✨Repurposing Geometric Foundation Models for Multi-view Diffusion

📝 Summary:
Geometric Latent Diffusion (GLD) framework utilizes geometric foundation models' feature space as latent space for novel view synthesis, achieving superior 2D and 3D performance while reducing trainin...

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22275
• PDF: https://arxiv.org/pdf/2603.22275
• Project Page: https://cvlab-kaist.github.io/GLD/
• Github: https://github.com/cvlab-kaist/GLD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

📝 Summary:
OpenResearcher presents a reproducible pipeline for training deep research agents using offline search environments and synthesized trajectories, achieving improved accuracy on benchmark tasks. AI-gen...

🔹 Publication Date: Published on Mar 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.20278
• PDF: https://arxiv.org/pdf/2603.20278
• Project Page: https://github.com/TIGER-AI-Lab/OpenResearcher
• Github: https://github.com/TIGER-AI-Lab/OpenResearcher

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

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

#AI #DeepLearning #ResearchAutomation #Reproducibility #OpenScience

✨FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models

📝 Summary:
FluidWorld demonstrates that partial differential equations can serve as an efficient alternative to attention mechanisms and convolutional recurrent networks in world modeling, achieving better spati...

🔹 Publication Date: Published on Mar 22

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.21315
• PDF: https://arxiv.org/pdf/2603.21315
• Project Page: https://infinition.github.io/FluidWorld
• Github: https://github.com/infinition/FluidWorld

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs

📝 Summary:
AwaRes is a spatial-on-demand framework for VLMs that resolves the accuracy-efficiency trade-off. It operates on a low-resolution global view and uses tool-calling to dynamically retrieve high-resolution segments as needed. Training involves multi-turn reinforcement learning with composite rewards.

🔹 Publication Date: Published on Mar 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.16932
• PDF: https://arxiv.org/pdf/2603.16932
• Project Page: https://nimrodshabtay.github.io/AwaRes/
• Github: https://github.com/NimrodShabtay/AwaRes

✨ Datasets citing this paper:
• https://huggingface.co/datasets/NimrodShabtay1986/AwaRes

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

📝 Summary:
SafeFlow Q-Learning extends FQL to safe offline reinforcement learning by combining a Hamilton-Jacobi reachability-inspired safety value function with an efficient one-step flow policy, achieving lowe...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15136
• PDF: https://arxiv.org/pdf/2603.15136
• Project Page: https://tau-intelligence.com/safe-fql/
• Github: https://github.com/tau-intelligence/safe-fql

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AdditiveLLM2: A Multi-modal Large Language Model for Additive Manufacturing

📝 Summary:
AdditiveLLM2 is a multi-modal LLM built on Gemma 3, specialized for additive manufacturing via domain-adaptive pretraining and instruction tuning on a small dataset. It achieves over 90 percent accuracy in AM language and vision tasks, proving an accessible specialization method for domain-specif...

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22017
• PDF: https://arxiv.org/pdf/2603.22017

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Progressive Training for Explainable Citation-Grounded Dialogue: Reducing Hallucination to Zero in English-Hindi LLMs

📝 Summary:
XKD-Dial is a progressive training pipeline for explainable, bilingual English-Hindi knowledge-grounded dialogue. It achieves zero hallucination rates by using citation grounding and improves explainability through post-hoc analyses.

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.18911
• PDF: https://arxiv.org/pdf/2603.18911

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

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

#LLMs #ExplainableAI #NaturalLanguageProcessing #AIResearch #HallucinationReduction

✨Aperiodic Structures Never Collapse: Fibonacci Hierarchies for Lossless Compression

📝 Summary:
Fibonacci quasicrystal tilings provide superior lossless compression advantages over periodic alternatives through structural properties that maintain dictionary reuse across all scales and achieve lo...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.14999
• PDF: https://arxiv.org/pdf/2603.14999
• Github: https://github.com/robtacconelli/quasicryth

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Scalable Prompt Routing via Fine-Grained Latent Task Discovery

📝 Summary:
This paper introduces a two-stage prompt routing architecture for efficiently selecting optimal language models. It uses graph-based clustering to discover latent task types and a mixture-of-experts for quality estimation. This approach improves performance and reduces computational cost by dynam...

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19415
• PDF: https://arxiv.org/pdf/2603.19415

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

📝 Summary:
LeWorldModel is a stable, end-to-end JEPA that trains efficiently from raw pixels with only two loss terms. It achieves competitive performance in control tasks, plans faster, and encodes meaningful physical structures, even detecting impossible events.

🔹 Publication Date: Published on Mar 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19312
• PDF: https://arxiv.org/pdf/2603.19312
• Project Page: https://le-wm.github.io/
• Github: https://github.com/lucas-maes/le-wm

🔹 Models citing this paper:
• https://huggingface.co/aguennoune17/atlas-v2-nwm-fp8-compressed

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

📝 Summary:
ThinkJEPA improves latent world models by combining dense JEPA dynamics with VLM semantic guidance through a dual-temporal pathway. This framework enhances long-horizon hand-manipulation trajectory prediction.

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22281
• PDF: https://arxiv.org/pdf/2603.22281

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

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

#ThinkJEPA #LatentWorldModels #VLM #Robotics #AI

✨TrajLoom: Dense Future Trajectory Generation from Video

📝 Summary:
TrajLoom is a new framework for predicting dense future motion trajectories in videos. It uses grid-anchor encoding, a VAE for a compact latent space, and flow matching to generate realistic future motion. The method significantly extends prediction horizons and improves motion realism.

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22606
• PDF: https://arxiv.org/pdf/2603.22606
• Project Page: https://trajloom.github.io/
• Github: https://github.com/zewei-Zhang/TrajLoom

🔹 Models citing this paper:
• https://huggingface.co/zeweizhang/TrajLoom

✨ Datasets citing this paper:
• https://huggingface.co/datasets/zeweizhang/TrajLoomDatasets

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI

📝 Summary:
Large language models can automate systematic literature reviews with human-level performance while reducing review time from weeks to hours. AI-generated summary Systematic literature reviews are ess...

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22327
• PDF: https://arxiv.org/pdf/2603.22327
• Project Page: https://oxrml.com/agent-slr/
• Github: https://github.com/OxRML/AgentSLR

✨ Datasets citing this paper:
• https://huggingface.co/datasets/OxRML/AgentSLR

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

📝 Summary:
LLM-based systems use executable workflows that interleave various computational components, with recent approaches organized by workflow structure determination timing and optimization dimensions. AI...

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22386
• PDF: https://arxiv.org/pdf/2603.22386
• Github: https://github.com/IBM/awesome-agentic-workflow-optimization

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PEARL: Personalized Streaming Video Understanding Model

📝 Summary:
Personalized streaming video understanding addresses real-time visual input processing with precise temporal annotations, enabling interactive AI assistants through a new benchmark and plug-and-play s...

🔹 Publication Date: Published on Mar 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.20422
• PDF: https://arxiv.org/pdf/2603.20422
• Github: https://github.com/Yuanhong-Zheng/PEARL

✨ Datasets citing this paper:
• https://huggingface.co/datasets/zyh200727/PEARL-Data

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

📝 Summary:
WildWorld is a large-scale dataset for action-conditioned world modeling that provides explicit state annotations from a photorealistic game, enabling better understanding of latent-state dynamics and...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23497
• PDF: https://arxiv.org/pdf/2603.23497
• Project Page: https://shandaai.github.io/wildworld-project/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

📝 Summary:
Researchers developed a token-level reinforcement learning method called PEPO that improves multimodal chain-of-thought reasoning by distinguishing visual grounding from inference through perception-e...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.22847
• PDF: https://arxiv.org/pdf/2603.22847
• Github: https://github.com/xzxxntxdy/PEPO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

📝 Summary:
A unified reinforcement learning framework is proposed for interleaved text and image generation, using GRPO and FlowGRPO with modifications to enable scalable multi-round generation. AI-generated sum...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23500
• PDF: https://arxiv.org/pdf/2603.23500

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

📝 Summary:
SpecEyes accelerates agentic multimodal large language models by using a lightweight speculative planner with cognitive gating and heterogeneous parallel processing to reduce latency and improve throu...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23483
• PDF: https://arxiv.org/pdf/2603.23483
• Github: https://github.com/MAC-AutoML/SpecEyes

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation

📝 Summary:
A new benchmark and evaluation method for multi-subject image generation that identifies and analyzes cross-subject attribute misbinding failures not detected by traditional metrics. AI-generated summ...

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.21937
• PDF: https://arxiv.org/pdf/2603.21937

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment

📝 Summary:
ABot-PhysWorld is a 14B Diffusion Transformer model that generates physically plausible videos through physics-aware training and evaluation on a new benchmark. AI-generated summary Video-based world ...

🔹 Publication Date: Published on Mar 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.23376
• PDF: https://arxiv.org/pdf/2603.23376
• Github: https://github.com/amap-cvlab/ABot-PhysWorld

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research