✨InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning

📝 Summary:
Intervention Training improves large language model reasoning by enabling fine-grained credit assignment through targeted corrections that localize errors and enhance reinforcement learning performanc...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14209
• PDF: https://arxiv.org/pdf/2601.14209

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems

📝 Summary:
A comprehensive benchmark for evaluating LLM-based data agents across diverse data science tasks demonstrates superior performance for multimodal agents while highlighting persistent challenges in uns...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.13591
• PDF: https://arxiv.org/pdf/2601.13591

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RemoteVAR: Autoregressive Visual Modeling for Remote Sensing Change Detection

📝 Summary:
RemoteVAR is a visual autoregressive framework for remote sensing change detection that improves upon existing methods through multi-resolution feature fusion and autoregressive training tailored for ...

🔹 Publication Date: Published on Jan 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.11898
• PDF: https://arxiv.org/pdf/2601.11898
• Github: https://github.com/yilmazkorkmaz1/RemoteVAR

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution

📝 Summary:
DARC is a two-stage framework stabilizing LLM self-play by decoupling question generation and using asymmetric self-distillation. This mitigates instability and bootstrapping errors, significantly improving reasoning performance across benchmarks without human annotations.

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.13761
• PDF: https://arxiv.org/pdf/2601.13761
• Github: https://github.com/RUCBM/DARC

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement

📝 Summary:
APOLO framework uses automated prompt optimization through multi-agent collaboration to improve emotion diagnosis accuracy and robustness in mental healthcare applications. AI-generated summary Lingui...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.13481
• PDF: https://arxiv.org/pdf/2601.13481

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Agentic Reasoning for Large Language Models

📝 Summary:
Agentic reasoning redefines LLMs as autonomous agents that plan, act, and learn through continuous interaction in dynamic environments. This survey organizes agentic reasoning by environmental dynamics, from single-agent capabilities to multi-agent collaboration, bridging thought and action throu...

🔹 Publication Date: Published on Jan 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.12538
• PDF: https://arxiv.org/pdf/2601.12538
• Github: https://github.com/weitianxin/Awesome-Agentic-Reasoning

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

📝 Summary:
Render-of-Thought framework converts textual reasoning steps into images using vision-language models to improve reasoning traceability and efficiency while maintaining competitive performance. AI-gen...

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14750
• PDF: https://arxiv.org/pdf/2601.14750

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models

📝 Summary:
Research reveals that causal attention in language models creates information bottlenecks when question-answer options follow context, leading to performance drops of over 14 percentage points compare...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14152
• PDF: https://arxiv.org/pdf/2601.14152

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

📝 Summary:
RebuttalAgent is a multi-agent framework that reframes rebuttal generation as an evidence-centric planning task, improving coverage, faithfulness, and strategic coherence in academic peer review. AI-g...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14171
• PDF: https://arxiv.org/pdf/2601.14171
• Project Page: https://mqleet.github.io/Paper2Rebuttal_ProjectPage/
• Github: https://github.com/AutoLab-SAI-SJTU/Paper2Rebuttal

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨XR: Cross-Modal Agents for Composed Image Retrieval

📝 Summary:
A multi-agent framework for compositional image retrieval that uses specialized agents for generation, filtering, and verification to improve semantic and visual query matching. AI-generated summary R...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14245
• PDF: https://arxiv.org/pdf/2601.14245
• Github: https://01yzzyu.github.io/xr.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Facilitating Proactive and Reactive Guidance for Decision Making on the Web: A Design Probe with WebSeek

📝 Summary:
WebSeek is a mixed-initiative browser extension that enables interactive web data extraction and analysis with AI-assisted guidance and automation. AI-generated summary Web AI agents such as ChatGPT A...

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.15100
• PDF: https://arxiv.org/pdf/2601.15100

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Rethinking Video Generation Model for the Embodied World

📝 Summary:
A comprehensive robotics benchmark evaluates video generation models across multiple task domains and embodiments, revealing deficiencies in physical realism and introducing a large-scale dataset to a...

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.15282
• PDF: https://arxiv.org/pdf/2601.15282
• Project Page: https://dagroup-pku.github.io/ReVidgen.github.io/
• Github: https://github.com/DAGroup-PKU/ReVidgen/

✨ Datasets citing this paper:
• https://huggingface.co/datasets/DAGroup-PKU/RBench
• https://huggingface.co/datasets/DAGroup-PKU/RoVid-X

✨ Spaces citing this paper:
• https://huggingface.co/spaces/DAGroup-PKU/RBench-Leaderboard

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FARE: Fast-Slow Agentic Robotic Exploration

📝 Summary:
FARE is a hierarchical exploration framework that combines large language model reasoning with reinforcement learning control to enable efficient autonomous robot navigation in complex environments. A...

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14681
• PDF: https://arxiv.org/pdf/2601.14681

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RoboBrain 2.5: Depth in Sight, Time in Mind

📝 Summary:
RoboBrain 2.5 enhances embodied AI through improved 3D spatial reasoning and temporal value estimation for more precise manipulation tasks. AI-generated summary We introduce RoboBrain 2.5, a next-gene...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14352
• PDF: https://arxiv.org/pdf/2601.14352
• Project Page: https://superrobobrain.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents

📝 Summary:
MMDeepResearch-Bench evaluates multimodal research agents on report generation with visual evidence, revealing trade-offs between prose quality, citation accuracy, and visual grounding. AI-generated s...

🔹 Publication Date: Published on Jan 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.12346
• PDF: https://arxiv.org/pdf/2601.12346
• Github: https://github.com/AIoT-MLSys-Lab/MMDeepResearch-Bench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/MMDR-2025/MMdeepresearch

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

📝 Summary:
FinVault presents the first execution-grounded security benchmark for financial agents, revealing significant vulnerabilities in current defense mechanisms when applied to real-world financial workflo...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.07853
• PDF: https://arxiv.org/pdf/2601.07853
• Github: https://github.com/aifinlab/FinVault

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems

📝 Summary:
Modern CI/CD pipelines integrating agent-generated code exhibit a structural failure in responsibility attribution. Decisions are executed through formally correct approval processes, yet no entity po...

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.15059
• PDF: https://arxiv.org/pdf/2601.15059

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

📝 Summary:
AgentEHR is a benchmark for autonomous EHR navigation involving complex clinical decision-making in raw data. The RetroSum framework addresses information loss and fractured reasoning through retrospective summarization and evolving experience strategies. RetroSum improves performance by up to 29...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.13918
• PDF: https://arxiv.org/pdf/2601.13918
• Github: https://github.com/BlueZeros/AgentEHR

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics

📝 Summary:
A general coding agent paradigm enables flexible formal theorem proving by directly interfacing with proof assistants and retrieving relevant theorems without task-specific training. AI-generated summ...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14027
• PDF: https://arxiv.org/pdf/2601.14027
• Project Page: https://demo.projectnumina.ai/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Typhoon OCR: Open Vision-Language Model For Thai Document Extraction

📝 Summary:
Typhoon OCR is an open vision-language model for Thai and English document extraction, tackling complex script and unstructured documents. It achieves high accuracy and layout reconstruction comparable to larger proprietary systems, yet is compact and computationally efficient.

🔹 Publication Date: Published on Jan 21

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14722
• PDF: https://arxiv.org/pdf/2601.14722

🔹 Models citing this paper:
• https://huggingface.co/typhoon-ai/typhoon-ocr-7b
• https://huggingface.co/typhoon-ai/typhoon-ocr1.5-2b
• https://huggingface.co/typhoon-ai/typhoon-ocr-3b

✨ Spaces citing this paper:
• https://huggingface.co/spaces/doeqoth/typhoon-ocr

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis

📝 Summary:
Research investigates the relationship between speaker embeddings and phonological rules in accent control for text-to-speech systems, introducing a metric to measure rule preservation versus embeddin...

🔹 Publication Date: Published on Jan 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.14417
• PDF: https://arxiv.org/pdf/2601.14417
• Project Page: https://sav-eng.github.io/icassp_samples.html

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research