Alignment tuning has become the de facto standard practice for enabling base large language models (LLMs) to serve as open-domain AI assistants. The alignment tuning process typically involves instruction learning through supervised fine-tuning (SFT) and preference tuning via reinforcement learning from human feedback (RLHF). A recent study, LIMA (Zhou et…

It’s better to consider RAG + FT, FT for a long term memory..

How do companies actually use LLMs in production?

We present CoDi-2, a versatile and interactive Multimodal Large Language Model (MLLM) that can follow complex multimodal interleaved instructions, conduct incontext learning (ICL), reason, chat, edit, etc., in an any-toany input-output modality paradigm. By aligning modalities with language for both encoding and generation, CoDi-2 empowers Large Language Models (LLMs) to…

After #LLMs hallucination, here comes #LLMs hypnosis! 😵‍💫 In a fun and poetic experiment, researchers were able to extract training data by asking #chatGPT to repeat “poem” forever. …

There is no “AI”, profile matching or anything else to find a partner, no matter what for.

// in progress..

Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However, challenges persist in the realm of image-to-video, especially in character animation, where temporally maintaining consistency with detailed information…