✨FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents

📝 Summary:
FS-Researcher is a dual-agent framework that scales LLM research tasks beyond context window limits. It uses a file system as persistent external memory, enabling a Context Builder and Report Writer to achieve state-of-the-art report quality and effective test-time scaling.

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01566
• PDF: https://arxiv.org/pdf/2602.01566

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing

📝 Summary:
Visual Instruction Benchmark for Image Editing introduces a three-level interaction hierarchy for evaluating visual instruction following capabilities in generative models. AI-generated summary Recent...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01851
• PDF: https://arxiv.org/pdf/2602.01851
• Github: https://vibe-benchmark.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Ebisu: Benchmarking Large Language Models in Japanese Finance

📝 Summary:
A Japanese financial language understanding benchmark named Ebisu is introduced, featuring two expert-annotated tasks that evaluate implicit commitment recognition and hierarchical financial terminolo...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01479
• PDF: https://arxiv.org/pdf/2602.01479

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PISCES: Annotation-free Text-to-Video Post-Training via Optimal Transport-Aligned Rewards

📝 Summary:
PISCES is an annotation-free text-to-video generation method that uses dual optimal transport-aligned rewards to improve visual quality and semantic alignment without human preference annotations. AI-...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01624
• PDF: https://arxiv.org/pdf/2602.01624

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PromptRL: Prompt Matters in RL for Flow-Based Image Generation

📝 Summary:
Flow matching models for text-to-image generation are enhanced through a reinforcement learning framework that addresses sample inefficiency and prompt overfitting by incorporating language models for...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01382
• PDF: https://arxiv.org/pdf/2602.01382
• Github: https://github.com/G-U-N/UniRL

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

📝 Summary:
Adaptive Ability Decomposing (A²D) enhances reinforcement learning with verifiable rewards by decomposing complex questions into simpler sub-questions, improving LLM reasoning through guided explorati...

🔹 Publication Date: Published on Jan 31

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.00759
• PDF: https://arxiv.org/pdf/2602.00759

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

📝 Summary:
Small language models can effectively evaluate outputs by leveraging internal representations rather than generating responses, enabling a more efficient and interpretable evaluation approach through ...

🔹 Publication Date: Published on Jan 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.22588
• PDF: https://arxiv.org/pdf/2601.22588
• Github: https://github.com/zhuochunli/Representation-as-a-judge

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora

📝 Summary:
WildGraphBench evaluates GraphRAG performance in realistic scenarios using Wikipedia's structured content to assess multi-fact aggregation and summarization capabilities across diverse document types....

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02053
• PDF: https://arxiv.org/pdf/2602.02053

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

📝 Summary:
RLAnything enhances reinforcement learning for LLMs and agents through dynamic model optimization and closed-loop feedback mechanisms that improve policy and reward model training. AI-generated summar...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02488
• PDF: https://arxiv.org/pdf/2602.02488
• Project Page: https://huggingface.co/collections/Gen-Verse/open-agentrl
• Github: https://github.com/Gen-Verse/Open-AgentRL

🔹 Models citing this paper:
• https://huggingface.co/Gen-Verse/RLAnything-Alf-7B
• https://huggingface.co/Gen-Verse/RLAnything-Alf-Reward-14B
• https://huggingface.co/Gen-Verse/RLAnything-OS-Reward-8B

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles

📝 Summary:
Deep Research Agents demonstrate capabilities in autonomous information retrieval but show significant gaps when evaluated against expert-level Wikipedia articles using a new live benchmark and compre...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01590
• PDF: https://arxiv.org/pdf/2602.01590

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Closing the Loop: Universal Repository Representation with RPG-Encoder

📝 Summary:
RPG-Encoder framework transforms repository comprehension and generation into a unified cycle by encoding code into high-fidelity Repository Planning Graph representations that improve understanding a...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02084
• PDF: https://arxiv.org/pdf/2602.02084
• Project Page: https://ayanami2003.github.io/RPG-Encoder/
• Github: https://github.com/microsoft/RPG-ZeroRepo

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Toward Cognitive Supersensing in Multimodal Large Language Model

📝 Summary:
MLLMs equipped with Cognitive Supersensing and Latent Visual Imagery Prediction demonstrate enhanced cognitive reasoning capabilities through integrated visual and textual reasoning pathways. AI-gener...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01541
• PDF: https://arxiv.org/pdf/2602.01541
• Project Page: https://pediamedai.com/Cognition-MLLM/cogsense/
• Github: https://github.com/PediaMedAI/Cognition-MLLM

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

📝 Summary:
A dual-stream framework called InteractAvatar is presented for generating talking avatars that can interact with objects in their environment, addressing challenges in grounded human-object interactio...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01538
• PDF: https://arxiv.org/pdf/2602.01538
• Github: https://github.com/angzong/InteractAvatar

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning

📝 Summary:
Visual metaphor transfer enables creative AI systems to decompose abstract conceptual relationships from reference images and reapply them to new subjects through a multi-agent framework grounded in c...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01335
• PDF: https://arxiv.org/pdf/2602.01335

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

📝 Summary:
Vision-DeepResearch benchmark addresses limitations in evaluating visual-textual search capabilities of multimodal models by introducing realistic evaluation conditions and improving visual retrieval ...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02185
• PDF: https://arxiv.org/pdf/2602.02185
• Project Page: https://osilly.github.io/Vision-DeepResearch/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

📝 Summary:
Vision-DeepResearch introduces a multimodal deep-research paradigm enabling multi-turn, multi-entity, and multi-scale visual and textual search with deep-research capabilities integrated through cold-...

🔹 Publication Date: Published on Jan 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.22060
• PDF: https://arxiv.org/pdf/2601.22060
• Project Page: https://osilly.github.io/Vision-DeepResearch/
• Github: https://github.com/Osilly/Vision-DeepResearch

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Kimi K2.5: Visual Agentic Intelligence

📝 Summary:
Kimi K2.5 is an open-source multimodal agentic model that enhances text and vision processing through joint optimization techniques and introduces Agent Swarm for parallel task execution. AI-generated...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02276
• PDF: https://arxiv.org/pdf/2602.02276
• Project Page: https://huggingface.co/moonshotai/Kimi-K2.5

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

📝 Summary:
A novel Causal Forcing method addresses the architectural gap in distilling bidirectional video diffusion models into autoregressive models by using AR teachers for ODE initialization, significantly i...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02214
• PDF: https://arxiv.org/pdf/2602.02214
• Project Page: https://thu-ml.github.io/CausalForcing.github.io/
• Github: https://thu-ml.github.io/CausalForcing.github.io/

🔹 Models citing this paper:
• https://huggingface.co/zhuhz22/Causal-Forcing

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation

📝 Summary:
Mind-Brush presents a unified agentic framework for text-to-image generation that dynamically retrieves multimodal evidence and employs reasoning tools to improve understanding of implicit user intent...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01756
• PDF: https://arxiv.org/pdf/2602.01756
• Github: https://github.com/PicoTrex/Mind-Brush

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Interacted Planes Reveal 3D Line Mapping

📝 Summary:
LiP-Map presents a line-plane joint optimization framework that explicitly models learnable line and planar primitives for accurate 3D line mapping in man-made environments. AI-generated summary 3D li...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01296
• PDF: https://arxiv.org/pdf/2602.01296
• Github: https://github.com/calmke/LiPMAP

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

📝 Summary:
UniReason integrates text-to-image generation and image editing through a dual reasoning paradigm that enhances planning with world knowledge and uses editing for visual refinement, achieving superior...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02437
• PDF: https://arxiv.org/pdf/2602.02437

🔹 Models citing this paper:
• https://huggingface.co/Alex11556666/UniReason

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research