✨LightRAG: Simple and Fast Retrieval-Augmented Generation

📝 Summary:
LightRAG improves Retrieval-Augmented Generation by addressing limitations of flat data representations and inadequate contextual awareness. It integrates graph structures into text indexing and retrieval, enhancing accuracy, efficiency, and response times through a dual-level system.

🔹 Publication Date: Published on Oct 8, 2024

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2410.05779
• PDF: https://arxiv.org/pdf/2410.05779
• Github: https://github.com/hkuds/lightrag

✨ Spaces citing this paper:
• https://huggingface.co/spaces/rm-lht/lightrag

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

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

#RAG #AI #NLP #GraphAI #InformationRetrieval

✨RiddleBench: A New Generative Reasoning Benchmark for LLMs

📝 Summary:
RiddleBench, a new benchmark of 1,737 puzzles, reveals fundamental weaknesses in state-of-the-art LLMs, including hallucination cascades and poor self-correction. Models achieve only about 60% accuracy, underscoring the need for more robust and reliable reasoning capabilities.

🔹 Publication Date: Published on Oct 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.24932
• PDF: https://arxiv.org/pdf/2510.24932

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ai4bharat/RiddleBench

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

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

#LLMs #GenerativeAI #AIResearch #Benchmarks #NLP

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

📝 Summary:
AgentScope 1.0 is a developer-centric framework for building agentic applications. It offers flexible tool-based interactions, unified interfaces, and ReAct-based infrastructure to enable efficient and safe development and deployment.

🔹 Publication Date: Published on Aug 22

🔹 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.iss.one/DataScienceT

#AIAgents #AIdevelopment #SoftwareFramework #AItools #ReActAI

✨RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies

📝 Summary:
RoboChallenge is an online evaluation system for robotic control algorithms, especially VLA models. It enables large-scale, reproducible real-robot testing to survey state-of-the-art models.

🔹 Publication Date: Published on Oct 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.17950
• PDF: https://arxiv.org/pdf/2510.17950

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

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

#Robotics #AI #MachineLearning #EmbodiedAI #RoboticsEvaluation

✨Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation

📝 Summary:
This paper presents GT-Pair for automatic preference data construction and Reg-DPO, which adds SFT loss to DPO for stable training. Combined with memory optimizations, it significantly improves video generation quality, outperforming existing methods.

🔹 Publication Date: Published on Nov 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.01450
• PDF: https://arxiv.org/pdf/2511.01450
• Github: https://github.com/JieDuTQS/Reg-DPO

🔹 Models citing this paper:
• https://huggingface.co/dujielvtqs/Reg-DPO

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

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

#VideoGeneration #GenerativeAI #DeepLearning #DPO #AIResearch

✨AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda

📝 Summary:
AyurParam-2.9B is a bilingual language model for Ayurveda, outperforming smaller models and competing with larger ones on medical tasks. Highlighting the need for domain adaptation and quality data.

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02374
• PDF: https://arxiv.org/pdf/2511.02374

🔹 Models citing this paper:
• https://huggingface.co/bharatgenai/AyurParam

✨ Spaces citing this paper:
• https://huggingface.co/spaces/Swanand3/BharatGen_AyurParam

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

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

#Ayurveda #LanguageModel #BilingualAI #NLP #HealthcareAI

✨3D Gaussian Splatting for Real-Time Radiance Field Rendering

📝 Summary:
This paper introduces a method using 3D Gaussians for scene representation to achieve state-of-the-art, high-quality real-time novel-view synthesis at 1080p resolution. It optimizes anisotropic Gaussians and uses a fast rendering algorithm, outperforming previous radiance field methods.

🔹 Publication Date: Published on Aug 8, 2023

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2308.04079
• PDF: https://arxiv.org/pdf/2308.04079
• Github: https://github.com/graphdeco-inria/gaussian-splatting

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Voxel51/gaussian_splatting

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

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

#3DGaussianSplatting #RadianceFields #ComputerGraphics #RealTimeRendering #NovelViewSynthesis

✨DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion

📝 Summary:
DyPE enhances diffusion transformers for ultra-high-resolution image generation by dynamically adjusting positional encodings. This training-free method allows pre-trained models to synthesize images far beyond their training resolution, achieving state-of-the-art fidelity without extra sampling ...

🔹 Publication Date: Published on Oct 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.20766
• PDF: https://arxiv.org/pdf/2510.20766
• Project Page: https://noamissachar.github.io/DyPE/
• Github: https://github.com/guyyariv/DyPE

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

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

#DiffusionModels #ImageGeneration #HighResolution #DeepLearning #ComputerVision

✨MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity

📝 Summary:
MME-CC is a new vision-grounded benchmark to evaluate multimodal large language models cognitive capacity in spatial, geometric, and knowledge-based reasoning tasks. It reveals that while some models lead, spatial and geometric reasoning remain broadly weak. This highlights the need for better ev...

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03146
• PDF: https://arxiv.org/pdf/2511.03146
• Project Page: https://randomtutu.github.io/MME-CC/

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

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

#MultimodalAI #LLMs #Benchmarking #CognitiveAI #ComputerVision

✨LEGO-Eval: Towards Fine-Grained Evaluation on Synthesizing 3D Embodied Environments with Tool Augmentation

📝 Summary:
The paper introduces LEGO-Eval, a tool-augmented framework, and LEGO-Bench, a detailed instruction benchmark, to improve 3D scene evaluation. It shows LEGO-Eval accurately assesses scene-instruction alignment, outperforming VLMs, and current generation methods largely fail to create realistic sce...

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03001
• PDF: https://arxiv.org/pdf/2511.03001
• Project Page: https://gyeomh.github.io/LEGO-Eval/

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

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

#EmbodiedAI #3DGeneration #EvaluationMetrics #VLMs #Benchmarking

✨Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation

📝 Summary:
M-Solomon is a multimodal embedder that adaptively decides when to augment queries. It uses a Multimodal LLM to generate augmentations for queries that require them, learning to augment only when necessary. This approach improves performance and significantly reduces embedding latency compared to...

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02358
• PDF: https://arxiv.org/pdf/2511.02358

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

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

#MultimodalAI #LLM #Embeddings #MachineLearning #DeepLearning

✨LiveTradeBench: Seeking Real-World Alpha with Large Language Models

📝 Summary:
LiveTradeBench evaluates LLMs in live trading environments with real-time data, multi-asset portfolios, and multiple markets. It reveals that strong static benchmark scores dont predict trading success, and some LLMs can adapt to live market signals. This highlights a gap in current LLM evaluations.

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03628
• PDF: https://arxiv.org/pdf/2511.03628
• Project Page: https://trade-bench.live/
• Github: https://github.com/ulab-uiuc/live-trade-bench

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

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

#LLM #AlgorithmicTrading #FinancialAI #QuantitativeFinance #AIResearch

✨Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects

📝 Summary:
Kinematify is an automated framework that synthesizes high-DoF articulated objects from images or text. It infers kinematic topologies and estimates joint parameters, combining MCTS search with geometry-driven optimization for physically consistent models.

🔹 Publication Date: Published on Nov 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.01294
• PDF: https://arxiv.org/pdf/2511.01294

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

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

#3DModeling #ComputerVision #Robotics #AIResearch #Kinematics

✨Diffusion Language Models are Super Data Learners

📝 Summary:
Diffusion Language Models DLMs consistently outperform autoregressive models, especially in low-data settings. This is due to any-order modeling, iterative bidirectional denoising, and Monte Carlo augmentation. DLMs maintain advantages at scale, achieving strong performance even by repeating limi...

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03276
• PDF: https://arxiv.org/pdf/2511.03276
• Project Page: https://github.com/JinjieNi/dlms-are-super-data-learners
• Github: https://github.com/JinjieNi/OpenMoE2

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

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

#DiffusionModels #LanguageModels #MachineLearning #LowDataLearning #AI

✨Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning

📝 Summary:
Orion-MSP is a novel tabular in-context learning architecture addressing limitations in existing models. It incorporates multi-scale processing, block-sparse attention, and a Perceiver-style memory. Orion-MSP achieves state-of-the-art performance on various benchmarks while scaling effectively to...

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02818
• PDF: https://arxiv.org/pdf/2511.02818

🔹 Models citing this paper:
• https://huggingface.co/Lexsi/Orion-MSP

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

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

#TabularLearning #SparseAttention #MachineLearning #DeepLearning #AI

✨TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

📝 Summary:
TabTune is a unified library that standardizes the workflow for tabular foundation models. It provides consistent access to state-of-the-art models, diverse adaptation strategies, and integrated evaluation for performance, calibration, and fairness.

🔹 Publication Date: Published on Nov 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02802
• PDF: https://arxiv.org/pdf/2511.02802
• Github: https://github.com/Lexsi-Labs/TabTune

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

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

#TabularData #FoundationModels #MachineLearning #DataScience #AIResearch

✨UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

📝 Summary:
UniAVGen uses dual Diffusion Transformers and Asymmetric Cross-Modal Interaction for unified audio-video generation. This framework ensures precise spatiotemporal synchronization and semantic consistency. It outperforms existing methods in sync and consistency with far fewer training samples.

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03334
• PDF: https://arxiv.org/pdf/2511.03334
• Project Page: https://mcg-nju.github.io/UniAVGen/
• Github: https://mcg-nju.github.io/UniAVGen/

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

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

#GenerativeAI #AudioVideoGeneration #DiffusionModels #CrossModalAI #DeepLearning

✨MemOS: A Memory OS for AI System

📝 Summary:
MemOS is a memory operating system that unifies plaintext, activation-based, and parameter-level memories for LLMs. It manages memory as a system resource with MemCubes, enabling efficient storage, retrieval, continual learning, and personalized modeling.

🔹 Publication Date: Published on Jul 4

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/memos-a-memory-os-for-ai-system
• PDF: https://arxiv.org/pdf/2507.03724
• Project Page: https://memos.openmem.net/
• Github: https://github.com/MemTensor/MemOS

🔹 Models citing this paper:
• https://huggingface.co/kagvi13/HMP

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

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

#MemOS #LLMs #MemoryManagement #OperatingSystems #AI

✨FG-CLIP: Fine-Grained Visual and Textual Alignment

📝 Summary:
FG-CLIP enhances fine-grained multimodal understanding, overcoming CLIPs limitations with coarse captions. It uses large models for long captions, a high-quality dataset with region boxes and detailed captions, and hard negative samples. FG-CLIP outperforms existing methods on fine-grained and ge...

🔹 Publication Date: Published on May 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2505.05071
• PDF: https://arxiv.org/pdf/2505.05071
• Github: https://github.com/360CVGroup/FG-CLIP

🔹 Models citing this paper:
• https://huggingface.co/qihoo360/fg-clip2-base
• https://huggingface.co/qihoo360/fg-clip-large
• https://huggingface.co/qihoo360/fg-clip-base

✨ Datasets citing this paper:
• https://huggingface.co/datasets/qihoo360/FineHARD
• https://huggingface.co/datasets/qihoo360/DCI-CN
• https://huggingface.co/datasets/qihoo360/DOCCI-CN

✨ Spaces citing this paper:
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Retrieval-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Densefeature-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP2-Retrieval-demo

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

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

#FGCLIP #FineGrainedAI #MultimodalLearning #ComputerVision #DeepLearning