Depth Anything V2
Paper
• 2406.09414 • Published
• 103
cool-papers
-
-
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 51 -
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Paper • 2406.04338 • Published • 39 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 120 -
GraCo: Granularity-Controllable Interactive Segmentation
Paper • 2405.00587 • Published -
Differential Transformer
Paper • 2410.05258 • Published • 180 -
APOLLO: SGD-like Memory, AdamW-level Performance
Paper • 2412.05270 • Published • 37 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper • 2501.00958 • Published • 109 -
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
Paper • 2501.03895 • Published • 52 -
The GAN is dead; long live the GAN! A Modern GAN Baseline
Paper • 2501.05441 • Published • 95 -
Infecting Generative AI With Viruses
Paper • 2501.05542 • Published • 13 -
MatAnyone: Stable Video Matting with Consistent Memory Propagation
Paper • 2501.14677 • Published • 34 -
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Paper • 2502.04320 • Published • 36 -
Diffusion Models without Classifier-free Guidance
Paper • 2502.12154 • Published • 8 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8 -
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
Paper • 2502.19204 • Published • 11 -
UniTok: A Unified Tokenizer for Visual Generation and Understanding
Paper • 2502.20321 • Published • 30 -
How far can we go with ImageNet for Text-to-Image generation?
Paper • 2502.21318 • Published • 26 -
AI-Invented Tonal Languages: Preventing a Machine Lingua Franca Beyond Human Understanding
Paper • 2503.01063 • Published • 5 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 126 -
Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective
Paper • 2503.01933 • Published • 13 -
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
Paper • 2503.04724 • Published • 72 -
Forgetting Transformer: Softmax Attention with a Forget Gate
Paper • 2503.02130 • Published • 32 -
AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
Paper • 2503.08417 • Published • 8 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 76 -
The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation
Paper • 2503.10636 • Published • 3 -
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
Paper • 2503.11647 • Published • 146 -
Tokenize Image as a Set
Paper • 2503.16425 • Published • 16 -
When Less is Enough: Adaptive Token Reduction for Efficient Image Representation
Paper • 2503.16660 • Published • 72 -
Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
Paper • 2503.20240 • Published • 22 -
SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
Paper • 2503.21732 • Published • 9 -
X^{2}-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction
Paper • 2503.21779 • Published • 4 -
AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation
Paper • 2503.19693 • Published • 76 -
Scaling Language-Free Visual Representation Learning
Paper • 2504.01017 • Published • 32 -
Gaussian Mixture Flow Matching Models
Paper • 2504.05304 • Published • 11 -
DDT: Decoupled Diffusion Transformer
Paper • 2504.05741 • Published • 77 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Paper • 2504.13837 • Published • 139 -
Group Downsampling with Equivariant Anti-aliasing
Paper • 2504.17258 • Published • 9 -
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Paper • 2504.20966 • Published • 31 -
Training-Free Efficient Video Generation via Dynamic Token Carving
Paper • 2505.16864 • Published • 24 -
Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
Paper • 2505.11881 • Published • 4 -
The Diffusion Duality
Paper • 2506.10892 • Published • 37 -
JAFAR: Jack up Any Feature at Any Resolution
Paper • 2506.11136 • Published • 10 -
Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model
Paper • 2506.15682 • Published • 5 -
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
Paper • 2506.20452 • Published • 19 -
Peccavi: Visual Paraphrase Attack Safe and Distortion Free Image Watermarking Technique for AI-Generated Images
Paper • 2506.22960 • Published • 6 -
Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
Paper • 2507.07994 • Published • 3 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 10 -
2D Gaussian Splatting with Semantic Alignment for Image Inpainting
Paper • 2509.01964 • Published • 7 -
ReSWD: ReSTIR'd, not shaken. Combining Reservoir Sampling and Sliced Wasserstein Distance for Variance Reduction
Paper • 2510.01061 • Published • 2 -
SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusion
Paper • 2412.10437 • Published • 6 -
Image-GS: Content-Adaptive Image Representation via 2D Gaussians
Paper • 2407.01866 • Published • 2 -
FineVision: Open Data Is All You Need
Paper • 2510.17269 • Published • 75 -
Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
Paper • 2510.19944 • Published • 21 -
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
Paper • 2505.20161 • Published • 1 -
Latent Diffusion Model without Variational Autoencoder
Paper • 2510.15301 • Published • 49 -
KLASS: KL-Guided Fast Inference in Masked Diffusion Models
Paper • 2511.05664 • Published • 37 -
VideoSSR: Video Self-Supervised Reinforcement Learning
Paper • 2511.06281 • Published • 25 -
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 70 -
Adversarial Flow Models
Paper • 2511.22475 • Published • 24 -
Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model
Paper • 2512.01030 • Published • 20 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 20 -
Relational Visual Similarity
Paper • 2512.07833 • Published • 25 -
Terrain Diffusion: A Diffusion-Based Successor to Perlin Noise in Infinite, Real-Time Terrain Generation
Paper • 2512.08309 • Published • 4 -
docling-project/SynthCodeNet
Viewer • Updated • 9.33M • 1.73k • 11 -
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Paper • 2511.23386 • Published • 16 -
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Paper • 2512.10534 • Published • 32 -
Sliding Window Attention Adaptation
Paper • 2512.10411 • Published • 21 -
MeshSplatting: Differentiable Rendering with Opaque Meshes
Paper • 2512.06818 • Published • 11 -
Spherical Leech Quantization for Visual Tokenization and Generation
Paper • 2512.14697 • Published • 8 -
Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings
Paper • 2509.10534 • Published • 4 -
RLP: Reinforcement as a Pretraining Objective
Paper • 2510.01265 • Published • 44 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 228 -
Multilingual Pretraining for Pixel Language Models
Paper • 2505.21265 • Published • 1 -
Language Modelling with Pixels
Paper • 2207.06991 • Published • 2 -
AgentOCR: Reimagining Agent History via Optical Self-Compression
Paper • 2601.04786 • Published • 30 -
GenCtrl -- A Formal Controllability Toolkit for Generative Models
Paper • 2601.05637 • Published • 5 -
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
Paper • 2601.07351 • Published • 26 -
JudgeRLVR: Judge First, Generate Second for Efficient Reasoning
Paper • 2601.08468 • Published • 7 -
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 155 -
Toward Efficient Agents: Memory, Tool learning, and Planning
Paper • 2601.14192 • Published • 55 -
Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
Paper • 2512.12167 • Published • 5 -
GutenOCR: A Grounded Vision-Language Front-End for Documents
Paper • 2601.14490 • Published • 37 -
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
Paper • 2601.13606 • Published • 11 -
Guidelines to Prompt Large Language Models for Code Generation: An Empirical Characterization
Paper • 2601.13118 • Published • 1 -
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
Paper • 2601.17027 • Published • 41 -
Self-Refining Video Sampling
Paper • 2601.18577 • Published • 25 -
Towards Pixel-Level VLM Perception via Simple Points Prediction
Paper • 2601.19228 • Published • 18 -
Self-Distillation Enables Continual Learning
Paper • 2601.19897 • Published • 26 -
Reinforcement Learning via Self-Distillation
Paper • 2601.20802 • Published • 40 -
One-step Latent-free Image Generation with Pixel Mean Flows
Paper • 2601.22158 • Published • 18 -
Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
Paper • 2601.22975 • Published • 105 -
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Paper • 2601.23182 • Published • 20 -
Optimizing Few-Step Generation with Adaptive Matching Distillation
Paper • 2602.07345 • Published • 9 -
Agents of Chaos
Paper • 2602.20021 • Published • 27 -
SIMSPINE: A Biomechanics-Aware Simulation Framework for 3D Spine Motion Annotation and Benchmarking
Paper • 2602.20792 • Published • 2