ML Research Hub
32.8K subscribers
4.32K photos
263 videos
23 files
4.66K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
This media is not supported in your browser
VIEW IN TELEGRAM
DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer

📝 Summary:
A novel video face swapping framework combines image face swapping techniques with diffusion transformers and curriculum learning to achieve superior identity preservation and visual realism. AI-gener...

🔹 Publication Date: Published on Jan 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.01425
• PDF: https://arxiv.org/pdf/2601.01425
• Project Page: https://guoxu1233.github.io/DreamID-V/
• Github: https://guoxu1233.github.io/DreamID-V/

🔹 Models citing this paper:
https://huggingface.co/XuGuo699/DreamID-V

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Self-Supervised Prompt Optimization

📝 Summary:
A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data. AI-generated summary Well-de...

🔹 Publication Date: Published on Feb 7, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.06855
• PDF: https://arxiv.org/pdf/2502.06855
• Github: https://github.com/geekan/metagpt

Spaces citing this paper:
https://huggingface.co/spaces/XiangJinYu/SPO
https://huggingface.co/spaces/tang-x/SPO
https://huggingface.co/spaces/ositamiles/SPO

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Recursive Language Models

📝 Summary:
We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy...

🔹 Publication Date: Published on Dec 31, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/recursive-language-models-6610-16b3d94b
• PDF: https://arxiv.org/pdf/2512.24601
• Project Page: https://alexzhang13.github.io/blog/2025/rlm/
• Github: https://github.com/alexzhang13/rlm/tree/main

Spaces citing this paper:
https://huggingface.co/spaces/sergiopaniego/repl

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

📝 Summary:
Youtu-LLM is a lightweight language model optimized for computational efficiency and agentic intelligence through a compact architecture, STEM-focused training curriculum, and scalable mid-training st...

🔹 Publication Date: Published on Dec 31, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/youtu-llm-unlocking-the-native-agentic-potential-for-lightweight-large-language-models-8640-ff62768a
• PDF: https://arxiv.org/pdf/2512.24618
• Project Page: https://youtu-tip.com/#llm
• Github: https://github.com/TencentCloudADP/youtu-tip

🔹 Models citing this paper:
https://huggingface.co/tencent/Youtu-LLM-2B
https://huggingface.co/tencent/Youtu-LLM-2B-Base
https://huggingface.co/tencent/Youtu-LLM-2B-GGUF

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Media is too big
VIEW IN TELEGRAM
NitroGen: An Open Foundation Model for Generalist Gaming Agents

📝 Summary:
NitroGen is a vision-action foundation model trained on extensive gameplay data that demonstrates strong cross-game generalization and effective transfer learning capabilities. AI-generated summary We...

🔹 Publication Date: Published on Jan 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02427
• PDF: https://arxiv.org/pdf/2601.02427
• Project Page: https://nitrogen.minedojo.org/
• Github: https://github.com/MineDojo/NitroGen

🔹 Models citing this paper:
https://huggingface.co/nvidia/NitroGen

Datasets citing this paper:
https://huggingface.co/datasets/nvidia/NitroGen

Spaces citing this paper:
https://huggingface.co/spaces/dennny123/NitroGen-SuperstarSaga
https://huggingface.co/spaces/blanchon/NitroGen-Pokemon

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

📝 Summary:
Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming exi...

🔹 Publication Date: Published on Apr 28, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.19413
• PDF: https://arxiv.org/pdf/2504.19413
• Github: https://github.com/mem0ai/mem0

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

📝 Summary:
The study reveals that in text-to-image generation, CFG Augmentation is the primary driver of few-step distillation in Distribution Matching Distillation (DMD), while the distribution matching term ac...

🔹 Publication Date: Published on Nov 27, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.22677
• PDF: https://arxiv.org/pdf/2511.22677
• Project Page: https://tongyi-mai.github.io/Z-Image-blog/
• Github: https://github.com/Tongyi-MAI/Z-Image/tree/main

🔹 Models citing this paper:
https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
https://huggingface.co/unsloth/Z-Image-Turbo-GGUF
https://huggingface.co/tsqn/Z-Image-Turbo_fp32-fp16-bf16_full_and_ema-only

Spaces citing this paper:
https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo
https://huggingface.co/spaces/mrfakename/Z-Image-Turbo
https://huggingface.co/spaces/linoyts/open-image-generation

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

📝 Summary:
Z-Image, a 6B-parameter Scalable Single-Stream Diffusion Transformer (S3-DiT) model, achieves high-performance image generation with reduced computational cost, offering sub-second inference and compa...

🔹 Publication Date: Published on Nov 27, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/z-image-an-efficient-image-generation-foundation-model-with-single-stream-diffusion-transformer-9846-b5faf99f
• PDF: https://arxiv.org/pdf/2511.22699
• Project Page: https://tongyi-mai.github.io/Z-Image-blog/
• Github: https://github.com/Tongyi-MAI/Z-Image

🔹 Models citing this paper:
https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
https://huggingface.co/unsloth/Z-Image-Turbo-GGUF
https://huggingface.co/tsqn/Z-Image-Turbo_fp32-fp16-bf16_full_and_ema-only

Spaces citing this paper:
https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo
https://huggingface.co/spaces/mrfakename/Z-Image-Turbo
https://huggingface.co/spaces/linoyts/open-image-generation

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
DeepCode: Open Agentic Coding

📝 Summary:
DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, ...

🔹 Publication Date: Published on Dec 8, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.07921
• PDF: https://arxiv.org/pdf/2512.07921
• Project Page: https://huggingface.co/papers/2511.03404
• Github: https://github.com/HKUDS/DeepCode

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Sharp Monocular View Synthesis in Less Than a Second

📝 Summary:
SHARP synthesizes photorealistic views from a single image using a 3D Gaussian representation, achieving state-of-the-art results with rapid processing. AI-generated summary We present SHARP, an appro...

🔹 Publication Date: Published on Dec 11, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.10685
• PDF: https://arxiv.org/pdf/2512.10685
• Project Page: https://apple.github.io/ml-sharp/
• Github: https://github.com/apple/ml-sharp

🔹 Models citing this paper:
https://huggingface.co/apple/Sharp
https://huggingface.co/agg23/Sharp-mlx-f16
https://huggingface.co/pearsonkyle/Sharp-coreml

Spaces citing this paper:
https://huggingface.co/spaces/ronedgecomb/ml-sharp
https://huggingface.co/spaces/Cristthomas/ml-sharp
https://huggingface.co/spaces/alibhji/ml-sharp

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

📝 Summary:
IndexTTS, an enhanced text-to-speech system combining XTTS and Tortoise models, offers improved naturalness, enhanced voice cloning, and controllable usage through hybrid character-pinyin modeling and...

🔹 Publication Date: Published on Feb 8, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.05512
• PDF: https://arxiv.org/pdf/2502.05512
• Project Page: https://index-tts.github.io
• Github: https://github.com/index-tts/index-tts

🔹 Models citing this paper:
https://huggingface.co/IndexTeam/IndexTTS-2
https://huggingface.co/IndexTeam/Index-TTS
https://huggingface.co/Toxzic/indextts-colab

Spaces citing this paper:
https://huggingface.co/spaces/Mo2294/MoTTS
https://huggingface.co/spaces/shawange/MoTTS
https://huggingface.co/spaces/shawange/MoTTS-CPU

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

📝 Summary:
OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks. AI...

🔹 Publication Date: Published on Jul 23, 2024

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2407.16741
• PDF: https://arxiv.org/pdf/2407.16741
• Github: https://github.com/OpenDevin/OpenDevin/?tab=readme-ov-file#-join-our-community

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams

📝 Summary:
InfiniteVGGT enables continuous 3D visual geometry understanding through a causal transformer with adaptive memory management, outperforming existing streaming methods in long-term stability while int...

🔹 Publication Date: Published on Jan 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02281
• PDF: https://arxiv.org/pdf/2601.02281
• Github: https://github.com/AutoLab-SAI-SJTU/InfiniteVGGT

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

📝 Summary:
NextFlow is a unified decoder-only autoregressive transformer that processes interleaved text-image tokens, enabling fast multimodal generation through novel next-token and next-scale prediction strat...

🔹 Publication Date: Published on Jan 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02204
• PDF: https://arxiv.org/pdf/2601.02204
• Github: https://github.com/ByteVisionLab/NextFlow

Datasets citing this paper:
https://huggingface.co/datasets/madebyollin/megalith-10m

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Zep: A Temporal Knowledge Graph Architecture for Agent Memory

📝 Summary:
Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases. AI-generat...

🔹 Publication Date: Published on Jan 20, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2501.13956
• PDF: https://arxiv.org/pdf/2501.13956
• Github: https://github.com/getzep/graphiti

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

📝 Summary:
DataFlow is an LLM-driven data preparation framework that enhances data quality and reproducibility for various tasks, improving LLM performance with automatically generated pipelines. AI-generated su...

🔹 Publication Date: Published on Dec 18, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/dataflow-an-llm-driven-framework-for-unified-data-preparation-and-workflow-automation-in-the-era-of-data-centric-ai-3906-5f097fd0
• PDF: https://arxiv.org/pdf/2512.16676
• Project Page: https://github.com/OpenDCAI/DataFlow
• Github: https://github.com/OpenDCAI/DataFlow

Datasets citing this paper:
https://huggingface.co/datasets/OpenDCAI/dataflow-demo-Text2SQL
https://huggingface.co/datasets/OpenDCAI/dataflow-instruct-10k
https://huggingface.co/datasets/OpenDCAI/dataflow-demo-Reasoning

==================================

For more data science resources:
https://t.me/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research