✨GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

📝 Summary:
GUI-Libra addresses limitations in open-source GUI agents through specialized training methods that improve reasoning-grounding alignment and reinforcement learning under partial verifiability, demons...

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22190
• PDF: https://arxiv.org/pdf/2602.22190
• Project Page: https://gui-libra.github.io
• Github: https://github.com/GUI-Libra/GUI-Libra

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors

📝 Summary:
Object hallucinations in LVLMs are primarily caused by language decoder priors, leading to the development of a training-free framework that suppresses these priors to reduce hallucinations. AI-genera...

🔹 Publication Date: Published on Feb 25

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22144
• PDF: https://arxiv.org/pdf/2602.22144
• Github: https://github.com/lingfengren/NoLan

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment

📝 Summary:
MoBind learns joint representations between IMU signals and 2D pose sequences through hierarchical contrastive learning to achieve cross-modal retrieval, temporal synchronization, and action recogniti...

🔹 Publication Date: Published on Feb 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.19004
• PDF: https://arxiv.org/pdf/2602.19004
• Github: https://github.com/bbvisual/MoBind

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨NanoKnow: How to Know What Your Language Model Knows

📝 Summary:
NanoKnow is a benchmark using open pre-training data to analyze how LLMs acquire knowledge. It shows accuracy relies on pre-training frequency, which external evidence can mitigate, and that parametric and external knowledge are complementary, but irrelevant data is harmful.

🔹 Publication Date: Published on Feb 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.20122
• PDF: https://arxiv.org/pdf/2602.20122
• Github: https://github.com/castorini/NanoKnow/tree/main

✨ Datasets citing this paper:
• https://huggingface.co/datasets/LingweiGu/NanoKnow-Fineweb-Edu-Index
• https://huggingface.co/datasets/LingweiGu/NanoKnow_Benchmark

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Image Generation with a Sphere Encoder

📝 Summary:
The Sphere Encoder is an efficient generative model that maps images to a spherical latent space. It produces high-quality images in a single pass, matching diffusion models at a fraction of the inference cost.

🔹 Publication Date: Published on Feb 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.15030
• PDF: https://arxiv.org/pdf/2602.15030
• Project Page: https://sphere-encoder.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨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

✨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

✨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

✨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

✨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