Sparse Autoencoders Find Highly Interpretable Features in Language Models
Paper
•
2309.08600
•
Published
•
11
LLM as a big cell
-
-
Language Modeling Is Compression
Paper • 2309.10668 • Published • 79 -
Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference Using Sorted Fine-Tuning (SoFT)
Paper • 2309.08968 • Published • 22 -
VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning
Paper • 2309.15091 • Published • 31 -
HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models
Paper • 2310.14566 • Published • 23 -
Contrastive Prefence Learning: Learning from Human Feedback without RL
Paper • 2310.13639 • Published • 21 -
SILC: Improving Vision Language Pretraining with Self-Distillation
Paper • 2310.13355 • Published • 4 -
An Early Evaluation of GPT-4V(ision)
Paper • 2310.16534 • Published • 21 -
MM-VID: Advancing Video Understanding with GPT-4V(ision)
Paper • 2310.19773 • Published • 18 -
Large Language Models as Generalizable Policies for Embodied Tasks
Paper • 2310.17722 • Published • 6