🔹 Title: Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

🔹 Publication Date: Published on Oct 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.03222
• PDF: https://arxiv.org/pdf/2510.03222
• Github: https://github.com/CarlanLark/Lp-Reg-dev

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08431
• PDF: https://arxiv.org/pdf/2510.08431
• Github: https://github.com/NVlabs/rcm

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: UniVideo: Unified Understanding, Generation, and Editing for Videos

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08377
• PDF: https://arxiv.org/pdf/2510.08377
• Project Page: https://congwei1230.github.io/UniVideo/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: First Try Matters: Revisiting the Role of Reflection in Reasoning Models

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08308
• PDF: https://arxiv.org/pdf/2510.08308

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07172
• PDF: https://arxiv.org/pdf/2510.07172
• Github: https://github.com/HKUST-KnowComp/NewtonBench

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08555
• PDF: https://arxiv.org/pdf/2510.08555
• Project Page: https://onevfall.github.io/project_page/videocanvas/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Recycling Pretrained Checkpoints: Orthogonal Growth of Mixture-of-Experts for Efficient Large Language Model Pre-Training

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08008
• PDF: https://arxiv.org/pdf/2510.08008

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07429
• PDF: https://arxiv.org/pdf/2510.07429

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.06915
• PDF: https://arxiv.org/pdf/2510.06915
• Github: https://github.com/LCM-Lab/LongRM

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08559
• PDF: https://arxiv.org/pdf/2510.08559
• Project Page: https://scivideobench.github.io/
• Github: https://github.com/dengandong/SciVideoBench

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08549
• PDF: https://arxiv.org/pdf/2510.08549
• Project Page: https://nothingbutbut.github.io/era/
• Github: https://github.com/nothingbutbut/era

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Reinforcing Diffusion Models by Direct Group Preference Optimization

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08425
• PDF: https://arxiv.org/pdf/2510.08425

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Training-Free Group Relative Policy Optimization

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08191
• PDF: https://arxiv.org/pdf/2510.08191
• Github: https://github.com/TencentCloudADP/youtu-agent/tree/training_free_GRPO

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08143
• PDF: https://arxiv.org/pdf/2510.08143
• Project Page: https://shiandu.github.io/UniMMVSR-website/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: A^2Search: Ambiguity-Aware Question Answering with Reinforcement Learning

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07958
• PDF: https://arxiv.org/pdf/2510.07958
• Github: https://github.com/zfj1998/A2Search

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07242
• PDF: https://arxiv.org/pdf/2510.07242

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: The Alignment Waltz: Jointly Training Agents to Collaborate for Safety

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08240
• PDF: https://arxiv.org/pdf/2510.08240

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08551
• PDF: https://arxiv.org/pdf/2510.08551
• Github: https://city-super.github.io/artdeco/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs

🔹 Publication Date: Published on Oct 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.07499
• PDF: https://arxiv.org/pdf/2510.07499

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08276
• PDF: https://arxiv.org/pdf/2510.08276

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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

🔹 Title: DexNDM: Closing the Reality Gap for Dexterous In-Hand Rotation via Joint-Wise Neural Dynamics Model

🔹 Publication Date: Published on Oct 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.08556
• PDF: https://arxiv.org/pdf/2510.08556
• Github: https://meowuu7.github.io/DexNDM/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

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