Tag: understanding-generation

Mar 18, 2026

MaskGIT: Masked Generative Image Transformer

Mar 18, 2026

Autoregressive Image Generation without Vector Quantization

Mar 18, 2026

LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation

Mar 18, 2026

Making LLaMA SEE and Draw with SEED Tokenizer

Mar 18, 2026

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling

Mar 18, 2026

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Mar 18, 2026

TRANSFUSION: PREDICT THE NEXT TOKEN AND DIFFUSE IMAGES WITH ONE MULTI-MODAL MODEL

Mar 18, 2026

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Mar 18, 2026

EMMA: Efficient Visual Alignment in Multi-Modal LLMs

Mar 18, 2026

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

Mar 18, 2026

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Mar 18, 2026

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Mar 18, 2026

LangBridge: Interpreting Image as a Combination of Language Embeddings

Mar 18, 2026

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Mar 18, 2026

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens

Mar 18, 2026

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

Mar 18, 2026

ReCA: A Parametric ReLU Composite Activation Function

Mar 18, 2026

Emerging Properties in Unified Multimodal Pretraining

Mar 18, 2026

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation

Mar 18, 2026

Mask-Based LoRA Tuning for Flexible Video Editing with Spatiotemporal Guidance

Mar 18, 2026

Ming-Omni: A Unified Multimodal Model for Perception and Generation

Mar 18, 2026

Show-o2: Improved Native Unified Multimodal Models

Mar 18, 2026

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Mar 18, 2026

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Mar 18, 2026

HunyuanImage 3.0 Technical Report

Mar 18, 2026

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

Mar 18, 2026

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

Mar 18, 2026

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Mar 18, 2026

BLIP3o-NEXT: Next Frontier of Native Image Generation

Mar 18, 2026

Emu3.5: Native Multimodal Models are World Learners

Mar 18, 2026

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning

Mar 18, 2026

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

Mar 18, 2026

OmniGen2: A Versatile and Open-Source Generative Model for Diverse Generation Tasks

Mar 18, 2026

Paper Trail

Explorer

Tag: understanding-generation

MaskGIT: Masked Generative Image Transformer

Autoregressive Image Generation without Vector Quantization

LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation

Making LLaMA SEE and Draw with SEED Tokenizer

AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling

Chameleon: Mixed-Modal Early-Fusion Foundation Models

TRANSFUSION: PREDICT THE NEXT TOKEN AND DIFFUSE IMAGES WITH ONE MULTI-MODAL MODEL

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

EMMA: Efficient Visual Alignment in Multi-Modal LLMs

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

LangBridge: Interpreting Image as a Combination of Language Embeddings

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement

ReCA: A Parametric ReLU Composite Activation Function

Emerging Properties in Unified Multimodal Pretraining

Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation

Mask-Based LoRA Tuning for Flexible Video Editing with Spatiotemporal Guidance

Ming-Omni: A Unified Multimodal Model for Perception and Generation

Show-o2: Improved Native Unified Multimodal Models

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

HunyuanImage 3.0 Technical Report

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

Seedream 4.0: Toward Next-generation Multimodal Image Generation

BLIP3o-NEXT: Next Frontier of Native Image Generation

Emu3.5: Native Multimodal Models are World Learners

MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

OmniGen2: A Versatile and Open-Source Generative Model for Diverse Generation Tasks

Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis