✨Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

📝 Summary:
This paper proposes Citation-aware Rubric Rewards CaRR and C-GRPO to enhance deep search agents. CaRR provides fine-grained, citation-aware rewards that promote factual, comprehensive, evidence-grounded reasoning, reducing shortcuts. C-GRPO outperforms standard RL baselines, offering robust agent...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.06021
• PDF: https://arxiv.org/pdf/2601.06021
• Github: https://github.com/THUDM/CaRR

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

📝 Summary:
VideoAR presents a large-scale visual autoregressive framework for video generation that combines multi-scale next-frame prediction with autoregressive modeling, achieving state-of-the-art results wit...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05966
• PDF: https://arxiv.org/pdf/2601.05966

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation

📝 Summary:
DR-LoRA dynamically adjusts LoRA ranks for experts in Mixture-of-Experts models based on task-specific demands, improving parameter efficiency and performance. AI-generated summary Mixture-of-Experts ...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04823
• PDF: https://arxiv.org/pdf/2601.04823

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck

📝 Summary:
Latent Policy Optimization via Iterative Information Bottleneck addresses exploration collapse in LLM reasoning by enabling topological branching of reasoning trajectories through information bottlene...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05870
• PDF: https://arxiv.org/pdf/2601.05870

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

📝 Summary:
Video generation models trained on synthetic physics primitives demonstrate zero-shot generalization to complex real-world scenarios by modeling force propagation through time and space. AI-generated ...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05848
• PDF: https://arxiv.org/pdf/2601.05848
• Project Page: https://goal-force.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨GenCtrl -- A Formal Controllability Toolkit for Generative Models

📝 Summary:
Generative models' controllability is theoretically analyzed through a framework that estimates controllable sets with distribution-free bounds, revealing that controllability is fragile and context-d...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05637
• PDF: https://arxiv.org/pdf/2601.05637

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Over-Searching in Search-Augmented Large Language Models

📝 Summary:
Search-augmented large language models suffer from over-searching behavior that wastes computational resources and introduces hallucinations, with findings showing varied impacts across model types an...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05503
• PDF: https://arxiv.org/pdf/2601.05503

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos

📝 Summary:
NeoVerse is a scalable 4D world model that enables pose-free reconstruction and novel-trajectory video generation from monocular videos with state-of-the-art performance. AI-generated summary In this ...

🔹 Publication Date: Published on Jan 1

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/neoverse-enhancing-4d-world-model-with-in-the-wild-monocular-videos
• PDF: https://arxiv.org/pdf/2601.00393
• Project Page: https://neoverse-4d.github.io/
• Github: https://neoverse-4d.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

📝 Summary:
Large vision-language models are enhanced for image geolocalization by incorporating map-based reasoning and agent-in-the-map loop optimization, achieving superior accuracy compared to existing models...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05432
• PDF: https://arxiv.org/pdf/2601.05432
• Project Page: https://amap-ml.github.io/Thinking-with-Map/
• Github: https://github.com/AMAP-ML/Thinking-with-Map

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning

📝 Summary:
Large language models struggle with long chain-of-thought reasoning due to unstable structural patterns, but a molecular-inspired approach using effective semantic isomers and distribution-transfer-gr...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.06002
• PDF: https://arxiv.org/pdf/2601.06002

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

📝 Summary:
EnvScaler automates the creation of tool-interaction environments through programmatic synthesis, enhancing LLM performance in complex multi-turn, multi-tool tasks via supervised fine-tuning and reinf...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05808
• PDF: https://arxiv.org/pdf/2601.05808
• Github: https://github.com/RUC-NLPIR/EnvScaler

🔹 Models citing this paper:
• https://huggingface.co/XXHStudyHard/EnvScaler-Qwen3-1.7B
• https://huggingface.co/XXHStudyHard/EnvScaler-Qwen3-4B
• https://huggingface.co/XXHStudyHard/EnvScaler-Qwen3-8B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/XXHStudyHard/EnvScaler-SFT-Traj-9K
• https://huggingface.co/datasets/XXHStudyHard/EnvScaler-191-Env
• https://huggingface.co/datasets/XXHStudyHard/EnvScaler-SFT-Scenario

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Can We Predict Before Executing Machine Learning Agents?

📝 Summary:
Autonomous machine learning agents overcome execution bottlenecks by predicting outcomes before physical execution, achieving faster convergence and improved performance through a predict-then-verify ...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05930
• PDF: https://arxiv.org/pdf/2601.05930
• Github: https://github.com/zjunlp/predict-before-execute

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

📝 Summary:
Large language models exhibit brittle beliefs under contextual perturbations, which are better measured by structural consistency metrics and addressed through structure-aware training methods. AI-gen...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05905
• PDF: https://arxiv.org/pdf/2601.05905
• Github: https://github.com/zjunlp/belief

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Orient Anything V2: Unifying Orientation and Rotation Understanding

📝 Summary:
Orient Anything V2 enhances 3D orientation understanding through scalable 3D asset synthesis, symmetry-aware periodic distribution fitting, and multi-frame relative rotation prediction, achieving stat...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05573
• PDF: https://arxiv.org/pdf/2601.05573
• Project Page: https://orient-anythingv2.github.io/
• Github: https://github.com/SpatialVision/Orient-Anything-V2

🔹 Models citing this paper:
• https://huggingface.co/Viglong/OriAnyV2_ckpt

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Viglong/OriAnyV2_Train_Render

✨ Spaces citing this paper:
• https://huggingface.co/spaces/Viglong/Orient-Anything-V2

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SmartSearch: Process Reward-Guided Query Refinement for Search Agents

📝 Summary:
SmartSearch enhances LLM-based search agents through process rewards and query refinement mechanisms that improve intermediate search query quality via a three-stage curriculum learning approach. AI-g...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04888
• PDF: https://arxiv.org/pdf/2601.04888
• Github: https://github.com/MYVAE/SmartSearch?tab=readme-ov-file

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs

📝 Summary:
Multimodal auto-completion leverages visual and textual context to improve real-time prediction accuracy in conversational interfaces, with a router framework enabling efficient model selection based ...

🔹 Publication Date: Published on Jan 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.05851
• PDF: https://arxiv.org/pdf/2601.05851

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentOCR: Reimagining Agent History via Optical Self-Compression

📝 Summary:
AgentOCR reimagines agent history as visual tokens to reduce token consumption and memory in agentic systems. It leverages optical caching and adaptive self-compression. This framework maintains strong performance while significantly cutting token usage and boosting efficiency.

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04786
• PDF: https://arxiv.org/pdf/2601.04786

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MMFormalizer: Multimodal Autoformalization in the Wild

📝 Summary:
MMFormalizer enables multimodal autoformalization by integrating visual perception with formal mathematical reasoning, supporting complex physical domains from classical mechanics to quantum mechanics...

🔹 Publication Date: Published on Jan 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.03017
• PDF: https://arxiv.org/pdf/2601.03017
• Project Page: https://mmformalizer.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

📝 Summary:
The Qwen3-VL-Embedding and Qwen3-VL-Reranker models form an end-to-end multimodal search pipeline, leveraging multi-stage training and cross-attention mechanisms to achieve high-precision retrieval ac...

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://www.arxiv.org/abs/2601.04720
• PDF: https://arxiv.org/pdf/2601.04720
• Github: https://github.com/QwenLM/Qwen3-VL-Embedding

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AnyDepth: Depth Estimation Made Easy

📝 Summary:
A lightweight monocular depth estimation framework uses DINOv3 as visual encoder and a compact transformer decoder to achieve higher accuracy with reduced computational overhead and improved data qual...

🔹 Publication Date: Published on Jan 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.02760
• PDF: https://arxiv.org/pdf/2601.02760
• Project Page: https://aigeeksgroup.github.io/AnyDepth
• Github: https://aigeeksgroup.github.io/AnyDepth

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research