✨PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

📝 Summary:
PyTorch Fully Sharded Data Parallel (FSDP) enables efficient and scalable training of large models across hardware configurations. AI-generated summary It is widely acknowledged that large models have...

🔹 Publication Date: Published on Apr 21, 2023

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2304.11277
• PDF: https://arxiv.org/pdf/2304.11277
• Github: https://github.com/pytorch/pytorch/blob/main/torch/distributed/fsdp/fully_sharded_data_parallel.py

🔹 Models citing this paper:
• https://huggingface.co/Undi95/dbrx-base
• https://huggingface.co/alpindale/dbrx-instruct
• https://huggingface.co/SinclairSchneider/dbrx-instruct-quantization-fixed

✨ Spaces citing this paper:
• https://huggingface.co/spaces/nanotron/ultrascale-playbook
• https://huggingface.co/spaces/Ki-Seki/ultrascale-playbook-zh-cn
• https://huggingface.co/spaces/weege007/ultrascale-playbook

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PyTorch Distributed: Experiences on Accelerating Data Parallel Training

📝 Summary:
The PyTorch distributed data parallel module optimizes large-scale model training using techniques like gradient bucketing, computation-communication overlap, and selective synchronization to achieve ...

🔹 Publication Date: Published on Jun 28, 2020

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2006.15704
• PDF: https://arxiv.org/pdf/2006.15704
• Github: https://github.com/pytorch/pytorch/blob/master/torch/nn/parallel/distributed.py

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Video Generation Models Are Good Latent Reward Models

📝 Summary:
PRFL optimizes video generation preferences in latent space, improving alignment with human preferences while reducing memory consumption and training time. AI-generated summary Reward feedback learni...

🔹 Publication Date: Published on Nov 26, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.21541
• PDF: https://arxiv.org/pdf/2511.21541
• Project Page: https://hy-video-prfl.github.io/HY-VIDEO-PRFL/
• Github: https://github.com/Tencent-Hunyuan/HY-Video-PRFL

🔹 Models citing this paper:
• https://huggingface.co/tencent/HY-Video-PRFL

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RAG-Anything: All-in-One RAG Framework

📝 Summary:
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks. A...

🔹 Publication Date: Published on Oct 14, 2025

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/rag-anything-all-in-one-rag-framework
• PDF: https://arxiv.org/pdf/2510.12323
• Github: https://github.com/HKUDS/RAG-Anything

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SAM 3: Segment Anything with Concepts

📝 Summary:
Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization. A...

🔹 Publication Date: Published on Nov 20, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/sam-3-segment-anything-with-concepts-8758-14547cc3
• PDF: https://arxiv.org/pdf/2511.16719
• Project Page: https://ai.meta.com/sam3/
• Github: https://github.com/facebookresearch/sam3

✨ Spaces citing this paper:
• https://huggingface.co/spaces/kith777/rag_agent

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Very Large-Scale Multi-Agent Simulation in AgentScope

📝 Summary:
Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendl...

🔹 Publication Date: Published on Jul 25, 2024

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2407.17789
• PDF: https://arxiv.org/pdf/2407.17789
• Github: https://github.com/modelscope/agentscope

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

📝 Summary:
olmOCR is an open-source toolkit using a fine-tuned vision language model to process PDFs into clean text while preserving structure, optimized for large-scale batch processing. AI-generated summary P...

🔹 Publication Date: Published on Feb 25, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2502.18443
• PDF: https://arxiv.org/pdf/2502.18443
• Github: https://github.com/allenai/olmocr

✨ Datasets citing this paper:
• https://huggingface.co/datasets/davanstrien/test-olmocr2
• https://huggingface.co/datasets/davanstrien/newspapers-olmocr2
• https://huggingface.co/datasets/stckmn/ocr-output-Directive017-1761355297

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

📝 Summary:
AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe devel...

🔹 Publication Date: Published on Aug 22, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.16279
• PDF: https://arxiv.org/pdf/2508.16279
• Github: https://github.com/agentscope-ai/agentscope

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MediaPipe: A Framework for Building Perception Pipelines

📝 Summary:
MediaPipe is a framework for building perception applications. It helps developers combine components, prototype, and measure performance across platforms, addressing key development challenges. This allows focusing on algorithm improvement with reproducible results.

🔹 Publication Date: Published on Jun 14, 2019

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/1906.08172
• PDF: https://arxiv.org/pdf/1906.08172
• Github: https://github.com/google-ai-edge/mediapipe

✨ Spaces citing this paper:
• https://huggingface.co/spaces/Jha-Pranav/PixelCare

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Multi-Agent Software Development through Cross-Team Collaboration

📝 Summary:
Cross-Team Collaboration improves software quality by enabling multiple LLM agent teams to propose and communicate decisions. AI-generated summary The latest breakthroughs in Large Language Models ( L...

🔹 Publication Date: Published on Jun 13, 2024

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2406.08979
• PDF: https://arxiv.org/pdf/2406.08979
• Github: https://github.com/OpenBMB/ChatDev

✨ Spaces citing this paper:
• https://huggingface.co/spaces/shanghengdu/LLM-Agent-Optimization-PaperList

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Scaling Large-Language-Model-based Multi-Agent Collaboration

📝 Summary:
This study proposes MacNet, a multi-agent collaboration network organizing agents via directed acyclic graphs. It shows MacNet outperforms baselines, scales to over a thousand agents, and reveals a collaborative scaling law with abilities emerging earlier than neural scaling.

🔹 Publication Date: Published on Jun 11, 2024

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2406.07155
• PDF: https://arxiv.org/pdf/2406.07155
• Project Page: https://github.com/OpenBMB/ChatDev/tree/macnet
• Github: https://github.com/OpenBMB/ChatDev/tree/macnet

✨ Spaces citing this paper:
• https://huggingface.co/spaces/shanghengdu/LLM-Agent-Optimization-PaperList

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Single-stream Policy Optimization

📝 Summary:
Single-stream Policy Optimization SPO improves LLM policy-gradient training by eliminating group-based issues. SPO uses a persistent value tracker and global advantage normalization for a stable learning signal, achieving higher accuracy and significant gains on hard math benchmarks.

🔹 Publication Date: Published on Sep 16, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.13232
• PDF: https://arxiv.org/pdf/2509.13232
• Project Page: https://zhongwenxu.notion.site/Single-stream-Policy-Optimization-26a1c4e140e380d78d51fa4567727f50
• Github: https://github.com/volcengine/verl

🔹 Models citing this paper:
• https://huggingface.co/jingyaogong/MiniMind2-gguf

✨ Datasets citing this paper:
• https://huggingface.co/datasets/dingzihan737/SPO_Qwen3-8B_DAPO_16k_ReTool_Binary

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

📝 Summary:
This paper proposes Citation-aware Rubric Rewards CaRR and C-GRPO to enhance deep search agents. CaRR provides fine-grained, citation-aware rewards that promote factual, comprehensive, evidence-grounded reasoning, reducing shortcuts. C-GRPO outperforms standard RL baselines, offering robust agent...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.06021
• PDF: https://arxiv.org/pdf/2601.06021
• Github: https://github.com/THUDM/CaRR

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

📝 Summary:
VideoAR presents a large-scale visual autoregressive framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling, achieving state-of-the-art results wit...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05966
• PDF: https://arxiv.org/pdf/2601.05966

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation

📝 Summary:
DR-LoRA dynamically adjusts LoRA ranks for experts in Mixture-of-Experts models based on task-specific demands, improving parameter efficiency and performance. AI-generated summary Mixture-of-Experts ...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04823
• PDF: https://arxiv.org/pdf/2601.04823

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck

📝 Summary:
Latent Policy Optimization via Iterative Information Bottleneck addresses exploration collapse in LLM reasoning by enabling topological branching of reasoning trajectories through information bottlene...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05870
• PDF: https://arxiv.org/pdf/2601.05870

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

📝 Summary:
Video generation models trained on synthetic physics primitives demonstrate zero-shot generalization to complex real-world scenarios by modeling force propagation through time and space. AI-generated ...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05848
• PDF: https://arxiv.org/pdf/2601.05848
• Project Page: https://goal-force.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨GenCtrl -- A Formal Controllability Toolkit for Generative Models

📝 Summary:
Generative models' controllability is theoretically analyzed through a framework that estimates controllable sets with distribution-free bounds, revealing that controllability is fragile and context-d...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05637
• PDF: https://arxiv.org/pdf/2601.05637

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Over-Searching in Search-Augmented Large Language Models

📝 Summary:
Search-augmented large language models suffer from over-searching behavior that wastes computational resources and introduces hallucinations, with findings showing varied impacts across model types an...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05503
• PDF: https://arxiv.org/pdf/2601.05503

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

📝 Summary:
NeoVerse is a scalable 4D world model that enables pose-free reconstruction and novel-trajectory video generation from monocular videos with state-of-the-art performance. AI-generated summary In this ...

🔹 Publication Date: Published on Jan 1

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/neoverse-enhancing-4d-world-model-with-in-the-wild-monocular-videos
• PDF: https://arxiv.org/pdf/2601.00393
• Project Page: https://neoverse-4d.github.io/
• Github: https://neoverse-4d.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research