✨TranslateGemma Technical Report

📝 Summary:
TranslateGemma enhances Gemma 3's multilingual capabilities through two-stage fine-tuning with synthetic and human-translated data, achieving superior translation quality with improved efficiency. AI-...

🔹 Publication Date: Published on Jan 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09012
• PDF: https://arxiv.org/pdf/2601.09012

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understanding

📝 Summary:
OpenVoxel enables open-vocabulary 3D scene understanding through training-free grouping and captioning of sparse voxels using Vision Language Models and Multi-modal Large Language Models. AI-generated...

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09575
• PDF: https://arxiv.org/pdf/2601.09575

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

📝 Summary:
EvoFSM is a structured self-evolving framework for LLM agents that uses finite state machines to improve adaptability while maintaining control through constrained optimization and memory mechanisms. ...

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09465
• PDF: https://arxiv.org/pdf/2601.09465

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The AI Hippocampus: How Far are We From Human Memory?

📝 Summary:
Memory mechanisms in large language models and multi-modal language models are categorized into implicit, explicit, and agentic paradigms, supporting enhanced reasoning, adaptability, and contextual f...

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09113
• PDF: https://arxiv.org/pdf/2601.09113

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ExpSeek: Self-Triggered Experience Seeking for Web Agents

📝 Summary:
ExpSeek enables web agents to proactively seek experience during interaction using entropy-based timing and tailored content. This step-level approach significantly improves performance over passive methods, even when using smaller experience models.

🔹 Publication Date: Published on Jan 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.08605
• PDF: https://arxiv.org/pdf/2601.08605

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models

📝 Summary:
Imagine-then-Plan framework enables agent learning through adaptive lookahead imagination, combining imagined trajectories with current observations to guide policy learning in complex task scenarios....

🔹 Publication Date: Published on Jan 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.08955
• PDF: https://arxiv.org/pdf/2601.08955

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models

📝 Summary:
Diffusion Transformer-based image-to-video models suffer from condition isolation where visual attention becomes detached from text guidance; focal guidance addresses this through fine-grained semanti...

🔹 Publication Date: Published on Jan 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.07287
• PDF: https://arxiv.org/pdf/2601.07287

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

📝 Summary:
DASD-4B-Thinking is a new lightweight model achieving state-of-the-art reasoning by enhancing sequence-level distillation. It addresses limitations in current teacher-student knowledge transfer by better capturing the teachers full output distribution, using significantly fewer training samples.

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09088
• PDF: https://arxiv.org/pdf/2601.09088
• Project Page: https://github.com/D2I-ai/dasd-thinking
• Github: https://github.com/D2I-ai/dasd-thinking

🔹 Models citing this paper:
• https://huggingface.co/Alibaba-Apsara/DASD-4B-Thinking
• https://huggingface.co/Alibaba-Apsara/DASD-30B-A3B-Thinking-Preview

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b
• https://huggingface.co/datasets/Alibaba-Apsara/Superior-Reasoning-SFT-gpt-oss-120b-Logprob

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

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

#AI #MachineLearning #LLM #KnowledgeDistillation #ChainOfThought

✨Geometric Stability: The Missing Axis of Representations

📝 Summary:
This paper introduces geometric stability, a new metric quantifying how reliably representational geometry holds under perturbation. It is distinct from similarity, offering complementary insights for safety monitoring, controllability, and model selection across diverse systems.

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09173
• PDF: https://arxiv.org/pdf/2601.09173
• Github: https://github.com/prashantcraju/geometric-stability

🔹 Models citing this paper:
• https://huggingface.co/pcr2120/shesha-geometry

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

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

#GeometricStability #RepresentationalGeometry #MachineLearning #AIResearch #ModelEvaluation

✨Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning

📝 Summary:
Omni-R1 proposes unified generative multimodal reasoning. It uses intermediate image generation to enable diverse skills across tasks. Omni-R1-Zero, needing no multimodal data, matches or exceeds its performance, showing a promising path.

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09536
• PDF: https://arxiv.org/pdf/2601.09536

🔹 Models citing this paper:
• https://huggingface.co/ModalityDance/Omni-R1
• https://huggingface.co/ModalityDance/Omni-R1-Zero

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ModalityDance/Omni-Bench

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

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

#MultimodalAI #GenerativeAI #DeepLearning #ComputerVision #AIResearch

✨LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm

📝 Summary:
LoongFlow is a self-evolving agent that integrates LLMs into a cognitive Plan-Execute-Summarize PES paradigm for directed evolutionary search. It prevents premature convergence by balancing exploration and exploitation with a hybrid memory system. LoongFlow achieves superior solutions 60% more ef...

🔹 Publication Date: Published on Dec 30, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.24077
• PDF: https://arxiv.org/pdf/2512.24077
• Project Page: https://github.com/baidu-baige/LoongFlow
• Github: https://github.com/baidu-baige/LoongFlow

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

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

#EvolutionarySearch #LLMs #CognitiveAI #AIAgents #Optimization

🎁❗️TODAY FREE❗️🎁

Entry to our VIP channel is completely free today. Tomorrow it will cost $500! 🔥

JOIN 👇

https://t.iss.one/+DBdNGbxImzgxMDBi
https://t.iss.one/+DBdNGbxImzgxMDBi
https://t.iss.one/+DBdNGbxImzgxMDBi

✨Cluster Workload Allocation: Semantic Soft Affinity Using Natural Language Processing

📝 Summary:
This paper introduces an LLM-based approach to interpret natural language hints for cluster workload allocation. It achieved over 95% accuracy and improved placement compared to traditional methods, simplifying workload orchestration.

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09282
• PDF: https://arxiv.org/pdf/2601.09282

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

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

#ClusterAllocation #NLP #LLMs #WorkloadOrchestration #AIResearch

✨SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

📝 Summary:
SampoNLP is a new corpus-free toolkit for creating morphological lexicons for Uralic languages. It was used to systematically evaluate BPE tokenizers, identifying optimal vocabulary sizes and demonstrating BPE's limitations for these highly agglutinative languages.

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04469
• PDF: https://arxiv.org/pdf/2601.04469
• Github: https://github.com/AragonerUA/SampoNLP

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

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

#NLP #ComputationalLinguistics #Morphology #Tokenization #UralicLanguages

✨DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing

📝 Summary:
DPWriter is an RL framework that improves output diversity in LLM creative writing. It introduces Diverse Planning Branching and group-aware diversity rewards to encourage distinct generation trajectories. This approach significantly boosts diversity without compromising quality.

🔹 Publication Date: Published on Jan 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09609
• PDF: https://arxiv.org/pdf/2601.09609

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

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

#ReinforcementLearning #LLM #CreativeWriting #AI #NLP

✨No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning

📝 Summary:
ECHO is an RL framework addressing stale critics in LLM agent training. It jointly optimizes policy and critic through a co-evolutionary loop and cascaded rollouts. This ensures synchronized feedback, leading to more stable training and higher task success in open-world environments.

🔹 Publication Date: Published on Jan 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.06794
• PDF: https://arxiv.org/pdf/2601.06794

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

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

#ReinforcementLearning #LLMAgents #MachineLearning #AIResearch #OpenWorldAI

✨Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

📝 Summary:
Flow Equivariant World Models unify self-motion and external object motion as Lie group flows, enabling stable, symmetry-guided representations. They outperform other models in partially observed environments, particularly for long-term prediction and out-of-view dynamics, leading to data-efficie...

🔹 Publication Date: Published on Jan 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.01075
• PDF: https://arxiv.org/pdf/2601.01075
• Project Page: https://flowequivariantworldmodels.github.io/
• Github: https://github.com/hlillemark/flowm

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

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

#WorldModels #Equivariance #MachineLearning #AI #DeepLearning

✨sui-1: Grounded and Verifiable Long-Form Summarization

📝 Summary:
sui-1 is a 24B model producing verifiable abstractive summaries with inline citations. It uses synthetic data training to significantly outperform larger models, showing task-specific training beats scale for grounded summarization.

🔹 Publication Date: Published on Jan 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.08472
• PDF: https://arxiv.org/pdf/2601.08472

🔹 Models citing this paper:
• https://huggingface.co/ellamind/sui-1-24b
• https://huggingface.co/ellamind/sui-1-24b-fp8

✨ Spaces citing this paper:
• https://huggingface.co/spaces/ellamind/sui-demo

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG

📝 Summary:
OpenDecoder enhances retrieval-augmented generation by explicitly evaluating retrieved information quality through relevance, ranking, and query performance prediction scores, improving robustness to ...

🔹 Publication Date: Published on Jan 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.09028
• PDF: https://arxiv.org/pdf/2601.09028

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning

📝 Summary:
SCALER is an RL framework for language models that sustains effective training signals in reasoning tasks. It uses adaptive environment design and scalable synthesis of diverse problems to prevent reward sparsity and overfitting, enabling sustained performance improvements.

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04809
• PDF: https://arxiv.org/pdf/2601.04809

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research