✨Coarse-Guided Visual Generation via Weighted h-Transform Sampling

📝 Summary:
This paper presents a novel training-free method for coarse-guided visual generation using h-transform to guide diffusion models. It modifies sampling transition probabilities with a drift function and employs a noise-level-aware schedule. This balances guidance adherence and high-quality synthes...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12057
• PDF: https://arxiv.org/pdf/2603.12057
• Github: https://github.com/HKUST-LongGroup/Coarse-guided-Gen

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks

📝 Summary:
NerVE provides a unified framework for analyzing feed-forward network dynamics in large language models through spectral analysis metrics that reveal information flow organization and optimization imp...

🔹 Publication Date: Published on Mar 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.06922
• PDF: https://arxiv.org/pdf/2603.06922
• Project Page: https://nerve-eigenspectrum.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation

📝 Summary:
ShotVerse introduces a plan-then-control framework for text-driven cinematic multi-shot video generation. It uses a VLM-based planner to generate camera trajectories and a controller for rendering them into video. Supported by a new calibrated dataset, ShotVerse-Bench, it achieves precise, consis...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11421
• PDF: https://arxiv.org/pdf/2603.11421
• Project Page: https://shotverse.github.io/
• Github: https://github.com/Songlin1998/ShotVerse

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing

📝 Summary:
WeEdit presents a systematic approach for text-centric image editing with a scalable data pipeline, multi-language benchmarks, and a two-stage training strategy combining supervised fine-tuning and re...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.11593
• PDF: https://arxiv.org/pdf/2603.11593

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams

📝 Summary:
OmniStream is a unified visual backbone that processes streaming video data through causal spatiotemporal attention and 3D rotary positional embeddings, enabling general-purpose visual understanding a...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12265
• PDF: https://arxiv.org/pdf/2603.12265
• Project Page: https://go2heart.github.io/omnistream/
• Github: https://github.com/Go2Heart/OmniStream

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation

📝 Summary:
Reinforcement learning framework with novel reward modeling and benchmarking approaches improves fidelity and instruction adherence in image editing and text-to-image generation. AI-generated summary ...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12247
• PDF: https://arxiv.org/pdf/2603.12247
• Project Page: https://firm-reward.github.io/
• Github: https://github.com/VisionXLab/FIRM-Reward

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections

📝 Summary:
MADQA benchmark evaluates multimodal agents' strategic reasoning capabilities through diverse PDF document questions, revealing gaps between human-level accuracy and efficient reasoning performance. A...

🔹 Publication Date: Published on Mar 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.12180
• PDF: https://arxiv.org/pdf/2603.12180
• Project Page: https://huggingface.co/spaces/Snowflake/MADQA-Leaderboard
• Github: https://github.com/OxRML/MADQA

✨ Datasets citing this paper:
• https://huggingface.co/datasets/OxRML/MADQA

✨ Spaces citing this paper:
• https://huggingface.co/spaces/Snowflake/MADQA-Leaderboard

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨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