Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference Paper • 2412.13663 • Published 12 days ago • 112
Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers Paper • 2412.12276 • Published 14 days ago • 15
Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models Paper • 2412.12606 • Published 13 days ago • 41
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping Paper • 2412.11279 • Published 15 days ago • 12
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation Paper • 2412.11919 • Published 14 days ago • 33
No More Adam: Learning Rate Scaling at Initialization is All You Need Paper • 2412.11768 • Published 14 days ago • 41
An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control Paper • 2403.04880 • Published Mar 7 • 7
TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices Paper • 2410.00531 • Published Oct 1 • 29