✨GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

📝 Summary:
GRADE is introduced as the first benchmark for assessing discipline-informed knowledge and reasoning in image editing, revealing significant limitations in current models under knowledge-intensive edi...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12264
• PDF: https://arxiv.org/pdf/2603.12264
• Project Page: https://grade-bench.github.io/
• Github: https://github.com/VisionXLab/GRADE

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

📝 Summary:
A novel framework called Endogenous Chain-of-Thought is proposed to enhance multimodal large language models' reasoning capabilities in diffusion frameworks by enabling iterative thought refinement an...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12252
• PDF: https://arxiv.org/pdf/2603.12252
• Project Page: https://internlm.github.io/EndoCoT/
• Github: https://github.com/InternLM/EndoCoT

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

📝 Summary:
Spatial-TTT enables streaming visual-based spatial intelligence through test-time training that adapts parameters to capture spatial evidence over long video sequences using hybrid architecture and 3D...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12255
• PDF: https://arxiv.org/pdf/2603.12255
• Project Page: https://liuff19.github.io/Spatial-TTT/
• Github: https://github.com/THU-SI/Spatial-TTT

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Tiny Aya: Bridging Scale and Multilingual Depth

📝 Summary:
Tiny Aya demonstrates high-quality multilingual capabilities with 3.35 billion parameters through region-aware posttraining and balanced language performance. AI-generated summary Tiny Aya redefines w...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11510
• PDF: https://arxiv.org/pdf/2603.11510

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Are Video Reasoning Models Ready to Go Outside?

📝 Summary:
ROVA is a training framework that enhances vision-language model robustness under real-world disturbances through spatio-temporal corruption modeling and adaptive sample difficulty assessment. AI-gene...

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.10652
• PDF: https://arxiv.org/pdf/2603.10652
• Project Page: https://robust-video-reason.github.io/
• Github: https://github.com/codepassionor/ROVA

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Geometric Autoencoder for Diffusion Models

📝 Summary:
Geometric Autoencoder (GAE) presents a principled approach to latent diffusion modeling by optimizing semantic supervision, latent manifold stability, and reconstruction robustness through geometric a...

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.10365
• PDF: https://arxiv.org/pdf/2603.10365
• Project Page: https://huggingface.co/sii-research/gae-imagenet256-f16d32
• Github: https://github.com/sii-research/GAE

🔹 Models citing this paper:
• https://huggingface.co/GK50/GAE-Checkpoints
• https://huggingface.co/sii-research/gae-imagenet256-f16d32

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Video-Based Reward Modeling for Computer-Use Agents

📝 Summary:
Video-execution reward modeling enables scalable evaluation of computer-using agents by predicting task success from user instructions and execution videos, outperforming proprietary models across mul...

🔹 Publication Date: Published on Mar 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.10178
• PDF: https://arxiv.org/pdf/2603.10178
• Github: https://github.com/limenlp/ExeVRM

🔹 Models citing this paper:
• https://huggingface.co/lime-nlp/ExeVRM-8B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/lime-nlp/ExeVR-53k

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

📝 Summary:
TeamHOI enables decentralized cooperative human-object interaction using a Transformer-based policy with teammate tokens and a masked adversarial motion prior for realistic multi-agent coordination. A...

🔹 Publication Date: Published on Mar 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.07988
• PDF: https://arxiv.org/pdf/2603.07988
• Project Page: https://splionar.github.io/TeamHOI/
• Github: https://github.com/sail-sg/TeamHOI

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving

📝 Summary:
SoundWeaver accelerates text-to-audio diffusion generation by caching semantically similar audio and dynamically skipping function evaluations, achieving significant latency reduction with minimal qua...

🔹 Publication Date: Published on Mar 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.07865
• PDF: https://arxiv.org/pdf/2603.07865

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning

📝 Summary:
DreamVideo-Omni is a unified framework for video synthesis that enables precise multi-subject identity control and multi-granularity motion manipulation through a two-stage training approach combining...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12257
• PDF: https://arxiv.org/pdf/2603.12257
• Project Page: https://dreamvideo-omni.github.io/
• Github: https://dreamvideo-omni.github.io/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training

📝 Summary:
Research examines the effectiveness of reasoning versus non-reasoning large language model judges in reinforcement learning-based alignment, revealing that reasoning judges prevent reward hacking but ...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12246
• PDF: https://arxiv.org/pdf/2603.12246

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers

📝 Summary:
Elastic Latent Interface Transformer (ELIT) decouples compute from image resolution in diffusion transformers by introducing learnable latent tokens that adaptively prioritize important regions, enabl...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12245
• PDF: https://arxiv.org/pdf/2603.12245
• Project Page: https://snap-research.github.io/elit/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Multi-Task Reinforcement Learning for Enhanced Multimodal LLM-as-a-Judge

📝 Summary:
Multi-Task Reinforcement Learning framework improves multimodal large language models' judgment consistency and generalization across diverse visual tasks. AI-generated summary Multimodal Large Langua...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11665
• PDF: https://arxiv.org/pdf/2603.11665

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks

📝 Summary:
Softmax self-attention models exhibit attention sinks where probability mass concentrates on fixed positions due to normalization constraints, while ReLU attention avoids this behavior. AI-generated s...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11487
• PDF: https://arxiv.org/pdf/2603.11487
• Github: https://github.com/YuvMilo/sinks-are-provably-necessary

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining

📝 Summary:
Large language models trained on reconstructed agent trajectories from multi-agent simulations show improved performance in long-context understanding, coding proficiency, and agentic capabilities. AI...

🔹 Publication Date: Published on Mar 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11103
• PDF: https://arxiv.org/pdf/2603.11103

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse

📝 Summary:
IndexCache reduces sparse attention computation in large language models by reusing top-k token selections across layers, achieving significant speedups with minimal quality loss. AI-generated summary...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12201
• PDF: https://arxiv.org/pdf/2603.12201

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation

📝 Summary:
EVATok is a framework for efficient video tokenization that adapts token assignment based on video content, improving reconstruction quality and generation efficiency through learned routers and adapt...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12267
• PDF: https://arxiv.org/pdf/2603.12267
• Project Page: https://silentview.github.io/EVATok/
• Github: https://github.com/HKU-MMLab/EVATok

🔹 Models citing this paper:
• https://huggingface.co/YuuTennYi/EVATok

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

📝 Summary:
Training Qwen3-8B on DIVE data improves performance across out-of-distribution benchmarks, with diversity scaling outperforming quantity scaling even with less data. AI-generated summary Recent work s...

🔹 Publication Date: Published on Mar 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11076
• PDF: https://arxiv.org/pdf/2603.11076
• Project Page: https://sheep333c.github.io/DIVE/
• Github: https://github.com/sheep333c/DIVE

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EmbTracker: Traceable Black-box Watermarking for Federated Language Models

📝 Summary:
EmbTracker is a server-side black-box watermarking framework for federated language models that provides client-level traceability through unique identity-specific watermarks embedded via backdoor det...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12089
• PDF: https://arxiv.org/pdf/2603.12089

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

📝 Summary:
Mobile-GS enables real-time 3D Gaussian Splatting rendering on mobile devices through depth-aware order-independent rendering, neural view-dependent enhancement, and compression techniques. AI-generat...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11531
• PDF: https://arxiv.org/pdf/2603.11531
• Project Page: https://xiaobiaodu.github.io/mobile-gs-project/
• Github: https://github.com/xiaobiaodu/mobile-gs

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DVD: Deterministic Video Depth Estimation with Generative Priors

📝 Summary:
DVD adapts pre-trained video diffusion models into deterministic single-pass depth regressors using structural anchors, latent manifold rectification, and global affine coherence. This framework achieves state-of-the-art zero-shot video depth estimation with significantly less data, overcoming li...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12250
• PDF: https://arxiv.org/pdf/2603.12250
• Project Page: https://dvd-project.github.io/
• Github: https://github.com/EnVision-Research/DVD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research