[추후 논문 리뷰 paper 정리] - 계속 업데이트

---

2023.05.06

1. Segment Anything: https://ai.facebook.com/research/publications/segment-anything/

Segment Anything | Meta AI Research

 

2. InstructGPT: https://arxiv.org/abs/2203.02155

Training language models to follow instructions with human feedback

 

3. DDPM(Denoising Diffusion Probabilistic Models): https://arxiv.org/abs/2006.11239

Denoising Diffusion Probabilistic Models

 

4. DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection: https://paperswithcode.com/paper/dino-detr-with-improved-denoising-anchor-1

Papers with Code - DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

 

5. LLaMA: Open and Efficient Foundation Language Models: https://paperswithcode.com/paper/llama-open-and-efficient-foundation-language-1

Papers with Code - LLaMA: Open and Efficient Foundation Language Models

---

2023.05.16

6. Hypernetworks: https://arxiv.org/abs/1609.09106

HyperNetworks

 

7. PET-Neus: https://paperswithcode.com/paper/pet-neus-positional-encoding-tri-planes-for

Papers with Code - PET-NeuS: Positional Encoding Tri-Planes for Neural Surfaces

---

2023.05.17

8. LoRA: [2106.09685] LoRA: Low-Rank Adaptation of Large Language Models (arxiv.org)

LoRA: Low-Rank Adaptation of Large Language Models

---

9. SAM high quality: https://paperswithcode.com/paper/segment-anything-in-high-quality

Papers with Code - Segment Anything in High Quality

---

10. QLoRA:https://arxiv.org/abs/2305.14314

QLoRA: Efficient Finetuning of Quantized LLMs

---

11. LightGlue: https://paperswithcode.com/paper/lightglue-local-feature-matching-at-light

Papers with Code - LightGlue: Local Feature Matching at Light Speed

---

12. DragGAN: https://github.com/XingangPan/DragGAN 

GitHub - XingangPan/DragGAN: Official Code for DragGAN (SIGGRAPH 2023)

---

2023.08.05

13. SDXL: https://github.com/stability-ai/generative-models

GitHub - Stability-AI/generative-models: Generative Models by Stability AI

---

14. TAV: https://github.com/showlab/Tune-A-Video

GitHub - showlab/Tune-A-Video: [ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

15. CoDeF: https://paperswithcode.com/paper/codef-content-deformation-fields-for

Papers with Code - CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

---

16. TF-ICON: https://paperswithcode.com/paper/tf-icon-diffusion-based-training-free-cross

Papers with Code - TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition

---

17. Point-Bind & Point-LLM: https://arxiv.org/pdf/2309.00615.pdf

---

19. DEVA: https://paperswithcode.com/paper/tracking-anything-with-decoupled-video

Papers with Code - Tracking Anything with Decoupled Video Segmentation

20. Vote2Cap: https://github.com/ch3cook-fdu/vote2cap-detr

GitHub - ch3cook-fdu/Vote2Cap-DETR: Code release for ''End-to-End 3D Dense Captioning with Vote2Cap-DETR'' (CVPR2023)

---

21. InstaFlow: https://github.com/gnobitab/instaflow

GitHub - gnobitab/InstaFlow: :zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow

---

2023.10.02

22. DreamGaussian: https://paperswithcode.com/paper/dreamgaussian-generative-gaussian-splatting

Papers with Code - DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

23. Propainter: https://github.com/sczhou/propainter

GitHub - sczhou/ProPainter: [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

24. 3D gaussian splatting: https://arxiv.org/pdf/2308.04079.pdf

---

25. MetaClip: https://paperswithcode.com/paper/demystifying-clip-data

Papers with Code - Demystifying CLIP Data

---

26. From CLIP to DINO: https://paperswithcode.com/paper/from-clip-to-dino-visual-encoders-shout-in 

Papers with Code - From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

27. NEFTune: https://github.com/neelsjain/neftune 

GitHub - neelsjain/NEFTune: Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

---

28. Cutie: https://github.com/hkchengrex/Cutie

GitHub - hkchengrex/Cutie: [arXiv 2023] Putting the Object Back Into Video Object Segmentation

---

29. PALI: https://github.com/kyegomez/PALI3

GitHub - kyegomez/PALI3: Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"

30. Lion: https://github.com/lucidrains/lion-pytorch

GitHub - lucidrains/lion-pytorch: 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purported

---

31. Mustango: https://github.com/amaai-lab/mustango

GitHub - AMAAI-Lab/mustango: Mustango: Toward Controllable Text-to-Music Generation

---

32. OneLLM: https://paperswithcode.com/paper/onellm-one-framework-to-align-all-modalities 

Papers with Code - OneLLM: One Framework to Align All Modalities with Language

---

33. Alpha CLIP:https://github.com/sunzey/alphaclip

GitHub - SunzeY/AlphaCLIP: Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

---

34. Ferret(LMM): https://github.com/apple/ml-ferret

GitHub - apple/ml-ferret

---

35. DreamGaussian4D: https://github.com/jiawei-ren/dreamgaussian4d

GitHub - jiawei-ren/dreamgaussian4d: [arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

---

36. Affusion: https://github.com/happylittlecat2333/Auffusion

GitHub - happylittlecat2333/Auffusion: Official codes and models of the paper "Auffusion: Leveraging the Power of Diffusion and

---

37. InstantID: https://paperswithcode.com/paper/instantid-zero-shot-identity-preserving

Papers with Code - InstantID: Zero-shot Identity-Preserving Generation in Seconds

---

38. https://paperswithcode.com/paper/scalable-diffusion-models-with-state-space

Papers with Code - Scalable Diffusion Models with State Space Backbone

---

39. https://paperswithcode.com/paper/the-boundary-of-neural-network-trainability

Papers with Code - The boundary of neural network trainability is fractal

40. RoSA: https://github.com/ist-daslab/rosa?tab=readme-ov-file

GitHub - IST-DASLab/RoSA

---

41. VMamba: https://paperswithcode.com/paper/vmamba-visual-state-space-model

 

---

42. Latte: https://github.com/Vchitect/Latte

GitHub - Vchitect/Latte: Latte: Latent Diffusion Transformer for Video Generation.

---

43. SuGaR: https://github.com/Anttwo/SuGaR

GitHub - Anttwo/SuGaR: Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Recons

---

44. TripoSR: https://paperswithcode.com/paper/triposr-fast-3d-object-reconstruction-from-a

Papers with Code - TripoSR: Fast 3D Object Reconstruction from a Single Image

45. ViewDiff: https://github.com/facebookresearch/viewdiff?tab=readme-ov-file

GitHub - facebookresearch/ViewDiff: ViewDiff generates high-quality, multi-view consistent images of a real-world 3D object in a

---

46. InstantStyle: https://github.com/instantstyle/instantstyle

GitHub - InstantStyle/InstantStyle: InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

---

47. XCube: https://arxiv.org/pdf/2312.03806

 

48. https://github.com/hp-l33/aim (AiM)

---

49. https://github.com/huage001/linfusion?tab=readme-ov-file

GitHub - Huage001/LinFusion: Official PyTorch and Diffusers Implementation of "LinFusion: 1 GPU, 1 Minute, 16K Image"

50. KSID: https://github.com/axning/ksid

---

51. MambaST: https://github.com/FilippoBotti/MambaST

 

52. Direct3D: https://arxiv.org/abs/2405.14832

Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer

---

53. Intrinsic Image Decomposition: https://github.com/compphoto/Intrinsic

GitHub - compphoto/Intrinsic: Repo for the paper "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023)

---

54. https://github.com/pixtella/anagram-mtl

GitHub - Pixtella/Anagram-MTL: [WACV 2025] Official implementation for the paper "Diffusion-based Visual Anagram as Multi-task L

 

55. Divot: https://paperswithcode.com/paper/divot-diffusion-powers-video-tokenizer-for

Papers with Code - Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation