✨Counting to Four is still a Chore for VLMs

📝 Summary:
Vision-language models exhibit counting failures due to reduced visual evidence utilization in later language layers, which can be mitigated through modality attention share interventions. AI-generate...

🔹 Publication Date: Published on Apr 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.10039
• PDF: https://arxiv.org/pdf/2604.10039
• Project Page: https://huggingface.co/papers?q=modality%20projection%20stage
• Github: https://github.com/leduy99/-CVPRW26-Modality-Attention-Share

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Panoptic Pairwise Distortion Graph

📝 Summary:
Researchers introduce a novel approach to image assessment by representing image pairs as structured distortion graphs that capture region-level degradation information, challenging existing multimoda...

🔹 Publication Date: Published on Apr 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.11004
• PDF: https://arxiv.org/pdf/2604.11004
• Project Page: https://aismartperception.github.io/distortion-graph/
• Github: https://github.com/AISmartPerception/distortion-graphs

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

📝 Summary:
AggAgent enables efficient parallel test-time scaling for long-horizon agentic tasks by aggregating trajectories through a lightweight agent that navigates and synthesizes information on demand. AI-ge...

🔹 Publication Date: Published on Apr 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.11753
• PDF: https://arxiv.org/pdf/2604.11753

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Efficient RL Training for LLMs with Experience Replay

📝 Summary:
Experience replay techniques for large language model post-training balance staleness variance and computational costs while maintaining performance and policy entropy. AI-generated summary While Expe...

🔹 Publication Date: Published on Apr 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.08706
• PDF: https://arxiv.org/pdf/2604.08706

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨TRACE: Capability-Targeted Agentic Training

📝 Summary:
TRACE improves LLM agents by identifying capability gaps from trajectory comparisons. It then creates targeted training environments for specific skills, using LoRA adapters for efficient, environment-specific self-improvement. This boosts performance on customer service and tool use tasks, outpe...

🔹 Publication Date: Published on Apr 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.05336
• PDF: https://arxiv.org/pdf/2604.05336
• Project Page: https://scalingintelligence.stanford.edu/blogs/trace/
• Github: https://github.com/ScalingIntelligence/TRACE

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

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

#LLMAgents #AI #MachineLearning #LoRA #DeepLearning

✨IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs

📝 Summary:
IceCache is a novel KV cache management strategy for long-sequence LLMs that uses semantic token clustering with PagedAttention. It significantly improves memory efficiency while maintaining high accuracy, reducing the KV cache budget by 75% and outperforming other offloading methods.

🔹 Publication Date: Published on Apr 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.10539
• PDF: https://arxiv.org/pdf/2604.10539
• Project Page: https://yuzhenmao.github.io/IceCache/
• Github: https://github.com/yuzhenmao/IceCache

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ATANT: An Evaluation Framework for AI Continuity

📝 Summary:
ATANT presents an open framework for evaluating AI system continuity through a 10-checkpoint methodology using a 250-story corpus across 6 life domains, achieving 100% accuracy in cumulative testing. ...

🔹 Publication Date: Published on Apr 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.06710
• PDF: https://arxiv.org/pdf/2604.06710
• Project Page: https://kenoticlabs.com
• Github: https://github.com/Kenotic-Labs/ATANT

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Kenotic-Labs/ATANTV1.0-corpus

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

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

#AI #AIEvaluation #AIConsistency #Research #DataScience

✨Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing

📝 Summary:
Audio-Omni presents the first framework unifying audio generation and editing across diverse audio domains. It combines a multimodal LLM and diffusion transformer, introduces AudioEdit, and achieves state-of-the-art results.

🔹 Publication Date: Published on Apr 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.10708
• PDF: https://arxiv.org/pdf/2604.10708
• Project Page: https://zeyuet.github.io/Audio-Omni/
• Github: https://github.com/ZeyueT/Audio-Omni

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory

📝 Summary:
RoMem introduces a temporal knowledge graph module that uses semantic speed gates and continuous phase rotation to distinguish persistent from evolving facts, achieving superior performance in tempora...

🔹 Publication Date: Published on Apr 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.11544
• PDF: https://arxiv.org/pdf/2604.11544

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

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

#TemporalKnowledgeGraphs #AgenticMemory #PhaseRotation #AIResearch #MachineLearning

✨Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

📝 Summary:
On-policy distillation dynamics in large language models depend on compatible thinking patterns between teacher and student models, with successful distillation characterized by alignment on high-prob...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13016
• PDF: https://arxiv.org/pdf/2604.13016
• Github: https://github.com/thunlp/OPD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Toward Autonomous Long-Horizon Engineering for ML Research

📝 Summary:
AiScientist enables autonomous long-horizon ML research engineering by combining hierarchical orchestration with durable state management, achieving superior performance on benchmark tasks through str...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13018
• PDF: https://arxiv.org/pdf/2604.13018
• Github: https://github.com/AweAI-Team/AiScientist

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks

📝 Summary:
Sequence-Level PPO addresses instability in long-chain-of-thought reasoning by reformulating the process as a contextual bandit problem with decoupled value functions for improved efficiency. AI-gener...

🔹 Publication Date: Published on Apr 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.08865
• PDF: https://arxiv.org/pdf/2604.08865
• Github: https://github.com/sustech-nlp/SPPO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting

📝 Summary:
Habitat-GS extends Habitat-Sim by integrating 3D Gaussian Splatting for photorealistic rendering and gaussian avatars for dynamic human modeling, enabling improved agent generalization and human-aware...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12626
• PDF: https://arxiv.org/pdf/2604.12626
• Project Page: https://zju3dv.github.io/habitat-gs/
• Github: https://github.com/zju3dv/habitat-gs

✨ Datasets citing this paper:
• https://huggingface.co/datasets/RukawaY/gs_scenes

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Rethinking the Diffusion Model from a Langevin Perspective

📝 Summary:
The article provides a unified Langevin perspective on diffusion models, clarifying their theoretical foundations and connections between different mathematical formulations. AI-generated summary Diff...

🔹 Publication Date: Published on Apr 12

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.10465
• PDF: https://arxiv.org/pdf/2604.10465
• Project Page: https://iclr-blogposts.github.io/2026/blog/2026/rethinking-diffusion-langevin/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Generative Refinement Networks for Visual Synthesis

📝 Summary:
Generative Refinement Networks introduce a novel visual synthesis approach that combines hierarchical binary quantization with adaptive refinement mechanisms to improve computational efficiency and vi...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13030
• PDF: https://arxiv.org/pdf/2604.13030
• Github: https://github.com/MGenAI/GRN

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

📝 Summary:
Lightning OPD enables efficient offline on-policy distillation for large language models by enforcing teacher consistency and eliminating the need for live teacher inference servers. AI-generated summ...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13010
• PDF: https://arxiv.org/pdf/2604.13010

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

📝 Summary:
Nemotron 3 Super is a 120 billion parameter hybrid Mamba-Attention Mixture-of-Experts model pre-trained in NVFP4 with LatentMoE architecture and MTP layers for accelerated inference, achieving superio...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12374
• PDF: https://arxiv.org/pdf/2604.12374

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Towards Long-horizon Agentic Multimodal Search

📝 Summary:
A novel long-horizon multimodal deep search framework called LMM-Searcher is introduced, featuring a file-based visual representation mechanism and progressive visual loading to handle heterogeneous i...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12890
• PDF: https://arxiv.org/pdf/2604.12890
• Github: https://github.com/RUCAIBox/LMM-Searcher

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance

📝 Summary:
KnowRL is a knowledge-guided reinforcement learning framework that improves reasoning in language models by optimizing compact, interaction-aware guidance subsets through constrained subset search and...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12627
• PDF: https://arxiv.org/pdf/2604.12627
• Github: https://github.com/Hasuer/KnowRL

🔹 Models citing this paper:
• https://huggingface.co/HasuerYu/KnowRL-Nemotron-1.5B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/HasuerYu/KnowRL-KP-Annotations
• https://huggingface.co/datasets/HasuerYu/KnowRL-Train-Data

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Self-Adversarial One Step Generation via Condition Shifting

📝 Summary:
APEx enables efficient one-step text-to-image synthesis by eliminating adversarial training through endogenous gradient estimation from flow models, achieving superior quality and speed compared to ex...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.12322
• PDF: https://arxiv.org/pdf/2604.12322
• Github: https://github.com/LINs-lab/APEX

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Lyra 2.0: Explorable Generative 3D Worlds

📝 Summary:
Lyra 2.0 enables large-scale 3D scene creation through persistent video generation that addresses spatial forgetting and temporal drifting issues in long-horizon video models. AI-generated summary Rec...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13036
• PDF: https://arxiv.org/pdf/2604.13036

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research