ML Research Hub
32.9K subscribers
5.48K photos
348 videos
24 files
5.93K 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
SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

📝 Summary:
Spectral-Evolution-Aware Cache (SeaCache) improves diffusion model inference speed by using spectrally aligned representations to optimize intermediate output reuse, achieving better latency-quality t...

🔹 Publication Date: Published on Feb 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18993
• PDF: https://arxiv.org/pdf/2602.18993
• Project Page: https://jiwoogit.github.io/SeaCache/
• Github: https://github.com/jiwoogit/SeaCache

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
VecGlypher: Unified Vector Glyph Generation with Language Models

📝 Summary:
VecGlypher is a multimodal language model that generates high-fidelity vector glyphs directly from text or images by emitting SVG path tokens. This bypasses raster processes, creating editable outlines in one pass. It outperforms prior methods, simplifying font design.

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.21461
• PDF: https://arxiv.org/pdf/2602.21461
• Project Page: https://xk-huang.github.io/VecGlypher/
• Github: https://github.com/xk-huang/VecGlypher

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

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

#VectorGraphics #LLM #FontDesign #GenerativeAI #AI
Limited Time Offer: Premium Q1 & Q2 Publications at Just $300!
🎓 Exclusive February Sale - Ending Soon!
Are you looking to boost your academic profile with high-impact publications? We're offering an exceptional opportunity you don't want to miss!
What We Offer:
Q1 & Q2 Journal Articles - Top-tier, indexed publications
Unbeatable Price: Only $300 per article
Limited Time: Offer valid until the end of February 2026
Why Choose Our Service?

Fast publication process
Reputable Q1 & Q2 journals
Expert support throughout
Guaranteed acceptance

Contact: @Omidyzd62
1
Functional Continuous Decomposition

📝 Summary:
Functional Continuous Decomposition FCD is a new framework for parametric, continuous optimization of time-series data. It extracts M modes capturing local and global patterns, improving feature extraction. FCD features enhance machine learning models, leading to faster convergence and higher acc...

🔹 Publication Date: Published on Feb 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.20857
• PDF: https://arxiv.org/pdf/2602.20857
• Project Page: https://arxiv.org/abs/2602.20857
• Github: https://github.com/Tima-a/fcd

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

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

#FCD #TimeSeries #Optimization #FeatureExtraction #MachineLearning
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

📝 Summary:
MolHIT presents a hierarchical discrete diffusion model for molecular graph generation. It achieves state-of-the-art performance with near-perfect chemical validity and strong property-guided synthesis, surpassing existing methods.

🔹 Publication Date: Published on Feb 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.17602
• PDF: https://arxiv.org/pdf/2602.17602

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

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

#MolHIT #MolecularGraphs #DiffusionModels #DrugDiscovery #Cheminformatics
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

📝 Summary:
DualPath addresses KV-cache I/O bottlenecks in LLM inference with dual-path loading. It loads KV-cache into decode engines, transfers it to prefill engines, and dynamically balances load to boost throughput up to 1.96 times.

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.21548
• PDF: https://arxiv.org/pdf/2602.21548

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

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

#LLM #AI #MachineLearning #PerformanceOptimization #SystemDesign
Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language

📝 Summary:
Yor-Sarc introduces the first gold-standard dataset for sarcasm detection in Yorùbá, a low-resource African language. It offers 436 expertly annotated instances with high inter-annotator agreement and soft labels, designed to advance NLP for African languages.

🔹 Publication Date: Published on Feb 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18964
• PDF: https://arxiv.org/pdf/2602.18964
• Project Page: https://arxiv.org/abs/2602.18964
• Github: https://github.com/toheebadura/yor-sarc

Datasets citing this paper:
https://huggingface.co/datasets/toheebadura/yor-sarc

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

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

#NLP #SarcasmDetection #Yoruba #LowResourceLanguages #AfricanLanguages
1
This media is not supported in your browser
VIEW IN TELEGRAM
SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

📝 Summary:
Spectral-Evolution-Aware Cache (SeaCache) improves diffusion model inference speed by using spectrally aligned representations to optimize intermediate output reuse, achieving better latency-quality t...

🔹 Publication Date: Published on Feb 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18993
• PDF: https://arxiv.org/pdf/2602.18993
• Project Page: https://jiwoogit.github.io/SeaCache/
• Github: https://github.com/jiwoogit/SeaCache

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
2
From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors

📝 Summary:
PhysicEdit addresses physically implausible image editing by modeling edits as predictive physical state transitions. It uses a dual-thinking diffusion framework guided by a vision-language model, greatly enhancing physical realism.

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.21778
• PDF: https://arxiv.org/pdf/2602.21778
• Project Page: https://liangbingzhao.github.io/statics2dynamics/
• Github: https://github.com/liangbingzhao/PhysicEdit

Datasets citing this paper:
https://huggingface.co/datasets/metazlb/PhysicTran38K

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

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

#ImageEditing #DiffusionModels #ComputerVision #PhysicsAI #AIResearch
DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction

📝 Summary:
DM4CT benchmarks diffusion models for CT reconstruction, tackling practical challenges like noise and artifacts. It evaluates ten diffusion methods against baselines on diverse real-world and synthetic CT datasets, offering detailed performance insights.

🔹 Publication Date: Published on Feb 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.18589
• PDF: https://arxiv.org/pdf/2602.18589
• Project Page: https://dm4ct.github.io/DM4CT/
• Github: https://github.com/DM4CT/DM4CT

🔹 Models citing this paper:
https://huggingface.co/jiayangshi/lodochallenge_pixel_diffusion
https://huggingface.co/jiayangshi/lodochallenge_latent_diffusion
https://huggingface.co/jiayangshi/lodoind_pixel_diffusion

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

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

#DiffusionModels #CTReconstruction #MedicalImaging #AIResearch #DeepLearning
1
ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads?

📝 Summary:
ISO-Bench evaluates coding agents on real-world LLM inference optimization tasks using combined execution and LLM metrics. Agents often identify bottlenecks but fail to execute working solutions, highlighting that scaffolding is as important as the model itself.

🔹 Publication Date: Published on Feb 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.19594
• PDF: https://arxiv.org/pdf/2602.19594

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

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

#CodingAgents #LLMOptimization #AIResearch #Benchmarking #LargeLanguageModels
1
The Truthfulness Spectrum Hypothesis

📝 Summary:
This paper proposes the truthfulness spectrum hypothesis: LLMs contain truth directions ranging from domain-general to domain-specific. While general directions exist, domain-specific ones steer more effectively, with post-training reshaping this geometry to influence behaviors like sycophancy.

🔹 Publication Date: Published on Feb 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.20273
• PDF: https://arxiv.org/pdf/2602.20273
• Github: https://github.com/zfying/truth_spec

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

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

#LLMs #AIResearch #AIAlignment #NLP #Truthfulness
1
Intent Laundering: AI Safety Datasets Are Not What They Seem

📝 Summary:
AI safety datasets overrely on unrealistic triggering cues. This paper introduces intent laundering to remove these cues, revealing that models previously deemed safe become vulnerable. This method also works as a powerful jailbreaking technique, exposing a critical flaw in current AI safety eval...

🔹 Publication Date: Published on Feb 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.16729
• PDF: https://arxiv.org/pdf/2602.16729

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

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

#AISafety #JailbreakingAI #LLMSecurity #AIDatasets #AIEvaluation
1
The Trinity of Consistency as a Defining Principle for General World Models

📝 Summary:
This paper proposes the Trinity of Consistency modal, spatial, temporal as a foundational theoretical framework for General World Models. It systematically reviews multimodal learning through this lens and introduces CoW-Bench, a new benchmark for evaluating current and future models.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23152
• PDF: https://arxiv.org/pdf/2602.23152
• Project Page: https://openraiser.github.io/CoW-Bench/
• Github: https://github.com/openraiser/awesome-world-model-evolution

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
OmniGAIA: Towards Native Omni-Modal AI Agents

📝 Summary:
OmniGAIA benchmark evaluates multi-modal agents on complex reasoning tasks across video, audio, and image modalities, while OmniAtlas agent improves tool-use capabilities through hindsight-guided tree...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22897
• PDF: https://arxiv.org/pdf/2602.22897
• Github: https://github.com/RUC-NLPIR/OmniGAIA

Datasets citing this paper:
https://huggingface.co/datasets/RUC-NLPIR/OmniGAIA
https://huggingface.co/datasets/RUC-NLPIR/Omnimodal-Agent-SFT-2K

Spaces citing this paper:
https://huggingface.co/spaces/RUC-NLPIR/OmniGAIA-Leaderboard

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving

📝 Summary:
A risk-aware framework for autonomous driving that uses world modeling and risk evaluation to generalize beyond expert demonstrations without requiring explicit expert supervision. AI-generated summar...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23259
• PDF: https://arxiv.org/pdf/2602.23259

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

📝 Summary:
DyaDiT is a multi-modal diffusion transformer that generates contextually appropriate human motion from dyadic audio signals by capturing interaction dynamics between two speakers. AI-generated summar...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23165
• PDF: https://arxiv.org/pdf/2602.23165

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
GeoWorld: Geometric World Models

📝 Summary:
GeoWorld addresses limitations in energy-based predictive world models by utilizing hyperbolic geometry to preserve latent state structures and improve long-horizon prediction performance. AI-generate...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23058
• PDF: https://arxiv.org/pdf/2602.23058
• Project Page: https://steve-zeyu-zhang.github.io/GeoWorld

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
veScale-FSDP: Flexible and High-Performance FSDP at Scale

📝 Summary:
veScale-FSDP introduces a redesigned fully sharded data parallel system with flexible sharding and structure-aware planning to improve scalability and efficiency for large-scale model training. AI-gen...

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22437
• PDF: https://arxiv.org/pdf/2602.22437
• Github: https://github.com/volcengine/veScale

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Imagination Helps Visual Reasoning, But Not Yet in Latent Space

📝 Summary:
Research reveals that latent visual reasoning in multimodal models suffers from input-latent and latent-answer disconnects, leading to the proposal of CapImagine, a text-based approach that outperform...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22766
• PDF: https://arxiv.org/pdf/2602.22766
• Github: https://github.com/Michael4933/CapImagine

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization

📝 Summary:
EMPO² is a hybrid reinforcement learning framework that enhances exploration for large language model agents by integrating memory mechanisms with on- and off-policy updates, demonstrating improved pe...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23008
• PDF: https://arxiv.org/pdf/2602.23008

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research