moonshotai/Kimi-K2.5
Image-Text-to-Text
•
171B
•
Updated
•
955k
•
•
2.26k
Yegor Sviridov
Rexschwert
AI & ML interests
AI, Big Data, Data Science, Machine Learning, Computer Vision, Natural Language Processing
Recent Activity
liked
a model
2 days ago
moonshotai/Kimi-K2.5
liked
a model
5 months ago
Qwen/Qwen3-VL-30B-A3B-Thinking
liked
a model
6 months ago
HuggingFaceTB/SmolVLM-256M-Instruct
Organizations
liked
a
model
2 days ago
liked
a
model
5 months ago
liked
a
model
6 months ago
reacted to
Kseniase's
post with 🔥❤️🚀👍
7 months ago
Post
5265
13 New types of LoRA
LoRA (Low-Rank Adaptation) is a popular lightweight method for fine-tuning AI models. It doesn't update the full model, it adds small trainable components, low-rank matrices, while keeping the original weights frozen. Only these adapters are trained.
Recently, many interesting new LoRA variations came out, so it’s a great time to take a look at these 13 clever approaches:
1. T-LoRA → T-LoRA: Single Image Diffusion Model Customization Without Overfitting (2507.05964)
A timestep-dependent LoRA method for adapting diffusion models with a single image. It dynamically adjusts updates and uses orthogonal initialization to reduce overlap, achieving better fidelity–alignment balance than standard LoRA
2. SingLoRA → SingLoRA: Low Rank Adaptation Using a Single Matrix (2507.05566)
Simplifies LoRA by using only one small matrix instead of usual two, and multiplying it by its own transpose (like A × Aᵀ). It uses half the parameters of LoRA and avoids scale mismatch between different matrices
3. LiON-LoRA → LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion (2507.05678)
Improves control and precision in video diffusion models when training data is limited. It builds on LoRA, adding 3 key principles: linear scalability, orthogonality, and norm consistency. A controllable token and modified self-attention enables smooth adjustment of motion
4. LoRA-Mixer → LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing (2507.00029)
Combines LoRA and mixture-of-experts (MoE) to adapt LLMs for multiple tasks. It dynamically routes task-specific LoRA experts into linear projections of attention modules, supporting both joint training and frozen expert reuse
5. QR-LoRA → QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation (2507.04599)
Separates content and style when combining multiple LoRA adapters. It implements QR decomposition to structure parameter updates, where the orthogonal Q matrix reduces interference between features, and the R matrix captures specific transformations
Read further in the comments 👇
If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
LoRA (Low-Rank Adaptation) is a popular lightweight method for fine-tuning AI models. It doesn't update the full model, it adds small trainable components, low-rank matrices, while keeping the original weights frozen. Only these adapters are trained.
Recently, many interesting new LoRA variations came out, so it’s a great time to take a look at these 13 clever approaches:
1. T-LoRA → T-LoRA: Single Image Diffusion Model Customization Without Overfitting (2507.05964)
A timestep-dependent LoRA method for adapting diffusion models with a single image. It dynamically adjusts updates and uses orthogonal initialization to reduce overlap, achieving better fidelity–alignment balance than standard LoRA
2. SingLoRA → SingLoRA: Low Rank Adaptation Using a Single Matrix (2507.05566)
Simplifies LoRA by using only one small matrix instead of usual two, and multiplying it by its own transpose (like A × Aᵀ). It uses half the parameters of LoRA and avoids scale mismatch between different matrices
3. LiON-LoRA → LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion (2507.05678)
Improves control and precision in video diffusion models when training data is limited. It builds on LoRA, adding 3 key principles: linear scalability, orthogonality, and norm consistency. A controllable token and modified self-attention enables smooth adjustment of motion
4. LoRA-Mixer → LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing (2507.00029)
Combines LoRA and mixture-of-experts (MoE) to adapt LLMs for multiple tasks. It dynamically routes task-specific LoRA experts into linear projections of attention modules, supporting both joint training and frozen expert reuse
5. QR-LoRA → QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation (2507.04599)
Separates content and style when combining multiple LoRA adapters. It implements QR decomposition to structure parameter updates, where the orthogonal Q matrix reduces interference between features, and the R matrix captures specific transformations
Read further in the comments 👇
If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
- 1 reply
liked
a
Space
8 months ago
liked
a
model
9 months ago
upvoted
an
article
10 months ago
Article
How to Build an MCP Server with Gradio
•
202
liked
a
model
10 months ago
liked
a
dataset
10 months ago
liked
a
model
10 months ago
liked
a
dataset
10 months ago
published
a
model
10 months ago
reacted to
nyuuzyou's
post with 🔥👍
10 months ago
Post
5659
🇷🇺 Russian Forum Messages Dataset -
nyuuzyou/ruforum
Collection of approximately 58 million Russian forum messages featuring:
- Complete message content from Russian online forums spanning 2010-2025
- Comprehensive metadata including unique message IDs and timestamps
- Full text content preserving original user discussions and interactions
- Monolingual dataset focused exclusively on Russian language content
This dataset offers a unique textual archive of Russian online conversations suitable for text generation, sentiment analysis, and language modeling research. Released to the public domain under CC0 1.0 license.
Collection of approximately 58 million Russian forum messages featuring:
- Complete message content from Russian online forums spanning 2010-2025
- Comprehensive metadata including unique message IDs and timestamps
- Full text content preserving original user discussions and interactions
- Monolingual dataset focused exclusively on Russian language content
This dataset offers a unique textual archive of Russian online conversations suitable for text generation, sentiment analysis, and language modeling research. Released to the public domain under CC0 1.0 license.
liked
3
models
11 months ago
