Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
Paper
•
2412.15213
•
Published
•
17
Paper
-
-
No More Adam: Learning Rate Scaling at Initialization is All You Need
Paper • 2412.11768 • Published • 35 -
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
Paper • 2412.13663 • Published • 82 -
Autoregressive Video Generation without Vector Quantization
Paper • 2412.14169 • Published • 11 -
ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers
Paper • 2412.12571 • Published • 7 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 67 -
Causal Diffusion Transformers for Generative Modeling
Paper • 2412.12095 • Published • 22 -
Apollo: An Exploration of Video Understanding in Large Multimodal Models
Paper • 2412.10360 • Published • 126 -
Large Action Models: From Inception to Implementation
Paper • 2412.10047 • Published • 25 -
Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation
Paper • 2412.09428 • Published • 7 -
Phi-4 Technical Report
Paper • 2412.08905 • Published • 87 -
MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
Paper • 2412.14164 • Published • 1 -
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Paper • 2412.09596 • Published • 89 -
OLA-VLM: Elevating Visual Perception in Multimodal LLMs with Auxiliary Embedding Distillation
Paper • 2412.09585 • Published • 10 -
Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
Paper • 2412.09548 • Published • 1 -
Multimodal Latent Language Modeling with Next-Token Diffusion
Paper • 2412.08635 • Published • 38 -
MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation
Paper • 2412.07147 • Published • 5