✨AI Generalisation Gap In Comorbid Sleep Disorder Staging

📝 Summary:
AI sleep staging models trained on healthy subjects perform poorly on stroke patients due to fundamental differences in sleep architecture. This necessitates disease-specific approaches. The paper introduces iSLEEPS, a new stroke dataset, to confirm this generalization gap and highlights the need...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23582
• PDF: https://arxiv.org/pdf/2603.23582
• Project Page: https://himalayansaswatabose.github.io/iSLEEPS_Explainability.github.io/
• Github: https://github.com/HimalayanSaswataBose/iSLEEPS_GeneralisationGapAndExplainability

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

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

#AIGeneralization #SleepStaging #StrokeResearch #MedicalAI #MachineLearning

✨Brevity Constraints Reverse Performance Hierarchies in Language Models

📝 Summary:
Large language models can underperform smaller ones due to verbose responses that introduce errors. Constraining output length reveals their superior latent capabilities, reversing performance hierarchies. This demands scale-aware prompt engineering for optimal performance.

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00025
• PDF: https://arxiv.org/pdf/2604.00025
• Github: https://github.com/logicsame/Brevity-Constraints-Reverse-Performance-Hierarchies-in-Language-Models

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

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

#LLM #PromptEngineering #AI #MachineLearning #NLP

✨Do Phone-Use Agents Respect Your Privacy?

📝 Summary:
This paper introduces MyPhoneBench, a framework to evaluate phone agents' privacy behavior. It found agents often over-share optional data, indicating current success metrics overestimate their deployment readiness due to privacy failures.

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00986
• PDF: https://arxiv.org/pdf/2604.00986
• Github: https://github.com/FreedomIntelligence/MyPhoneBench

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

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

#PhoneAgents #DataPrivacy #AI #PrivacyResearch #Cybersecurity

✨S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

📝 Summary:
S0 tuning optimizes recurrent state matrices in hybrid models, outperforming LoRA with zero inference overhead. It significantly improves performance on benchmarks like HumanEval and enables efficient task switching.

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01168
• PDF: https://arxiv.org/pdf/2604.01168
• Project Page: https://www.jackyoung.io/research/s0-tuning
• Github: https://github.com/JackYoung27/s0-tuning

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

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

#S0Tuning #DeepLearning #LLMs #ModelOptimization #MachineLearning

✨When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation

📝 Summary:
LLM agents struggle with user interruptions during long web navigation tasks. This paper introduces InterruptBench, the first systematic study and benchmark to evaluate interruptible agents in these scenarios. Results show that current LLMs find handling mid-task interruptions effectively and eff...

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00892
• PDF: https://arxiv.org/pdf/2604.00892
• Project Page: https://github.com/HenryPengZou/InterruptBench
• Github: https://github.com/HenryPengZou/InterruptBench

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

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

#LLMAgents #UserInteractions #WebNavigation #AIResearch #Benchmarking

✨Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy

📝 Summary:
Behavioral consistency in LLM agents correlates with higher accuracy across models. However, consistency can amplify both correct and incorrect interpretations, meaning consistent wrong interpretations are a major failure mode. Thus, accurate interpretation is more crucial than execution consiste...

🔹 Publication Date: Published on Mar 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.25764
• PDF: https://arxiv.org/pdf/2603.25764

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

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

#LLMAgents #ModelAccuracy #BehavioralAI #AIResearch #AIInterpretation

✨AgentWatcher: A Rule-based Prompt Injection Monitor

📝 Summary:
AgentWatcher defends LLMs against prompt injection, which struggles with long contexts and opaque detection. It achieves scalability by using causal attribution to pinpoint influential context segments. Detection is explainable through a monitor LLM that applies explicit rules.

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01194
• PDF: https://arxiv.org/pdf/2604.01194
• Github: https://github.com/wang-yanting/AgentWatcher

🔹 Models citing this paper:
• https://huggingface.co/SecureLLMSys/AgentWatcher-Qwen3-4B-Instruct-2507

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding

📝 Summary:
PixelPrune reduces VLM computational costs by removing redundant image patches before Vision Transformer encoding. It uses predictive-coding compression in pixel space, speeding up inference and training up to 4.2x and 1.9x respectively while maintaining accuracy.

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.00886
• PDF: https://arxiv.org/pdf/2604.00886
• Github: https://github.com/OPPO-Mente-Lab/PixelPrune

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨GPA: Learning GUI Process Automation from Demonstrations

📝 Summary:
GUI Process Automation (GPA) offers robust, deterministic, and privacy-preserving vision-based robotic process automation with faster execution than current vision-language model approaches. AI-genera...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01676
• PDF: https://arxiv.org/pdf/2604.01676
• Project Page: https://www.salesforceairesearch.com/gpa

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook

📝 Summary:
Latent space is emerging as a fundamental computational substrate for language-based models, offering advantages over explicit token-level approaches through continuous representation that mitigates l...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02029
• PDF: https://arxiv.org/pdf/2604.02029
• Github: https://github.com/YU-deep/Awesome-Latent-Space

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

📝 Summary:
SKILL0 enables LLM agents to internalize skills during training, allowing zero-shot autonomous behavior through a dynamic curriculum that reduces contextual overhead while improving task performance. ...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02268
• PDF: https://arxiv.org/pdf/2604.02268
• Github: https://github.com/ZJU-REAL/SkillZero

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FlowSlider: Training-Free Continuous Image Editing via Fidelity-Steering Decomposition

📝 Summary:
FlowSlider enables continuous image editing with slider-style control by decomposing updates into fidelity and steering components within Rectified Flow, providing stable strength control without addi...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02088
• PDF: https://arxiv.org/pdf/2604.02088
• Project Page: https://huggingface.co/spaces/dominoer/FlowSlider

✨ Spaces citing this paper:
• https://huggingface.co/spaces/dominoer/FlowSlider

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models

📝 Summary:
DataFlex is a unified framework for dynamic data-centric training of large language models that supports sample selection, domain mixture adjustment, and sample reweighting while maintaining compatibi...

🔹 Publication Date: Published on Mar 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.26164
• PDF: https://arxiv.org/pdf/2603.26164
• Github: https://github.com/OpenDCAI/DataFlex

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Generative World Renderer

📝 Summary:
A large-scale dynamic dataset derived from AAA games is introduced to improve generative inverse and forward rendering, featuring high-resolution synchronized RGB and G-buffer data alongside a novel V...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02329
• PDF: https://arxiv.org/pdf/2604.02329
• Project Page: https://alaya-studio.github.io/renderer
• Github: https://github.com/ShandaAI/AlayaRenderer

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

📝 Summary:
An autonomous research pipeline discovers Omni-SimpleMem, a unified multimodal memory framework that significantly improves lifelong AI agent performance through automated architectural modifications,...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01007
• PDF: https://arxiv.org/pdf/2604.01007

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EgoSim: Egocentric World Simulator for Embodied Interaction Generation

📝 Summary:
W e i n t r o d u c e E g o S i m , a c l o s e d - l o o p e g o c e n t r i c w o r l d s i m u l a t o r t h a t g e n e r a t e s s p a t i a l l y c o n s i s t e n t i n t e r a c t i o n v i d ...

🔹 Publication Date: Published on Apr 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01001
• PDF: https://arxiv.org/pdf/2604.01001
• Project Page: https://egosimulator.github.io/
• Github: https://egosimulator.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving

📝 Summary:
UniDriveVLA is a unified vision-language-action model for autonomous driving that decouples spatial perception and semantic reasoning through a mixture-of-transformers architecture with expert coordin...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02190
• PDF: https://arxiv.org/pdf/2604.02190
• Project Page: https://xiaomi-research.github.io/unidrivevla/
• Github: https://github.com/xiaomi-research/unidrivevla

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

📝 Summary:
VideoZeroBench presents a comprehensive benchmark for long-video question answering with rigorous spatio-temporal evidence verification, revealing significant gaps in current models' grounded video un...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.01569
• PDF: https://arxiv.org/pdf/2604.01569
• Project Page: https://marinero4972.github.io/projects/VideoZeroBench
• Github: https://github.com/marinero4972/VideoZeroBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers

📝 Summary:
Controllable diffusion models using linear attention architectures enable secure on-device visual generation with improved multi-condition input handling and faster convergence. AI-generated summary R...

🔹 Publication Date: Published on Mar 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27666
• PDF: https://arxiv.org/pdf/2603.27666

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model

📝 Summary:
LatentUM is a unified model that represents all modalities in a shared semantic latent space, enabling efficient cross-modal reasoning and generation without pixel-space mediation. AI-generated summar...

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02097
• PDF: https://arxiv.org/pdf/2604.02097
• Github: https://github.com/SJTU-DENG-Lab/LatentUM

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning

📝 Summary:
Apriel-Reasoner, a 15B LLM, uses reproducible multi-domain RL post-training with novel sampling and length penalty to boost reasoning accuracy and efficiency. It achieves 30-50% shorter traces, outperforming its base model and matching peers at lower inference cost.

🔹 Publication Date: Published on Apr 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02007
• PDF: https://arxiv.org/pdf/2604.02007

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research