My favourites
updated
Test-Time Scaling with Reflective Generative Model
Paper
• 2507.01951
• Published • 106
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth
Approach
Paper
• 2502.05171
• Published • 162
Autoregressive Diffusion Models
Paper
• 2110.02037
• Published
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative
Image Modeling
Paper
• 2502.09509
• Published • 9
Improving the Diffusability of Autoencoders
Paper
• 2502.14831
• Published • 2
Deep Compression Autoencoder for Efficient High-Resolution Diffusion
Models
Paper
• 2410.10733
• Published • 9
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured
Latent Space
Paper
• 2508.00413
• Published • 7
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion
Transformers
Paper
• 2504.10483
• Published • 22
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid
Mamba-Transformer Reasoning Model
Paper
• 2508.14444
• Published • 47
MetaCLIP 2: A Worldwide Scaling Recipe
Paper
• 2507.22062
• Published • 38
Waver: Wave Your Way to Lifelike Video Generation
Paper
• 2508.15761
• Published • 38
Qwen-Image Technical Report
Paper
• 2508.02324
• Published • 277
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior
Long-Context Learning
Paper
• 2508.18756
• Published • 36
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Paper
• 2509.10441
• Published • 31
Why Language Models Hallucinate
Paper
• 2509.04664
• Published • 200
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal
Conditioning
Paper
• 2509.08519
• Published • 128
Step1X-Edit: A Practical Framework for General Image Editing
Paper
• 2504.17761
• Published • 91
Transition Matching: Scalable and Flexible Generative Modeling
Paper
• 2506.23589
• Published • 1
MMaDA: Multimodal Large Diffusion Language Models
Paper
• 2505.15809
• Published • 100
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and
Future Frontiers
Paper
• 2506.23918
• Published • 91
Diffusion Beats Autoregressive in Data-Constrained Settings
Paper
• 2507.15857
• Published • 2
Hierarchical Reasoning Model
Paper
• 2506.21734
• Published • 54
UMO: Scaling Multi-Identity Consistency for Image Customization via
Matching Reward
Paper
• 2509.06818
• Published • 29
Wan-Animate: Unified Character Animation and Replacement with Holistic
Replication
Paper
• 2509.14055
• Published • 17
Inpainting-Guided Policy Optimization for Diffusion Large Language
Models
Paper
• 2509.10396
• Published • 17
Lynx: Towards High-Fidelity Personalized Video Generation
Paper
• 2509.15496
• Published • 13
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model
Self-Distillation
Paper
• 2509.19296
• Published • 32
Video models are zero-shot learners and reasoners
Paper
• 2509.20328
• Published • 98
What Characterizes Effective Reasoning? Revisiting Length, Review, and
Structure of CoT
Paper
• 2509.19284
• Published • 23
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Paper
• 2509.20427
• Published • 90
Paper
• 2509.22358
• Published • 2
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation
and Editing
Paper
• 2509.24900
• Published • 54
Diffusion Transformers with Representation Autoencoders
Paper
• 2510.11690
• Published • 171
WithAnyone: Towards Controllable and ID Consistent Image Generation
Paper
• 2510.14975
• Published • 86
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale
Prediction
Paper
• 2404.02905
• Published • 73
DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
Paper
• 2510.20766
• Published • 37
Continuous Autoregressive Language Models
Paper
• 2510.27688
• Published • 74
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper
• 2511.09611
• Published • 73
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper
• 2512.04677
• Published • 124
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper
• 2511.22699
• Published • 248
Vision Bridge Transformer at Scale
Paper
• 2511.23199
• Published • 47
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
Paper
• 2512.07829
• Published • 25
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper
• 2512.13687
• Published • 105
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
Paper
• 2512.12967
• Published • 113
What matters for Representation Alignment: Global Information or Spatial Structure?
Paper
• 2512.10794
• Published • 11
KlingAvatar 2.0 Technical Report
Paper
• 2512.13313
• Published • 43
Back to Basics: Let Denoising Generative Models Denoise
Paper
• 2511.13720
• Published • 73
PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss
Paper
• 2602.02493
• Published • 47
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Paper
• 2602.14041
• Published • 46
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Paper
• 2602.12205
• Published • 82
Autoregressive Image Generation with Masked Bit Modeling
Paper
• 2602.09024
• Published • 7
ViT-5: Vision Transformers for The Mid-2020s
Paper
• 2602.08071
• Published • 2
MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs
Paper
• 2602.12705
• Published • 62
Unified Latents (UL): How to train your latents
Paper
• 2602.17270
• Published • 63
dLLM: Simple Diffusion Language Modeling
Paper
• 2602.22661
• Published • 136
Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance
Paper
• 2603.02175
• Published • 24
Unified Multimodal Understanding and Generation Models: Advances,
Challenges, and Opportunities
Paper
• 2505.02567
• Published • 82
Helios: Real Real-Time Long Video Generation Model
Paper
• 2603.04379
• Published • 141
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper
• 2601.03233
• Published • 203
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper
• 2603.06569
• Published • 112
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
Paper
• 2603.09877
• Published • 46
MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with
Rectified Flow and Region-specific Contrastive Loss
Paper
• 2508.05772
• Published • 3
Agentic Reasoning for Large Language Models
Paper
• 2601.12538
• Published • 204
Mixture-of-Depths Attention
Paper
• 2603.15619
• Published • 79
Repurposing Geometric Foundation Models for Multi-view Diffusion
Paper
• 2603.22275
• Published • 50
PixelSmile: Toward Fine-Grained Facial Expression Editing
Paper
• 2603.25728
• Published • 103
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper
• 2603.17187
• Published • 137
MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines
Paper
• 2603.06679
• Published • 4
When Negation Is a Geometry Problem in Vision-Language Models
Paper
• 2603.20554
• Published
PowerCLIP: Powerset Alignment for Contrastive Pre-Training
Paper
• 2511.23170
• Published
DiVeQ: Differentiable Vector Quantization Using the Reparameterization Trick
Paper
• 2509.26469
• Published
LPM 1.0: Video-based Character Performance Model
Paper
• 2604.07823
• Published • 79
OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Paper
• 2603.24458
• Published • 7
DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Paper
• 2510.12691
• Published • 1
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Paper
• 2604.02029
• Published • 101
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper
• 2604.20796
• Published • 89
Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation
Paper
• 2604.19141
• Published • 1
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper
• 2604.24763
• Published • 69
Video Analysis and Generation via a Semantic Progress Function
Paper
• 2604.22554
• Published • 58
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility,
Reasoning, and Efficiency
Paper
• 2508.18265
• Published • 220
Phi-4-reasoning-vision-15B Technical Report
Paper
• 2603.03975
• Published • 21
MacTok: Robust Continuous Tokenization for Image Generation
Paper
• 2603.29634
• Published • 2
Qwen-Image-VAE-2.0 Technical Report
Paper
• 2605.13565
• Published • 62
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
Paper
• 2605.23902
• Published • 44
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper
• 2605.21573
• Published • 109
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Paper
• 2605.31604
• Published • 61
Bernini: Latent Semantic Planning for Video Diffusion
Paper
• 2605.22344
• Published • 20
Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion
Paper
• 2606.15236
• Published • 21
Text-to-Image • Updated • 1.08k
• 31
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
Paper
• 2606.09056
• Published • 8
Next-Latent Prediction Transformers Learn Compact World Models
Paper
• 2511.05963
• Published • 7
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution
Paper
• 2606.27313
• Published • 28
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
Paper
• 2606.23503
• Published • 3
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
Paper
• 2608.03573
• Published • 55
Abra: Scaling Diffusion Image Training
Paper
• 2608.17286
• Published • 12
Elastic Token Compression for Pixel-Space Diffusion Transformers
Paper
• 2608.29281
• Published • 1
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Paper
• 2608.25756
• Published
Vero: An Open RL Recipe for General Visual Reasoning
Paper
• 2604.04917
• Published • 29
NOVA: A Benchmark for Anomaly Localization and Clinical Reasoning in
Brain MRI
Paper
• 2505.14064
• Published • 20
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Paper
• 2609.11638
• Published • 219
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Paper
• 2609.24981
• Published • 56
VideoGen-Agent: Reinforcing Video Generation Agents
Paper
• 2609.24997
• Published • 49
OmniEdu: Open Foundation Models for Learning and Teaching
Paper
• 2609.23088
• Published • 55
Rufus-Air: An Open LLM Post-Training Recipe
Paper
• 2609.29421
• Published • 35
MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
Paper
• 2506.01946
• Published • 3
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper
• 2609.38721
• Published • 126
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation
Paper
• 2609.38597
• Published • 28
Video Generation Models: A Survey of Post-Training and Alignment
Paper
• 2610.00812
• Published • 19
LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning
Paper
• 2510.04573
• Published • 3
Apertus 1.5: From Open Text Models to Open Multimodal Reasoners
Paper
• 2610.15542
• Published • 41
Spectral-Spatial Interpretation
Paper
• 2610.21114
• Published • 27
WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Paper
• 2610.31329
• Published • 45
MOSS-Image Technical Report
Paper
• 2610.23374
• Published • 91
Paper
• 2608.15045
• Published • 51
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes
Paper
• 2609.03796
• Published • 58
Scalable Patch-Level Self-Supervised Learning
Paper
• 2610.10013
• Published • 3
EditAgent: Rethinking Agentic Image Editing
Paper
• 2610.39664
• Published • 13
Pixel-space video generation with U-JiT
Paper
• 2611.04764
• Published
Open Vision Banana: A Fully Open Recipe for Generative Visual Perception
Paper
• 2611.15844
• Published • 41
Back to Pixels: Lifting Latent Video Diffusion into Pixel Space
Paper
• 2611.17336
• Published • 7
Unbundling Multimodal Vision Encoding
Paper
• 2611.17334
• Published • 21
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation
Paper
• 2610.05608
• Published • 172
JVT: Just Video Transformer makes pixel-space video diffusion simple
Paper
• 2611.18549
• Published • 14
WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
Paper
• 2611.07392
• Published • 47
Iris-Z: Scaling One Generative Model Past Specialist Geometry Models
Paper
• 2611.16010
• Published • 4