✨Improving Recursive Transformers with Mixture of LoRAs

📝 Summary:
This paper proposes Mixture of LoRAs MoL to restore expressivity in parameter-shared recursive transformers. MoL uses token-conditional weight modulation in a shared feed-forward network, achieving state-of-the-art performance with compact models. An expert-merging procedure further enables effic...

🔹 Publication Date: Published on Dec 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12880
• PDF: https://arxiv.org/pdf/2512.12880

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space

📝 Summary:
DMLR is a new framework inspired by human cognition, dynamically interleaving reasoning and perception in latent space. It uses confidence-guided optimization for latent think tokens and injects relevant visual features, improving cross-modal reasoning and perception efficiently.

🔹 Publication Date: Published on Dec 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.12623
• PDF: https://arxiv.org/pdf/2512.12623
• Project Page: https://mllm-dmlr.github.io/
• Github: https://mllm-dmlr.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

🔥 NEW YEAR 2026 – PREMIUM SCIENTIFIC PAPER WRITING OFFER 🔥
Q1-Ready | Journal-Targeted | Publication-Focused

Serious researchers, PhD & MSc students, postdocs, universities, and funded startups only.

To start 2026 strong, we’re offering a limited New Year scientific writing package designed for fast-track publication, not academic busywork.

🎯 What We Offer (End-of-Year Special):

✍️ Full Research Paper Writing – $400
(Q1 / Q2 journal–ready)

Includes:
✅ Journal-targeted manunoscript (Elsevier / Springer / Wiley / IEEE / MDPI)
✅ IMRAD structure (Introduction–Methods–Results–Discussion)
✅ Strong problem formulation & novelty framing
✅ Methodology written to reviewer standards
✅ Professional academic English (native-level)
✅ Plagiarism-free (Turnitin <10%)
✅ Ready for immediate submission

📊 Available Paper Types:

Original Research Articles

Review & Systematic Review

AI / Machine Learning Papers

Engineering & Medical Research

Health AI & Clinical Data Studies

Interdisciplinary & Applied Research

🧠 Optional Add-ons (if needed):

Journal selection & scope matching

Cover letter to editor

Reviewer response (after review)

Statistical validation & result polishing

Figure & table redesign (publication quality)

🚀 Why This Is Different
We don’t “write generic papers.”
We engineer publishable research.

✔️ Real novelty positioning
✔️ Reviewer-proof logic
✔️ Data-driven arguments
✔️ Aligned with current 2025–2026 journal expectations

Many of our papers are built on real-world datasets and are already aligned with Q1 journal standards.

⏳ New Year Offer – Limited Time

Regular price: $1,500 – $3,000

New Year 2026 price: $400

Limited slots (quality > quantity)

🎓 Priority given to:

PhD / MSc students

Active researchers

Funded startups

Universities & labs

📩 DM for details, samples & timelines
Contact:
@Omidyzd62

Start 2026 with a submitted paper—not just a plan

✨When Reasoning Meets Its Laws

📝 Summary:
The Laws of Reasoning LoRe framework defines desired reasoning for Large Reasoning Models, focusing on compute and accuracy. A benchmark, LoRe-Bench, reveals models often lack compositionality, which a finetuning method improves for better performance.

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17901
• PDF: https://arxiv.org/pdf/2512.17901
• Project Page: https://lore-project.github.io/
• Github: https://github.com/ASTRAL-Group/LoRe

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

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

#AI #LargeLanguageModels #Reasoning #MachineLearning #NLP

✨Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience

📝 Summary:
Seed-Prover 1.5 is a formal theorem-proving model that uses agentic reinforcement learning and an efficient scaling workflow. It achieves superior performance in solving undergraduate, graduate, and PhD-level math problems with reduced computational resources. This demonstrates the potential of l...

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17260
• PDF: https://arxiv.org/pdf/2512.17260
• Github: https://github.com/ByteDance-Seed/Seed-Prover

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

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

#TheoremProving #ReinforcementLearning #AI #Mathematics #AI4Math

✨SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories

📝 Summary:
SWE-Bench++ is an automated framework generating scalable, multilingual, repository-level coding tasks from live GitHub pull requests. It overcomes manual curation limits and static datasets, offering a benchmark to evaluate and improve code generation models across 11 languages.

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17419
• PDF: https://arxiv.org/pdf/2512.17419
• Project Page: https://research.turing.com/swebench
• Github: https://huggingface.co/papers?q=GitHub%20pull%20requests

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

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

#SoftwareEngineering #CodeGeneration #AIBenchmarking #MachineLearning #OpenSource

✨4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

📝 Summary:
4D-RGPT, a specialized multimodal LLM, enhances 4D perception in video inputs through Perceptual 4D Distillation and is evaluated on R4D-Bench, a new benchmark for depth-aware dynamic scenes. AI-gener...

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17012
• PDF: https://arxiv.org/pdf/2512.17012
• Project Page: https://ca-joe-yang.github.io/resource/projects/4D_RGPT

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows

📝 Summary:
A framework for Scientific General Intelligence (SGI) is presented, evaluated using SGI-Bench, and improved with Test-Time Reinforcement Learning, highlighting gaps in existing models' scientific capa...

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.16969
• PDF: https://arxiv.org/pdf/2512.16969
• Project Page: https://internscience.github.io/SGI-Page/
• Github: https://github.com/InternScience/SGI-Bench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Animate Any Character in Any World

📝 Summary:
AniX extends controllable-entity models to enable diverse, user-defined character interactions in static 3D environments via natural language. It synthesizes temporally coherent videos through conditional autoregressive video generation, allowing characters to perform open-ended actions.

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17796
• PDF: https://arxiv.org/pdf/2512.17796
• Project Page: https://snowflakewang.github.io/AniX/
• Github: https://github.com/snowflakewang/AniX

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

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

#GenerativeAI #VideoGeneration #CharacterAnimation #NLP #3D

✨Are We on the Right Way to Assessing LLM-as-a-Judge?

📝 Summary:
Sage is a human-free evaluation suite assessing LLM-as-a-Judge consistency using rational choice theory. It reveals significant reliability problems in current top LLM judges, even in difficult cases. The study suggests finetuning, explicit rubrics, and panel judging can boost consistency.

🔹 Publication Date: Published on Dec 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.16041
• PDF: https://arxiv.org/pdf/2512.16041

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

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

#LLMEvaluation #LLMReliability #AIResearch #GenAI #NLP

✨Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

📝 Summary:
Canon layers are lightweight architectural components that enhance language model reasoning depth and breadth by promoting horizontal information flow. They improve performance across various architectures, validated in synthetic tasks and real-world pretraining.

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17351
• PDF: https://arxiv.org/pdf/2512.17351
• Project Page: https://physics.allen-zhu.com/part-4-architecture-design/part-4-1
• Github: https://github.com/facebookresearch/PhysicsLM4

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

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

#LanguageModels #LLM #AIArchitecture #DeepLearning #NLP

✨Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

📝 Summary:
Turn-PPO improves multi-turn reinforcement learning for LLM agents by using a turn-level MDP for advantage estimation. This PPO variant outperforms GRPO and standard PPO, addressing limitations in long-horizon reasoning. It demonstrates effectiveness on WebShop and Sokoban datasets.

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17008
• PDF: https://arxiv.org/pdf/2512.17008

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

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

#LLM #ReinforcementLearning #AI #MachineLearning #AgenticAI

✨Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding

📝 Summary:
A novel framework, Robust-R1, enhances multimodal large language models' robustness to visual degradations through explicit modeling, supervised fine-tuning, reward-driven alignment, and dynamic reaso...

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17532
• PDF: https://arxiv.org/pdf/2512.17532
• Project Page: https://jqt.me/index.html

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence

📝 Summary:
Proposed Egocentric2Embodiment pipeline translates human egocentric videos into structured training data for robots, enhancing their egocentric understanding and task performance. AI-generated summary...

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.16793
• PDF: https://arxiv.org/pdf/2512.16793
• Project Page: https://zgc-embodyai.github.io/PhysBrain/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models

📝 Summary:
StageVAR accelerates visual autoregressive models by recognizing early stages are critical while later detail-refinement stages can be pruned or approximated. This plug-and-play framework achieves up to 3.4x speedup with minimal quality loss, outperforming existing methods.

🔹 Publication Date: Published on Dec 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.16483
• PDF: https://arxiv.org/pdf/2512.16483
• Github: https://github.com/sen-mao/StageVAR

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

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

#ComputerVision #DeepLearning #ModelAcceleration #AI #NeuralNetworks

✨Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

📝 Summary:
This paper proposes a framework using a semantic-pixel reconstruction objective to adapt encoder features for generation. It creates a compact, semantically rich latent space, leading to state-of-the-art image reconstruction and improved text-to-image generation and editing.

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17909
• PDF: https://arxiv.org/pdf/2512.17909
• Project Page: https://jshilong.github.io/PS-VAE-PAGE/
• Github: https://jshilong.github.io/PS-VAE-PAGE/

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

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

#TextToImage #ImageGeneration #DeepLearning #ComputerVision #AIResearch

✨GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation

📝 Summary:
GroundingME is a new benchmark revealing significant visual grounding gaps in MLLMs, which often hallucinate instead of rejecting ungroundable queries. State-of-the-art models only reach 45.1% accuracy, raising safety concerns. Data-mixture training shows promise in improving their ability to rec...

🔹 Publication Date: Published on Dec 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.17495
• PDF: https://arxiv.org/pdf/2512.17495
• Project Page: https://groundingme.github.io/

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

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

#MLLMs #VisualGrounding #AISafety #AIResearch #Benchmarking

✨HERBench: A Benchmark for Multi-Evidence Integration in Video Question Answering

📝 Summary:
HERBench is a new VideoQA benchmark designed to test multi-evidence integration across time, revealing significant challenges for current Video-LLMs. It requires models to fuse at least three visual cues from distinct segments, with state-of-the-art models performing poorly due to retrieval and f...

🔹 Publication Date: Published on Dec 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.14870
• PDF: https://arxiv.org/pdf/2512.14870
• Project Page: https://herbench.github.io/
• Github: https://github.com/DanBenAmi/HERBench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/DanBenAmi/HERBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research