Deep Learning
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint Zhenzhi Wang
Text-conditioned motion synthesis has made remarkable progress with the emergence of diffusion models. However, the majority of these motion diffusion models are primarily designed for a single character and overlook multi-human interactions.
Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward
The latter case can be further reduced to adversarial MDP when preferences only depend on the final state.
On the Planning Abilities of Large Language Models: A Critical Investigation
Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities.
TAIA: Large Language Models are Out-of-Distribution Data Learners
However, in certain specialized domains, such as healthcare or harmless content generation, it is nearly impossible to obtain a large volume of high-quality data that matches the downstream distribution.
Coarse-to-Fine Concept Bottleneck Models
Deep learning algorithms have recently gained significant attention due to their impressive performance.
