✨FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

📝 Summary:
FoundationMotion is an automated pipeline for creating large-scale motion datasets using object detection, trajectory extraction, and LLM-generated captions, improving motion understanding in models. ...

🔹 Publication Date: Published on Dec 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.10927
• PDF: https://arxiv.org/pdf/2512.10927
• Project Page: https://yulugan.com/projects/FoundationMotion.html
• Github: https://github.com/Wolfv0/FoundationMotion/tree/main

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨KD-OCT: Efficient Knowledge Distillation for Clinical-Grade Retinal OCT Classification

📝 Summary:
A novel knowledge distillation framework compresses a high-performance ConvNeXtV2-Large model into a lightweight EfficientNet-B2 for efficient AMD and CNV classification in real-time clinical settings...

🔹 Publication Date: Published on Dec 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.09069
• PDF: https://arxiv.org/pdf/2512.09069
• Github: https://github.com/erfan-nourbakhsh/KD-OCT

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence

📝 Summary:
CoRe3D is a 3D reasoning framework for understanding and generation. It aligns high-level language intent with low-level 3D content using spatially grounded reasoning. This ensures consistent and accurate 3D outputs faithful to linguistic denoscriptions.

🔹 Publication Date: Published on Dec 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12768
• PDF: https://arxiv.org/pdf/2512.12768

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

200$ to 20k$ SOL Challenge!

As promised, i will do another challenge for those who missed the previous one!

Last one we completed in 6 days, let’s do this one even quicker!

Join my free group Before closing 👇
https://news.1rj.ru/str/+DAKLP7eUy9Y3ZjY0

#ad InsideAds

✨AutoMV: An Automatic Multi-Agent System for Music Video Generation

📝 Summary:
AutoMV, a multi-agent system, generates coherent full-length music videos directly from songs. It processes music attributes for agents to noscript and generate scenes, ensuring consistency. AutoMV outperforms existing methods, nearing professional MV quality.

🔹 Publication Date: Published on Dec 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12196v1
• PDF: https://arxiv.org/pdf/2512.12196
• Project Page: https://github.com/multimodal-art-projection/AutoMV
• Github: https://github.com/multimodal-art-projection/AutoMV

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners

📝 Summary:
A pre-trained 3D instance generator is reprogrammed to learn spatial understanding directly from geometric cues. This enables generalization to new layouts, showing it is an implicit spatial learner, pointing to foundation models for 3D scene generation.

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13683
• PDF: https://arxiv.org/pdf/2512.13683

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse

📝 Summary:
The rapid scaling of Large Language Models (LLMs) has achieved remarkable performance, but it also leads to prohibitive memory costs. Existing parameter-efficient approaches such as pruning and quanti...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14531
• PDF: https://arxiv.org/pdf/2512.14531
• Github: https://github.com/huawei-noah/noah-research/tree/master/VersatileFFN

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

📝 Summary:
Scone integrates composition and distinction in image generation by using a two-stage training scheme with semantic alignment and attention-based masking, outperforming existing models on benchmarks. ...

🔹 Publication Date: Published on Dec 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12675
• PDF: https://arxiv.org/pdf/2512.12675
• Github: https://github.com/Ryann-Ran/Scone

🔹 Models citing this paper:
• https://huggingface.co/Ryann829/Scone

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Ryann829/Scone-S2I-57K
• https://huggingface.co/datasets/Ryann829/SconeEval

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

📝 Summary:
WorldPlay is a streaming video diffusion model that achieves real-time, interactive world modeling with long-term geometric consistency by using a Dual Action Representation, Reconstituted Context Mem...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14614
• PDF: https://arxiv.org/pdf/2512.14614
• Project Page: https://3d-models.hunyuan.tencent.com/world/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Olmo 3

📝 Summary:
Olmo 3, a family of state-of-the-art fully-open language models at 7B and 32B parameter scales, excels in long-context reasoning, function calling, coding, instruction following, general chat, and kno...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13961
• PDF: https://arxiv.org/pdf/2512.13961
• Project Page: https://playground.allenai.org/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Feedforward 3D Editing via Text-Steerable Image-to-3D

📝 Summary:
Steer3D enables text-based editing of AI-generated 3D assets by adapting ControlNet for image-to-3D generation with flow-matching training and Direct Preference Optimization. AI-generated summary Rece...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13678
• PDF: https://arxiv.org/pdf/2512.13678
• Project Page: https://glab-caltech.github.io/steer3d/
• Github: https://glab-caltech.github.io/steer3d/#demo

🔹 Models citing this paper:
• https://huggingface.co/ziqima/Steer3D

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ziqima/Steer3D-Data
• https://huggingface.co/datasets/ziqima/Edit3D-Bench

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MMGR: Multi-Modal Generative Reasoning

📝 Summary:
MMGR is a new benchmark assessing video and image model reasoning across physical, logical, and spatial domains. It uncovers major performance gaps, showing models struggle with abstract reasoning and planning, often prioritizing visual plausibility over true causal correctness.

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14691
• PDF: https://arxiv.org/pdf/2512.14691

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics

📝 Summary:
RoboTracer, a 3D-aware visual language model, enhances spatial tracing by combining supervised and reinforcement fine-tuning with a universal spatial encoder and regression-supervised decoder, achievi...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13660
• PDF: https://arxiv.org/pdf/2512.13660
• Project Page: https://zhoues.github.io/RoboTracer/
• Github: https://zhoues.github.io/RoboTracer/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RecGPT-V2 Technical Report

📝 Summary:
RecGPT-V2 enhances recommender systems by integrating a Hierarchical Multi-Agent System, Hybrid Representation Inference, Meta-Prompting, constrained reinforcement learning, and an Agent-as-a-Judge fr...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14503
• PDF: https://arxiv.org/pdf/2512.14503

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives

📝 Summary:
MemFlow dynamically updates a memory bank by retrieving relevant historical frames for each video chunk, ensuring narrative coherence and generation efficiency with minimal computational overhead. AI-...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14699
• PDF: https://arxiv.org/pdf/2512.14699

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

📝 Summary:
A4-Agent, a training-free framework, decouples affordance prediction into three stages using specialized pre-trained models to enhance generalization and performance in real-world settings. AI-generat...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14442
• PDF: https://arxiv.org/pdf/2512.14442
• Project Page: https://zixinzhang02.github.io/A4-Agent-page/
• Github: https://zixinzhang02.github.io/A4-Agent-page/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed

📝 Summary:
AR-to-dLM conversion enhances diffusion language models' efficiency and speed while maintaining task accuracy through refined attention patterns and token masking strategies. AI-generated summary Diff...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14067
• PDF: https://arxiv.org/pdf/2512.14067

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation

📝 Summary:
Four abliteration tools are evaluated for their effectiveness in removing refusal representations from large language models, with findings showing variability in capability preservation and distribut...

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13655
• PDF: https://arxiv.org/pdf/2512.13655

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

📝 Summary:
WorldPlay is a streaming video diffusion model that achieves real-time, interactive world modeling with long-term geometric consistency by using a Dual Action Representation, Reconstituted Context Mem...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14614
• PDF: https://arxiv.org/pdf/2512.14614
• Project Page: https://3d-models.hunyuan.tencent.com/world/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement

📝 Summary:
ShowTable is a new pipeline that combines MLLMs and diffusion models to generate high-fidelity, creative infographics from data tables. It excels in multi-modal reasoning, generation, and error correction, outperforming existing methods for complex table visualization tasks.

🔹 Publication Date: Published on Dec 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.13303
• PDF: https://arxiv.org/pdf/2512.13303

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SS4D: Native 4D Generative Model via Structured Spacetime Latents

📝 Summary:
SS4D synthesizes dynamic 3D objects from monocular video using a native 4D generative model with structured spacetime latents, ensuring high fidelity, temporal coherence, and structural consistency. A...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14284
• PDF: https://arxiv.org/pdf/2512.14284
• Project Page: https://lizb6626.github.io/SS4D/
• Github: https://github.com/Lizb6626/SS4D/

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

For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research