✨PhyCo: Learning Controllable Physical Priors for Generative Motion

📝 Summary:
PhyCo enhances video diffusion models with physics-based control through a large-scale dataset, physics-supervised fine-tuning, and vision-language model guidance for improved physical consistency. AI...

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.28169
• PDF: https://arxiv.org/pdf/2604.28169
• Project Page: https://phyco-video.github.io/

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨InteractWeb-Bench: Can Multimodal Agent Escape Blind Execution in Interactive Website Generation?

📝 Summary:
InteractWeb-Bench presents the first multimodal interactive benchmark for website generation under non-expert low-code conditions, addressing semantic misalignment through diverse user agents and inte...

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27419
• PDF: https://arxiv.org/pdf/2604.27419
• Project Page: https://interactweb-bench.wangqiyao.me/
• Github: https://github.com/AIforIP/InteractWeb-Bench

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Co-Evolving Policy Distillation

📝 Summary:
Co-Evolving Policy Distillation enables unified integration of multiple expert capabilities through parallel training and bidirectional policy distillation, outperforming existing methods in multi-mod...

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27083
• PDF: https://arxiv.org/pdf/2604.27083

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control

📝 Summary:
ExoActor uses third-person video generation as a unified interface to model interaction dynamics between robots, environments, and objects, enabling task-conditioned humanoid behaviors through motion ...

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27711
• PDF: https://arxiv.org/pdf/2604.27711
• Project Page: https://baai-agents.github.io/ExoActor/

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Leveraging Verifier-Based Reinforcement Learning in Image Editing

📝 Summary:
This paper introduces Edit-R1, a framework for image editing that uses a chain-of-thought verifier-based reasoning reward model Edit-RRM. Edit-RRM provides fine-grained, principle-based rewards, overcoming limitations of existing models. This approach significantly enhances image editing performa...

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27505
• PDF: https://arxiv.org/pdf/2604.27505

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling

📝 Summary:
LenVM is a token-level framework that models remaining generation length as a value estimation problem. It improves length control and efficiency in autoregressive models, significantly outperforming baselines and enabling continuous control over performance-efficiency trade-offs.

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27039
• PDF: https://arxiv.org/pdf/2604.27039
• Project Page: https://length-value-model.github.io/
• Github: https://length-value-model.github.io/demo/index.html

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Efficient Training on Multiple Consumer GPUs with RoundPipe

📝 Summary:
RoundPipe introduces a novel pipeline scheduling approach that eliminates weight binding constraints in LLM fine-tuning, enabling efficient training on consumer GPUs through dynamic stage distribution...

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27085
• PDF: https://arxiv.org/pdf/2604.27085
• Project Page: https://itcarrot.github.io/RoundPipe/
• Github: https://github.com/ITcarrot/RoundPipe

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

📝 Summary:
Claw-Eval-Live presents a dynamic benchmark for evaluating workflow agents that tracks evolving demands and verifies task execution through detailed logging and structured assessment methods. AI-gener...

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.28139
• PDF: https://arxiv.org/pdf/2604.28139
• Project Page: https://claw-eval-live.github.io
• Github: https://claw-eval-live.github.io

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

💡 Level Up Your IT Career in 2026 – For FREE

Areas covered: #Python #AI #Cisco #PMP #Fortinet #AWS #Azure #Excel #CompTIA #ITIL #Cloud + more

🔗 Download each free resource here:
• Free Courses (Python, Excel, Cyber Security, Cisco, SQL, ITIL, PMP, AWS)
👉https://bit.ly/4ejSFbz

• IT Certs E-book
👉 https://bit.ly/42y8owh

• IT Exams Skill Test
👉 https://bit.ly/42kp7Dv

• Free AI Materials & Support Tools
👉 https://bit.ly/3QEfWek

• Free Cloud Study Guide
👉https://bit.ly/4u8Zb9r

📲 Need exam help? Contact admin: wa.link/40f942

💬 Join our study group (free tips & support): https://chat.whatsapp.com/K3n7OYEXgT1CHGylN6fM5a

✨Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models

📝 Summary:
LLMs prioritize task appropriate reasoning over conflicting instructions. This study shows these conflicts are detectable and that mechanistic interventions can significantly improve instruction following, enhancing LLM controllability.

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27251
• PDF: https://arxiv.org/pdf/2604.27251
• Github: https://github.com/Xingwei-Tan/compliance_sensibility

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #AI #AIControllability #InstructionFollowing #Reasoning

✨Instruction-Guided Poetry Generation in Arabic and Its Dialects

📝 Summary:
A new instruction-based dataset and fine-tuned LLMs enable controllable Arabic poetry generation across Modern Standard Arabic and dialects. This work allows users to create, revise, and continue poems effectively, moving beyond just analysis, as confirmed by strong evaluations.

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27766
• PDF: https://arxiv.org/pdf/2604.27766
• Github: https://github.com/mbzuai-nlp/instructpoet-ar

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #NLP #ArabicAI #GenerativeAI #PoetryGeneration

✨Safety Drift After Fine-Tuning: Evidence from High-Stakes Domains

📝 Summary:
Fine-tuning foundation models causes unpredictable and contradictory changes in safety, invalidating base-model safety evaluations. Safety properties do not persist reliably through adaptation. Explicit re-evaluation of fine-tuned models is crucial to manage risks in high-stakes domains.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24902
• PDF: https://arxiv.org/pdf/2604.24902

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AISafety #FineTuning #FoundationModels #ResponsibleAI #AIResearch

✨ViPO: Visual Preference Optimization at Scale

📝 Summary:
ViPO scales visual preference optimization using Poly-DPO for noisy data and constructing ViPO, a large high-quality dataset. This dual approach yields superior performance, emphasizing that algorithmic adaptability and data quality are crucial.

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24953
• PDF: https://arxiv.org/pdf/2604.24953
• Project Page: https://liming-ai.github.io/ViPO
• Github: https://liming-ai.github.io/ViPO

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisualAI #MachineLearning #DeepLearning #Optimization #DataScience

✨Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization

📝 Summary:
Semi-DPO addresses label noise in multi-dimensional visual preference learning. It treats consistent data as clean and conflicting data as noisy, using iterative refinement via pseudo-labeling. This improves alignment with complex human preferences and achieves state-of-the-art results.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24952
• PDF: https://arxiv.org/pdf/2604.24952
• Project Page: https://liming-ai.github.io/SemiDPO
• Github: https://liming-ai.github.io/SemiDPO

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MachineLearning #SemiSupervisedLearning #DPO #NoisyData #PreferenceLearning

✨FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

📝 Summary:
FlashRT significantly enhances the efficiency of optimization-based prompt injection and knowledge corruption attacks for long-context LLMs. It delivers 2x-7x speedup and 2x-4x GPU memory reduction, enabling systematic and scalable security evaluations.

🔹 Publication Date: Published on Apr 30

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.28157
• PDF: https://arxiv.org/pdf/2604.28157
• Github: https://github.com/wang-yanting/FlashRT

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Step-level Optimization for Efficient Computer-use Agents

📝 Summary:
Computer-use agents are inefficient when using large models for every step. This paper proposes an event-driven cascade that uses small policies by default, escalating to stronger models only when lightweight monitors detect high risk like stalls or semantic drift, thereby optimizing compute.

🔹 Publication Date: Published on Apr 29

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.27151
• PDF: https://arxiv.org/pdf/2604.27151
• Github: https://github.com/yale-nlp/StepWise

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #AgentSystems #ResourceOptimization #EfficientAI #AdaptiveSystems

✨SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

📝 Summary:
SignRoundV2 is a post-training quantization method for LLMs. It achieves competitive, near full-precision accuracy even at extremely low-bits like 2-bits. This is done via layer-wise bit allocation and pre-tuning scale search.

🔹 Publication Date: Published on Dec 4, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.04746
• PDF: https://arxiv.org/pdf/2512.04746
• Project Page: https://github.com/intel/auto-round
• Github: https://github.com/intel/auto-round

🔹 Models citing this paper:
• https://huggingface.co/Intel/MiroThinker-v1.5-30B-gguf-q2ks-mixed-AutoRound
• https://huggingface.co/Intel/DeepSeek-R1-0528-Qwen3-8B-int4-AutoRound

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLMs #Quantization #DeepLearning #AI #MachineLearning

✨Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

📝 Summary:
Nemotron 3 Nano Omni is a new efficient, open multimodal AI model. It natively supports audio, text, images, and video inputs, improving accuracy and efficiency over previous versions. It excels in document understanding and long audio-video comprehension.

🔹 Publication Date: Published on Apr 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.24954
• PDF: https://arxiv.org/pdf/2604.24954

🔹 Models citing this paper:
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4
• https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-FP8

✨ Spaces citing this paper:
• https://huggingface.co/spaces/akhaliq/Nemotron-3-Nano-Omni
• https://huggingface.co/spaces/developerjeremylive/Nemotron-3-Nano-Omni-etheroi

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AI #MultimodalAI #DeepLearning #OpenSourceAI #AIResearch

✨DeepSeek-OCR: Contexts Optical Compression

📝 Summary:
DeepSeek-OCR compresses long contexts via optical 2D mapping to achieve high OCR precision with significantly reduced vision tokens. It shows 97% accuracy at 10x compression, outperforming other OCR models efficiently. This innovation holds practical value for document processing and LLM training...

🔹 Publication Date: Published on Oct 21, 2025

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/deepseek-ocr-contexts-optical-compression
• PDF: https://arxiv.org/pdf/2510.18234
• Github: https://github.com/deepseek-ai/DeepSeek-OCR

🔹 Models citing this paper:
• https://huggingface.co/deepseek-ai/DeepSeek-OCR
• https://huggingface.co/deepseek-ai/DeepSeek-OCR-2
• https://huggingface.co/unsloth/DeepSeek-OCR

✨ Spaces citing this paper:
• https://huggingface.co/spaces/merterbak/DeepSeek-OCR-Demo
• https://huggingface.co/spaces/davidpcm/openclaw-stock-analyst
• https://huggingface.co/spaces/khang119966/DeepSeek-OCR-DEMO

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

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#OCR #AI #DeepLearning #ContextCompression #LLM