Large Language Model
Why Transformers Need Adam: A Hessian Perspective
CNNs, MLPs, and quadratic problems, and find that SGD can perform on par with Adam on problems without block heterogeneity, but performs worse than Adam when the heterogeneity exists.
Compositional 3D-aware Video Generation with LLM Director
Sampling to refine the composition.
LLMDF A: Analyzing Dataflow in Code with Large Language Models
Dataflow analysis is a fundamental code analysis technique that identifies dependencies between program values.
Enhancing Large Vision Language Models with Self-Training on Image Comprehension Yihe Deng 1, Pan Lu1,3, Fan Yin
Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire.
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
Work done during an internship at ByteDance San Jose, CA.
Paralinguistics-A ware Speech-Empowered Large Language Models for Natural Conversation
Recent work shows promising results in expanding the capabilities of large language models (LLM) to directly understand and synthesize speech.