[7 Jan 2023] ROIC-DM: Robust Text Inference and Classification via Diffusion Model ...

Abstract: Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for ...

Quantization plays a crucial role in deploying Large Language Models (LLMs) in resource-constrained environments. However, the presence of outlier features significantly hinders low-bit quantization.

Abstract: Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability ...