based Knowledge Distillation for Pre-trained Language Models
By combining the theoretical and empirical estimations of the decision distributions together, the estimation of logits can be successfully reduced to a simple root-finding problem.
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Recent AI-assistant agents, such as ChatGPT, predominantly rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback (RLHF) to align the output of large language models (LLMs) with human intentions, ensuring they are helpful, ethical, and reliable.
See, Think, Confirm: Interactive Prompting Between Vision and Language Models for Knowledge-based Visual Reasoning
The see stage scans the image and grounds the visual concept candidates with a visual perception model.
