ML Research Hub
32.3K subscribers
6.46K photos
441 videos
24 files
7.02K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents

📝 Summary:
A multi-agent system using uncertainty-aware design improves LLM agent performance on underspecified software development tasks by detecting ambiguity and proactively seeking clarification. AI-generat...

🔹 Publication Date: Published on Mar 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.26233
• PDF: https://arxiv.org/pdf/2603.26233
• Github: https://github.com/nedwards99/ask-or-assume

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning

📝 Summary:
Brainstacks enables continual multi-domain fine-tuning of large language models through modular adapter stacks with MoE-LoRA, residual boosting, and outcome-based routing that discovers transferable c...

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01152
• PDF: https://arxiv.org/pdf/2604.01152
• Project Page: https://huggingface.co/papers?q=null-space%20projection
• Github: https://github.com/achelousace/brainstacks

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

For more data science resources:
https://t.iss.one/DataScienceT

#LLM #ContinualLearning #MoELoRA #DeepLearning #AIResearch
ActionParty: Multi-Subject Action Binding in Generative Video Games

📝 Summary:
ActionParty solves the multi-agent control problem in video diffusion models. It introduces subject state tokens to disentangle global video rendering from individual action control. This allows simultaneous control of up to seven players across diverse environments, improving action following an...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02330
• PDF: https://arxiv.org/pdf/2604.02330
• Project Page: https://action-party.github.io/
• Github: https://action-party.github.io/

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
2
Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models

📝 Summary:
This work analyzes Late Interaction models, showing a length bias in multi-vector scoring for causal and sometimes bi-directional models. It also confirms MaxSim efficiently exploits token-level similarity, with no significant trends beyond the top token.

🔹 Publication Date: Published on Mar 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.26259
• PDF: https://arxiv.org/pdf/2603.26259

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

For more data science resources:
https://t.iss.one/DataScienceT

#LateInteraction #InformationRetrieval #ModelAnalysis #AlgorithmBias #SimilaritySearch
NearID: Identity Representation Learning via Near-identity Distractors

📝 Summary:
Researchers developed a novel framework using Near-identity distractors to improve identity-focused vision tasks by creating a dataset and evaluation protocol that better isolates identity from backgr...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01973
• PDF: https://arxiv.org/pdf/2604.01973
• Project Page: https://gorluxor.github.io/NearID/
• Github: https://github.com/Gorluxor/NearID

Datasets citing this paper:
https://huggingface.co/datasets/Aleksandar/NearID
https://huggingface.co/datasets/Aleksandar/NearID-Flux
https://huggingface.co/datasets/Aleksandar/NearID-FluxC

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Therefore I am. I Think

📝 Summary:
Large language models often make action choices before generating any reasoning text. Evidence shows early decision signals can be decoded and causally steered, with the subsequent 'thinking' rationalizing the pre-made choice. This suggests decisions precede explicit deliberation.

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01202
• PDF: https://arxiv.org/pdf/2604.01202

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines

📝 Summary:
Video world models with explicit external memory enable user-controlled environment editing and real-time multiplayer interactions by decomposing generation into memory, observation, and dynamics modu...

🔹 Publication Date: Published on Mar 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.06679
• PDF: https://arxiv.org/pdf/2603.06679

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Forecasting Supply Chain Disruptions with Foresight Learning

📝 Summary:
Large language models can be trained to produce calibrated probabilistic forecasts for supply chain disruptions, outperforming existing baselines and enabling decision-ready predictions through domain...

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01298
• PDF: https://arxiv.org/pdf/2604.01298
• Project Page: https://lightningrod.ai

Datasets citing this paper:
https://huggingface.co/datasets/LightningRodLabs/supply-chain-predictions

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery

📝 Summary:
Autonomous multi-agent evolution framework enables open-ended discovery through persistent memory, asynchronous execution, and collaborative problem-solving, achieving superior performance on mathemat...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01658
• PDF: https://arxiv.org/pdf/2604.01658
• Project Page: https://human-agent-society.github.io/CORAL
• Github: https://github.com/Human-Agent-Society/CORAL

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

📝 Summary:
Video diffusion models demonstrate emergent reasoning abilities in maze solving through early plan commitment and path length prediction, with improved performance achieved via Chaining with Early Pla...

🔹 Publication Date: Published on Mar 31

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.30043
• PDF: https://arxiv.org/pdf/2603.30043
• Project Page: https://video-maze-reasoning.github.io/

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
1
An Empirical Recipe for Universal Phone Recognition

📝 Summary:
PhoneticXEUS achieves leading performance for universal phone recognition in multilingual and accented speech. This results from large-scale training and an empirical analysis of key factors including SSL representations, data scale, and loss objectives.

🔹 Publication Date: Published on Mar 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.29042
• PDF: https://arxiv.org/pdf/2603.29042
• Github: https://github.com/changelinglab/PhoneticXeus

🔹 Models citing this paper:
https://huggingface.co/changelinglab/PhoneticXeus

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
Signals: Trajectory Sampling and Triage for Agentic Interactions

📝 Summary:
A signal framework efficiently triages agentic interaction trajectories. It computes low-cost signals from live interactions to identify informative samples for post-deployment optimization, achieving 82% informativeness and outperforming other methods.

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00356
• PDF: https://arxiv.org/pdf/2604.00356
• Project Page: https://planoai.dev/
• Github: https://github.com/katanemo/plano

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
This media is not supported in your browser
VIEW IN TELEGRAM
DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively

📝 Summary:
DeepScientist autonomously conducts scientific discovery through Bayesian Optimization, surpassing human state-of-the-art methods on multiple AI tasks. AI-generated summary While previous AI Scientist...

🔹 Publication Date: Published on Sep 30, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.26603
• PDF: https://arxiv.org/pdf/2509.26603
• Project Page: https://ai-researcher.net
• Github: https://github.com/ResearAI/DeepScientist

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model

📝 Summary:
LOME is an egocentric world model that generates realistic human-object interactions in videos by combining image, text, and action inputs with joint estimation of spatial human actions and environmen...

🔹 Publication Date: Published on Mar 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27449
• PDF: https://arxiv.org/pdf/2603.27449
• Project Page: https://zerg-overmind.github.io/LOME.github.io/
• Github: https://github.com/Zerg-Overmind/LOME

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

For more data science resources:
https://t.iss.one/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research
1
🔥2026 New IT Certification Prep Kit – Free!

SPOTO cover: #Python #AI #Cisco #PMI #Fortinet #AWS #Azure #Excel #CompTIA #ITIL #Cloud + more

Grab yours free kit now:
• Free Courses (Python, Excel, Cyber Security, Cisco, SQL, ITIL, PMP, AWS)
👉 https://bit.ly/3Ogtn3i
• IT Certs E-book
👉 https://bit.ly/41KZlru
• IT Exams Skill Test
👉 https://bit.ly/4ve6ZbC
• Free AI Materials & Support Tools
👉 https://bit.ly/4vagTuw
• Free Cloud Study Guide
👉 https://bit.ly/4c3BZCh

💬 Need exam help? Contact admin: wa.link/w6cems

Join our IT community: get free study materials, exam tips & peer support
https://chat.whatsapp.com/BiazIVo5RxfKENBv10F444
1
Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

📝 Summary:
This tutorial introduces Hunyuan3D 2.1, a system for generating high-fidelity, textured 3D assets to make AI content creation more accessible. It details the full workflow from data preparation to deployment, using Hunyuan3D-DiT for shape and Hunyuan3D-Paint for texture synthesis.

🔹 Publication Date: Published on Jun 18, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2506.15442
• PDF: https://arxiv.org/pdf/2506.15442
• Github: https://github.com/huggingface/huggingface.js

🔹 Models citing this paper:
https://huggingface.co/tencent/Hunyuan3D-2.1
https://huggingface.co/tencent/Hunyuan3D-Omni
https://huggingface.co/tencent/HY3D-Bench

Datasets citing this paper:
https://huggingface.co/datasets/tencent/HY3D-Bench

Spaces citing this paper:
https://huggingface.co/spaces/duranponce/ai-default
https://huggingface.co/spaces/AliothTalks/Hunyuan3D-2.1
https://huggingface.co/spaces/joaojack/Hunyuan3D-2.1

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

For more data science resources:
https://t.iss.one/DataScienceT

#3DGeneration #AI #ComputerGraphics #ImageTo3D #PBRMaterials
1
Follow the Machine Learning with Python channel on WhatsApp: https://whatsapp.com/channel/0029VaC7Weq29753hpcggW2A
1