ML Research Hub
32.8K subscribers
4.37K photos
269 videos
23 files
4.73K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
ReHyAt: Recurrent Hybrid Attention for Video Diffusion Transformers

📝 Summary:
ReHyAt presents a recurrent hybrid attention mechanism, merging softmax fidelity with linear efficiency. This enables scalable, high-quality video generation by reducing computational cost from quadratic to linear, with significantly lower training costs.

🔹 Publication Date: Published on Jan 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04342
• PDF: https://arxiv.org/pdf/2601.04342
• Project Page: https://qualcomm-ai-research.github.io/rehyat

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views

📝 Summary:
HairGuard is a framework for recovering fine-grained soft boundary details in 3D vision tasks through specialized depth refinement and view synthesis techniques. AI-generated summary Soft boundaries, ...

🔹 Publication Date: Published on Jan 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.03362
• PDF: https://arxiv.org/pdf/2601.03362

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Towards Open-Vocabulary Industrial Defect Understanding with a Large-Scale Multimodal Dataset

📝 Summary:
A large-scale industrial multimodal defect dataset with 1 million image-text pairs enables efficient foundation model adaptation for manufacturing quality inspection and generation tasks. AI-generated...

🔹 Publication Date: Published on Dec 30, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.24160
• PDF: https://arxiv.org/pdf/2512.24160
• Project Page: https://ninaneon.github.io/projectpage/
• Github: https://github.com/NinaNeon/IMDD-1M-Towards-Open-Vocabulary-Industrial-Defect-

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Memorization in 3D Shape Generation: An Empirical Study

📝 Summary:
Researchers develop a framework to measure memorization in 3D generative models and identify factors affecting it, finding that data modality and model design parameters influence how much training da...

🔹 Publication Date: Published on Dec 29, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.23628
• PDF: https://arxiv.org/pdf/2512.23628
• Github: https://github.com/zlab-princeton/3d-gen-mem

🔹 Models citing this paper:
https://huggingface.co/pudashi/3DGenMem

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering

📝 Summary:
AgentDevel presents a release engineering approach for large language model agents that treats them as shippable artifacts and emphasizes stable, auditable improvements through externalized testing an...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04620
• PDF: https://arxiv.org/pdf/2601.04620
• Project Page: https://trotsky1997.github.io/agentdevel-dashboard/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Beyond Binary Preference: Aligning Diffusion Models to Fine-grained Criteria by Decoupling Attributes

📝 Summary:
A two-stage framework for diffusion model alignment using hierarchical evaluation criteria and complex preference optimization demonstrates improved generation quality and expert alignment. AI-generat...

🔹 Publication Date: Published on Jan 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04300
• PDF: https://arxiv.org/pdf/2601.04300

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Learning User Preferences Through Interaction for Long-Term Collaboration

📝 Summary:
MultiSessionCollab benchmark evaluates agents' ability to learn and adapt to user preferences through persistent memory systems that enhance long-term collaboration quality. AI-generated summary As co...

🔹 Publication Date: Published on Jan 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02702
• PDF: https://arxiv.org/pdf/2601.02702

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach

📝 Summary:
Learning Using Privileged Information paradigm enhances object detection accuracy by integrating additional training-time information through teacher-student architectures without increasing inference...

🔹 Publication Date: Published on Jan 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02016
• PDF: https://arxiv.org/pdf/2601.02016
• Github: https://github.com/mbar0075/lupi-for-object-detection

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
LEMAS: Large A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models

📝 Summary:
The LEMAS-Dataset enables high-quality multilingual speech synthesis and editing through specialized models leveraging flow-matching and autoregressive architectures with novel training techniques. AI...

🔹 Publication Date: Published on Jan 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04233
• PDF: https://arxiv.org/pdf/2601.04233
• Project Page: https://huggingface.co/spaces/LEMAS-Project/LEMAS-Edit

🔹 Models citing this paper:
https://huggingface.co/LEMAS-Project/LEMAS-TTS
https://huggingface.co/LEMAS-Project/LEMAS-Edit

Datasets citing this paper:
https://huggingface.co/datasets/LEMAS-Project/LEMAS-Dataset-train
https://huggingface.co/datasets/LEMAS-Project/LEMAS-Dataset-eval

Spaces citing this paper:
https://huggingface.co/spaces/LEMAS-Project/LEMAS-TTS
https://huggingface.co/spaces/LEMAS-Project/LEMAS-Edit
https://huggingface.co/spaces/Kaiden423/LEMAS-TTS

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
VERSE: Visual Embedding Reduction and Space Exploration. Clustering-Guided Insights for Training Data Enhancement in Visually-Rich Document Understanding

📝 Summary:
VERSE is a methodology for analyzing and improving Vision-Language Models in document understanding by visualizing latent representations and generating synthetic data to enhance performance in error-...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05125
• PDF: https://arxiv.org/pdf/2601.05125
• Project Page: https://huggingface.co/spaces/de-Rodrigo/Embeddings
• Github: https://github.com/nachoDRT/VrDU-Doctor

Datasets citing this paper:
https://huggingface.co/datasets/de-Rodrigo/merit

Spaces citing this paper:
https://huggingface.co/spaces/de-Rodrigo/Embeddings
https://huggingface.co/spaces/de-Rodrigo/saliencies

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance

📝 Summary:
Safety alignment of large language models can be fully recovered with a single safety example, maintaining utility and achieving convergence in few epochs through identified low-rank gradient structur...

🔹 Publication Date: Published on Jan 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.01887
• PDF: https://arxiv.org/pdf/2601.01887

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

📝 Summary:
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale up model size or co...

🔹 Publication Date: Published on Nov 14, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/mirothinker-pushing-the-performance-boundaries-of-open-source-research-agents-via-model-context-and-interactive-scaling-9611-0f2289e7
• PDF: https://arxiv.org/pdf/2511.11793
• Project Page: https://dr.miromind.ai/
• Github: https://github.com/MiroMindAI/MiroThinker

🔹 Models citing this paper:
https://huggingface.co/miromind-ai/MiroThinker-v1.5-235B
https://huggingface.co/miromind-ai/MiroThinker-v1.5-30B
https://huggingface.co/miromind-ai/MiroThinker-v1.0-72B

Datasets citing this paper:
https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1

Spaces citing this paper:
https://huggingface.co/spaces/zoom-ai/hle-leaderboard
https://huggingface.co/spaces/miromind-ai/MiroMind-Open-Source-Deep-Research

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
LTX-2: Efficient Joint Audio-Visual Foundation Model

📝 Summary:
LTX-2 is an open-source audiovisual diffusion model that generates synchronized video and audio content using a dual-stream transformer architecture with cross-modal attention and classifier-free guid...

🔹 Publication Date: Published on Jan 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.03233
• PDF: https://arxiv.org/pdf/2601.03233
• Project Page: https://huggingface.co/papers/2511.12072
• Github: https://github.com/Lightricks/LTX-2

🔹 Models citing this paper:
https://huggingface.co/Lightricks/LTX-2
https://huggingface.co/unsloth/LTX-2-GGUF
https://huggingface.co/Lightricks/LTX-2-19b-IC-LoRA-Canny-Control

Spaces citing this paper:
https://huggingface.co/spaces/Lightricks/ltx-2-distilled
https://huggingface.co/spaces/Lightricks/ltx-2
https://huggingface.co/spaces/alexnasa/ltx-2-TURBO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
SimpleMem: Efficient Lifelong Memory for LLM Agents

📝 Summary:
To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction ...

🔹 Publication Date: Published on Jan 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02553
• PDF: https://arxiv.org/pdf/2601.02553
• Project Page: https://aiming-lab.github.io/SimpleMem-Page/
• Github: https://aiming-lab.github.io/SimpleMem-Page/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

📝 Summary:
SmolDocling is a compact vision-language model that performs end-to-end document conversion with robust performance across various document types using 256M parameters and a new markup format. AI-gene...

🔹 Publication Date: Published on Mar 14, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2503.11576
• PDF: https://huggingface.co/papers/2502.18443
• Project Page: https://huggingface.co/spaces/docling-project/SmolDocling-256M-Demo
• Github: https://github.com/docling-project/docling

🔹 Models citing this paper:
https://huggingface.co/docling-project/SmolDocling-256M-preview
https://huggingface.co/ibm-granite/granite-docling-258M
https://huggingface.co/prithivMLmods/granite-docling-258M-f32-GGUF

Datasets citing this paper:
https://huggingface.co/datasets/HuggingFaceM4/DoclingMatix
https://huggingface.co/datasets/docling-project/SynthCodeNet
https://huggingface.co/datasets/docling-project/SynthFormulaNet

Spaces citing this paper:
https://huggingface.co/spaces/ibm-granite/granite-docling-258m-demo
https://huggingface.co/spaces/ibm-granite/granite-docling-258M-WebGPU
https://huggingface.co/spaces/docling-project/SmolDocling-256M-Demo

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

📝 Summary:
VideoRAG enhances large language models for multi-modal video processing with a dual-channel architecture that integrates textual knowledge grounding and multi-modal context encoding. AI-generated sum...

🔹 Publication Date: Published on Feb 3, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.01549
• PDF: https://arxiv.org/pdf/2502.01549
• Github: https://github.com/hkuds/videorag

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Agent READMEs: An Empirical Study of Context Files for Agentic Coding

📝 Summary:
Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this proc...

🔹 Publication Date: Published on Nov 17, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.12884
• PDF: https://arxiv.org/pdf/2511.12884
• Project Page: https://huggingface.co/papers/2511.03404
• Github: https://github.com/openai/agents.md

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research