Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed…
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingby Mingjia Shi, Yuhao Zhou,…
Beyond Data Quantity: Key Factors Driving Performance in Multilingual Language Modelsby Sina Bagheri Nezhad, Ameeta…
Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasksby Hao…
EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationby Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun…
Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Modelsby Xiaochen Zhu, Georgi…
Attention with Dependency Parsing Augmentation for Fine-Grained Attributionby Qiang Ding, Lvzhou Luo, Yixuan Cao, Ping…
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsby Yuchen Fu, Zifeng…
NITRO: LLM Inference on Intel Laptop NPUsby Anthony Fei, Mohamed S. AbdelfattahFirst submitted to arxiv…
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformersby Dong Hoon Lee, Seunghoon…