✨ROSE: An Intent-Centered Evaluation Metric for NL2SQL

📝 Summary:
ROSE is a new NL2SQL metric addressing unreliable Execution Accuracy. It evaluates if predicted SQL answers user intent via a Prover-Refuter cascade, showing superior agreement with human experts.

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12988
• PDF: https://arxiv.org/pdf/2604.12988

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

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

#NL2SQL #NLP #EvaluationMetrics #AIResearch #DataScience

✨Cross-Tokenizer LLM Distillation through a Byte-Level Interface

📝 Summary:
Byte-Level Distillation BLD is a new simple method for cross-tokenizer LLM knowledge transfer. It uses a shared byte-level interface, converting teacher outputs to byte probabilities for student distillation. BLD performs competitively with complex approaches, suggesting the byte level is a natur...

🔹 Publication Date: Published on Apr 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.07466
• PDF: https://arxiv.org/pdf/2604.07466

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation

📝 Summary:
MM-WebAgent is a hierarchical agentic framework that coordinates AIGC-based element generation for coherent and visually consistent webpage design through joint optimization of layout and multimodal c...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15309
• PDF: https://arxiv.org/pdf/2604.15309
• Github: https://github.com/microsoft/MM-webagent

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking Attack

📝 Summary:
Activation-Scaling Guard (ASGuard) mitigates brittle refusal behaviors in large language models by identifying and recalibrating specific attention heads vulnerable to tense-based jailbreaking attacks...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.25843
• PDF: https://arxiv.org/pdf/2509.25843
• Github: https://github.com/dmis-lab/ASGuard

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

📝 Summary:
HY-World 2.0 is a multi-modal world model framework that generates high-fidelity 3D Gaussian Splatting scenes from diverse inputs using specialized modules for panorama generation, trajectory planning...

🔹 Publication Date: Published on Apr 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14268
• PDF: https://arxiv.org/pdf/2604.14268
• Project Page: https://3d-models.hunyuan.tencent.com/world/
• Github: https://github.com/Tencent-Hunyuan/HY-World-2.0

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

📝 Summary:
Teacher-student cooperation data synthesis framework addresses stylistic divergence in synthetic data for improved model fine-tuning performance. AI-generated summary A widely adopted strategy for mod...

🔹 Publication Date: Published on Mar 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14164
• PDF: https://arxiv.org/pdf/2604.14164
• Github: https://github.com/CoopReason/TESSY

✨ Datasets citing this paper:
• https://huggingface.co/datasets/CoopReason/TESSY-Code-80K

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning

📝 Summary:
LongAct improves long-context reasoning in LLMs by implementing saliency-guided sparse updates based on high-magnitude activation patterns in query and key vectors. AI-generated summary Reinforcement ...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14922
• PDF: https://arxiv.org/pdf/2604.14922

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards

📝 Summary:
UniDoc-RL introduces a reinforcement learning framework for LVLMs that jointly optimizes retrieval, reranking, visual perception, and reasoning through hierarchical decision-making and dense multi-rew...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14967
• PDF: https://arxiv.org/pdf/2604.14967
• Github: https://github.com/deepglint/UniDoc-RL

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨C2: Scalable Rubric-Augmented Reward Modeling from Binary Preferences

📝 Summary:
Cooperative yet Critical reward modeling (C2) enhances reward model reliability by enabling critical collaboration between a reward model and a rubric generator trained exclusively from binary prefere...

🔹 Publication Date: Published on Apr 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13618
• PDF: https://arxiv.org/pdf/2604.13618
• Github: https://github.com/asahi-research/C2

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

📝 Summary:
LeapAlign improves flow matching model fine-tuning by reducing computational costs and enabling stable gradient propagation through shortened trajectory steps while maintaining alignment with human pr...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15311
• PDF: https://arxiv.org/pdf/2604.15311
• Project Page: https://rockeycoss.github.io/leapalign/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DR^{3}-Eval: Towards Realistic and Reproducible Deep Research Evaluation

📝 Summary:
DR$^{3}$-Eval is a benchmark for evaluating deep research agents on multimodal, multi-file report generation, featuring a realistic simulation of web environments and a comprehensive evaluation framew...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14683
• PDF: https://arxiv.org/pdf/2604.14683
• Github: https://github.com/NJU-LINK/DR3-Eval

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems

📝 Summary:
The study analyzes Claude Code's architecture, identifying five motivating human values and tracing them through thirteen design principles to specific implementation choices, including a core while-l...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14228
• PDF: https://arxiv.org/pdf/2604.14228
• Github: https://github.com/VILA-Lab/Dive-into-Claude-Code

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

📝 Summary:
KV Packet is a cache reuse framework that eliminates recomputation overhead in large language models by treating cached documents as immutable packets with trainable soft-token adapters. AI-generated ...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13226
• PDF: https://arxiv.org/pdf/2604.13226
• Github: https://github.com/ChuangtaoChen-TUM/KVPacket

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

📝 Summary:
A unified generator-discriminator framework for autonomous driving motion planning that improves stability and performance through diffusion-based trajectory generation and reinforcement learning opti...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15308
• PDF: https://arxiv.org/pdf/2604.15308
• Project Page: https://hgao-cv.github.io/RAD-2/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

📝 Summary:
HiVLA presents a hierarchical vision-language-action framework that decouples semantic planning from motor control using a diffusion transformer action expert with cascaded cross-attention for improve...

🔹 Publication Date: Published on Apr 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14125
• PDF: https://arxiv.org/pdf/2604.14125
• Project Page: https://tianshuoy.github.io/HiVLA-page/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

📝 Summary:
GlobalSplat introduces a global scene representation framework that achieves compact, consistent 3D Gaussian splatting with reduced computational overhead and improved inference speed. AI-generated su...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15284
• PDF: https://arxiv.org/pdf/2604.15284
• Project Page: https://r-itk.github.io/globalsplat/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Model Capability Dominates: Inference-Time Optimization Lessons from AIMO 3

📝 Summary:
Majority voting improves mathematical reasoning but is limited by correlated errors; diverse reasoning strategies and model capability are more impactful than prompt engineering. AI-generated summary ...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27844
• PDF: https://arxiv.org/pdf/2603.27844
• Project Page: https://www.kaggle.com/code/natnitarach/aimo-3-model-capability-dominate
• Github: https://github.com/nat-nischw/model-capability-dominates-lessons-aimo3

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

📝 Summary:
A new local-first agent memory system implements comprehensive cognitive memory processes with enhanced retrieval and forgetting mechanisms, achieving superior performance in zero-LLM settings. AI-gen...

🔹 Publication Date: Published on Apr 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.04514
• PDF: https://arxiv.org/pdf/2604.04514
• Project Page: https://superlocalmemory.com/
• Github: https://github.com/qualixar/superlocalmemory

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification

📝 Summary:
TRACER trains ML surrogates using LLM classification production traces. These cost-efficient surrogates activate only if they agree with the original LLM above a threshold, saving significant costs. TRACER also provides interpretability for its routing decisions and achieves high coverage.

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14531
• PDF: https://arxiv.org/pdf/2604.14531

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

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

#LLMs #MachineLearning #CostEfficiency #AI #Interpretability

✨OneHOI: Unifying Human-Object Interaction Generation and Editing

📝 Summary:
OneHOI is a unified diffusion transformer framework that consolidates human-object interaction generation and editing into a single conditional denoising process. It uses structured interaction representations to overcome limitations of prior approaches, achieving state-of-the-art results across ...

🔹 Publication Date: Published on Apr 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14062
• PDF: https://arxiv.org/pdf/2604.14062
• Project Page: https://jiuntian.github.io/OneHOI/
• Github: https://github.com/jiuntian/OneHOI

✨ Datasets citing this paper:
• https://huggingface.co/datasets/jiuntian/hoiedit44k
• https://huggingface.co/datasets/jiuntian/IEBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Towards Autonomous Mechanistic Reasoning in Virtual Cells

📝 Summary:
Large language models are enhanced for biological research through a multi-agent framework that generates and validates mechanistic explanations using structured formalism and verified datasets. AI-ge...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.11661
• PDF: https://arxiv.org/pdf/2604.11661
• Project Page: https://valencelabs.substack.com/p/towards-reasoning-in-virtual-cells
• Github: https://github.com/valence-labs/VCR-Agent

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research