Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Modelsby Bingchen Liu, Ehsan Akhgari, Alexander…
Self-Attention Limits Working Memory Capacity of Transformer-Based Modelsby Dongyu Gong, Hantao ZhangFirst submitted to arxiv…
Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steeringby Qingru Zhang, Xiaodong Yu,…
Famba-V: Fast Vision Mamba with Cross-Layer Token Fusionby Hui Shen, Zhongwei Wan, Xin Wang, Mi…
GP-GPT: Large Language Model for Gene-Phenotype Mappingby Yanjun Lyu, Zihao Wu, Lu Zhang, Jing Zhang,…
Causal Inference with Large Language Model: A Surveyby Jing MaFirst submitted to arxiv on: 15…
REG: Refined Generalized Focal Loss for Road Asset Detection on Thai Highways Using Vision-Based Detection…
Towards Kinetic Manipulation of the Latent Spaceby Diego PorresFirst submitted to arxiv on: 15 Sep…
SFR-RAG: Towards Contextually Faithful LLMsby Xuan-Phi Nguyen, Shrey Pandit, Senthil Purushwalkam, Austin Xu, Hailin Chen,…
Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challengesby Vinay…