AI研究论文每日精选

FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models

FiT: Flexible Vision Transformer for Diffusion Model

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling

Speculative Streaming: Fast LLM Inference without Auxiliary Models

OneBit: Towards Extremely Low-bit Large Language Models

Learning to Learn Faster from Human Feedback with Language Model Predictive Control

CoLLaVO: Crayon Large Language and Vision mOdel

Reformatted Alignment

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration

GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements

Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesis

DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning

Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability