MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Paper
•
2407.08083
•
Published
•
33
my_read_book
-
-
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 62 -
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Paper • 2408.15237 • Published • 42 -
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Paper • 2409.11355 • Published • 31 -
OmniGen: Unified Image Generation
Paper • 2409.11340 • Published • 115 -
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Paper • 2409.12183 • Published • 39 -
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
Paper • 2409.12568 • Published • 51 -
Imagine yourself: Tuning-Free Personalized Image Generation
Paper • 2409.13346 • Published • 71 -
Training Language Models to Self-Correct via Reinforcement Learning
Paper • 2409.12917 • Published • 139 -
MaskBit: Embedding-free Image Generation via Bit Tokens
Paper • 2409.16211 • Published • 17 -
Emu3: Next-Token Prediction is All You Need
Paper • 2409.18869 • Published • 95 -
FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
Paper • 2412.09626 • Published • 20 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 102 -
ColorFlow: Retrieval-Augmented Image Sequence Colorization
Paper • 2412.11815 • Published • 26 -
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Paper • 2412.18319 • Published • 40 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper • 2501.06186 • Published • 66 -
Transformer^2: Self-adaptive LLMs
Paper • 2501.06252 • Published • 55 -
MiniMax-01: Scaling Foundation Models with Lightning Attention
Paper • 2501.08313 • Published • 289 -
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models
Paper • 2501.06751 • Published • 33 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 391 -
Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
Paper • 2501.12202 • Published • 46 -
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Paper • 2502.00299 • Published • 2 -
Region-Adaptive Sampling for Diffusion Transformers
Paper • 2502.10389 • Published • 54 -
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
Paper • 2502.18364 • Published • 36 -
Transformers without Normalization
Paper • 2503.10622 • Published • 162 -
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models
Paper • 2503.18886 • Published • 21 -
D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation
Paper • 2504.09454 • Published • 12 -
FlowTok: Flowing Seamlessly Across Text and Image Tokens
Paper • 2503.10772 • Published • 19 -
Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection
Paper • 2503.12271 • Published • 9 -
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Paper • 2504.16080 • Published • 15 -
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
Paper • 2503.10618 • Published • 17 -
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Paper • 2504.20966 • Published • 25