✨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

✨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

✨Show, Don't Tell: Morphing Latent Reasoning into Image Generation

📝 Summary:
LatentMorph integrates implicit latent reasoning into text-to-image generation through four lightweight components that enable adaptive self-refinement and improve both efficiency and cognitive alignm...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02227
• PDF: https://arxiv.org/pdf/2602.02227
• Github: https://github.com/EnVision-Research/LatentMorph

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PixelGen: Pixel Diffusion Beats Latent Diffusion with Perceptual Loss

📝 Summary:
PixelGen is a pixel-space diffusion framework that uses perceptual supervision through LPIPS and DINO-based losses to generate high-quality images without requiring VAEs or latent representations. AI-...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02493
• PDF: https://arxiv.org/pdf/2602.02493
• Project Page: https://zehong-ma.github.io/PixelGen/
• Github: https://github.com/Zehong-Ma/PixelGen

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SWE-Universe: Scale Real-World Verifiable Environments to Millions

📝 Summary:
A scalable framework for constructing real-world software engineering environments from GitHub pull requests using an efficient building agent with self-verification and hacking detection capabilities...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02361
• PDF: https://arxiv.org/pdf/2602.02361
• Github: https://huggingface.co/papers?q=GitHub%20pull%20requests

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

📝 Summary:
Post-training of reasoning large language models can be improved by correcting distribution mismatches between supervised fine-tuning and reinforcement learning stages through importance sampling rewe...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01058
• PDF: https://arxiv.org/pdf/2602.01058

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

📝 Summary:
Green-VLA is a five-stage vision-language-action framework for real-world robot deployment that achieves generalization across different robot embodiments through multimodal training and reinforcement...

🔹 Publication Date: Published on Jan 31

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.00919
• PDF: https://arxiv.org/pdf/2602.00919
• Project Page: https://greenvla.github.io
• Github: https://github.com/greenvla/GreenVLA

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LoopViT: Scaling Visual ARC with Looped Transformers

📝 Summary:
Loop-ViT introduces a recursive vision transformer architecture that decouples reasoning depth from model capacity through weight-tied recurrence and dynamic exit mechanisms, achieving superior visual...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02156
• PDF: https://arxiv.org/pdf/2602.02156
• Github: https://github.com/WenjieShu/LoopViT

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training

📝 Summary:
Rubric-ARM framework jointly optimizes rubric generation and judging through reinforcement learning to improve response quality assessment in creative and open-ended tasks. AI-generated summary Standa...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01511
• PDF: https://arxiv.org/pdf/2602.01511

🔹 Models citing this paper:
• https://huggingface.co/OpenRubrics/RubricARM-8B-Rubric
• https://huggingface.co/OpenRubrics/RubricARM-8B-Judge

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

📝 Summary:
PISA is a novel sparse attention method that improves diffusion transformer efficiency by approximating non-critical attention blocks instead of discarding them, achieving faster processing with maint...

🔹 Publication Date: Published on Feb 1

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01077
• PDF: https://arxiv.org/pdf/2602.01077
• Github: https://github.com/xie-lab-ml/piecewise-sparse-attention

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨OVD: On-policy Verbal Distillation

📝 Summary:
On-policy Verbal Distillation (OVD) enables efficient knowledge transfer from teacher to student models by replacing token-level probability matching with trajectory matching using discrete verbal sco...

🔹 Publication Date: Published on Jan 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.21968
• PDF: https://arxiv.org/pdf/2601.21968
• Github: https://OVD.github.io

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space

📝 Summary:
FSVideo is a fast transformer-based image-to-video diffusion framework that uses a compressed video autoencoder, diffusion transformer architecture with enhanced layer memory, and multi-resolution gen...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02092
• PDF: https://arxiv.org/pdf/2602.02092

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning

📝 Summary:
SPARKLING is a framework for mid-stage width expansion in deep learning models that maintains signal preservation and breaks symmetry to stabilize training and reduce computational costs. AI-generated...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02472
• PDF: https://arxiv.org/pdf/2602.02472

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨An Empirical Study of World Model Quantization

📝 Summary:
Post-training quantization effects in world models reveal unique failure modes and trade-offs between accuracy, bit-width, and planning performance, particularly in encoder-predictor module asymmetrie...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.02110
• PDF: https://arxiv.org/pdf/2602.02110
• Github: https://github.com/huawei-noah/noah-research/tree/master/QuantWM

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning

📝 Summary:
A training-free framework enables language model agents to automatically create and optimize tools during inference, improving their reasoning capabilities through self-evolution and memory consolidat...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01983
• PDF: https://arxiv.org/pdf/2602.01983

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Influence Guided Sampling for Domain Adaptation of Text Retrievers

📝 Summary:
An reinforcement learning-based sampling framework adaptively reweights training datasets to improve embedding model performance while reducing GPU costs. AI-generated summary General-purpose open-dom...

🔹 Publication Date: Published on Jan 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.21759
• PDF: https://arxiv.org/pdf/2601.21759

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨INDIBATOR: Diverse and Fact-Grounded Individuality for Multi-Agent Debate in Molecular Discovery

📝 Summary:
Multi-agent systems for molecular discovery that use individualized scientist profiles based on publication and molecular history outperform traditional role-based approaches. AI-generated summary Mul...

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01815
• PDF: https://arxiv.org/pdf/2602.01815

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios

📝 Summary:
AgentIF-OneDay is a new benchmark evaluating AI agents on diverse daily tasks using natural language instructions. It assesses problem-solving, attachment understanding, and file-based outputs across three user-centric categories. Benchmarking shows leading agent products and LLM APIs excel in th...

🔹 Publication Date: Published on Jan 28

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.20613
• PDF: https://arxiv.org/pdf/2601.20613

✨ Datasets citing this paper:
• https://huggingface.co/datasets/xbench/AgentIF-OneDay

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

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

#AIAgents #LLMs #Benchmark #InstructionFollowing #GeneralAI

✨VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration

📝 Summary:
VisionTrim accelerates MLLMs by selecting dominant visual tokens and merging them with text guidance. This training-free framework improves efficiency without performance loss, addressing high computational costs from excessive visual data.

🔹 Publication Date: Published on Jan 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.22674
• PDF: https://arxiv.org/pdf/2601.22674

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

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

#MLLM #VisionTokenCompression #ModelAcceleration #DeepLearning #TrainingFree

✨On the Limits of Layer Pruning for Generative Reasoning in LLMs

📝 Summary:
Layer pruning degrades LLM generative reasoning tasks, unlike classification which recovers well. While finetuning helps, generative reasoning recovery remains fundamentally limited, especially at higher pruning ratios.

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01997
• PDF: https://arxiv.org/pdf/2602.01997
• Github: https://github.com/safal312/on-the-limits-of-layer-pruning

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

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

#LLMs #ModelPruning #AIResearch #GenerativeAI #DeepLearning

✨Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

📝 Summary:
Generalizable Predictive Prompt Selection GPS efficiently selects informative prompts for RL-enhanced language models using Bayesian inference and a lightweight generative model. This method significantly improves training efficiency, final performance, and test-time efficiency.

🔹 Publication Date: Published on Feb 2

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.01970
• PDF: https://arxiv.org/pdf/2602.01970

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

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

#LLM #ReinforcementLearning #PromptEngineering #AI #MachineLearning