✨Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

📝 Summary:
This paper proposes a few-shot retrieval-augmented test-time adapter for open-vocabulary segmentation. It uses learned per-query fusion of textual and visual support features to overcome zero-shot limitations. This approach significantly narrows the performance gap with supervised segmentation wh...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23339
• PDF: https://arxiv.org/pdf/2602.23339
• Github: https://github.com/TilemahosAravanis/Retrieve-and-Segment

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨General Agent Evaluation

📝 Summary:
General-purpose agents lack systematic evaluation. This paper proposes principles, a protocol, and Exgentic framework to assess their versatility. Experiments show these agents generalize across diverse environments, performing well without specific tuning.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22953
• PDF: https://arxiv.org/pdf/2602.22953
• Project Page: https://www.exgentic.ai
• Github: https://github.com/Exgentic/exgentic

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨SciReasoner: Laying the Scientific Reasoning Ground Across Disciplines

📝 Summary:
A scientific reasoning foundation model pre-trained on diverse scientific data supports multiple tasks and enhances cross-domain generalization and fidelity through specialized training techniques. AI...

🔹 Publication Date: Published on Sep 25, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2509.21320
• PDF: https://arxiv.org/pdf/2509.21320
• Github: https://github.com/open-sciencelab/SciReason

🔹 Models citing this paper:
• https://huggingface.co/SciReason/SciReasoner-8B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/SciReason/SciLM-Instruction_Tuning
• https://huggingface.co/datasets/SciReason/SciLM-CoT_ColdStart

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation

📝 Summary:
MedCLIPSeg adapts CLIP for medical image segmentation using patch-level embeddings and probabilistic attention. This enables data-efficient, generalizable, and uncertainty-aware segmentation, outperforming prior methods with interpretable uncertainty maps.

🔹 Publication Date: Published on Feb 23

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.20423
• PDF: https://arxiv.org/pdf/2602.20423
• Project Page: https://tahakoleilat.github.io/MedCLIPSeg/
• Github: https://github.com/HealthX-Lab/MedCLIPSeg

🔹 Models citing this paper:
• https://huggingface.co/TahaKoleilat/MedCLIPSeg

✨ Datasets citing this paper:
• https://huggingface.co/datasets/TahaKoleilat/MedCLIPSeg

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale

📝 Summary:
VGG-T^3 scales 3D reconstruction linearly with input views by distilling variable-length scene representations into fixed-size MLPs through test-time training. This method achieves significant speedup over traditional quadratic approaches while maintaining high accuracy and global scene aggregation.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23361
• PDF: https://arxiv.org/pdf/2602.23361
• Project Page: https://research.nvidia.com/labs/dvl/projects/vgg-ttt/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

📝 Summary:
Reinforcement learning with verifiable rewards suffers from reduced reasoning diversity due to uniform error penalization, which is addressed by a confidence-aware asymmetric error penalty method that...

🔹 Publication Date: Published on Feb 24

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.21420
• PDF: https://arxiv.org/pdf/2602.21420

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Text-to-LoRA: Instant Transformer Adaption

📝 Summary:
Text-to-LoRA T2L instantly adapts large language models using natural language descriptions. This hypernetwork efficiently generates task-specific LoRA adapters in a single pass, matching dedicated fine-tuning and generalizing to unseen tasks with minimal compute.

🔹 Publication Date: Published on Jun 6, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2506.06105
• PDF: https://arxiv.org/pdf/2506.06105
• Github: https://github.com/sakanaai/text-to-lora

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Soft Adaptive Policy Optimization

📝 Summary:
Soft Adaptive Policy Optimization SAPO enhances reinforcement learning for LLMs. It uses a smooth, temperature-controlled gate to adaptively attenuate off-policy updates, improving training stability and performance on reasoning tasks.

🔹 Publication Date: Published on Nov 25, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.20347
• PDF: https://arxiv.org/pdf/2511.20347
• Project Page: https://swift.readthedocs.io/en/latest/Instruction/GRPO/AdvancedResearch/SAPO.html
• Github: https://github.com/NovaSky-AI/SkyRL/pull/762

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

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

#ReinforcementLearning #LLMs #PolicyOptimization #AI #MachineLearning

✨Accelerating Masked Image Generation by Learning Latent Controlled Dynamics

📝 Summary:
MIGM-Shortcut accelerates masked image generation by learning a lightweight model to predict feature evolution velocity from previous features and sampled tokens. This achieves over 4x speedup with maintained quality on state-of-the-art models.

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23996
• PDF: https://arxiv.org/pdf/2602.23996
• Github: https://github.com/Kaiwen-Zhu/MIGM-Shortcut

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

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

#ImageGeneration #DeepLearning #GenerativeAI #ComputerVision #AI

✨SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

📝 Summary:
SenCache accelerates diffusion model inference by dynamically selecting cache timesteps based on model output sensitivity to input perturbations. This principled framework improves visual quality over existing heuristic methods within similar computational budgets.

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.24208
• PDF: https://arxiv.org/pdf/2602.24208
• Github: https://github.com/vita-epfl/SenCache

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

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

#DiffusionModels #AI #MachineLearning #InferenceAcceleration #ComputerVision

✨Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators

📝 Summary:
STATIC accelerates constrained decoding for LLM generative retrieval on hardware accelerators. It transforms prefix trees into sparse matrices, vectorizing operations for massive speedups and low latency. This enables the first production-scale deployment of strictly constrained generative retrie...

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22647
• PDF: https://arxiv.org/pdf/2602.22647

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

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

#LLM #GenerativeAI #ConstrainedDecoding #AIHardware #DeepLearning

✨MeshSplatting: Differentiable Rendering with Opaque Meshes

📝 Summary:
MeshSplatting enables real-time novel view synthesis by combining mesh-based reconstruction with differentiable rendering to produce high-quality, efficient 3D meshes. AI-generated summary Primitive-b...

🔹 Publication Date: Published on Dec 7, 2025

🔹 Paper Links:
• arXiv Page: https://arxivlens.com/PaperView/Details/meshsplatting-differentiable-rendering-with-opaque-meshes-3886-1d3e00da
• PDF: https://arxiv.org/pdf/2512.06818
• Project Page: https://meshsplatting.github.io/
• Github: https://github.com/meshsplatting/mesh-splatting

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Enhancing Spatial Understanding in Image Generation via Reward Modeling

📝 Summary:
Text-to-image models struggle with complex spatial relationships. This paper introduces SpatialScore, a reward model trained on 80k preference pairs, to evaluate and improve spatial accuracy. It significantly enhances spatial understanding in image generation via reinforcement learning.

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.24233
• PDF: https://arxiv.org/pdf/2602.24233
• Project Page: https://dagroup-pku.github.io/SpatialT2I/
• Github: https://github.com/DAGroup-PKU/SpatialT2I

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

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

#ImageGeneration #TextToImage #SpatialAI #RewardModeling #DeepLearning

✨CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

📝 Summary:
CUDA Agent is a large-scale agentic reinforcement learning system for optimizing CUDA kernels. It uses data synthesis, a skill-augmented development environment, and RL to achieve state-of-the-art performance, outperforming torch.compile and other LLMs significantly.

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.24286
• PDF: https://arxiv.org/pdf/2602.24286
• Project Page: https://cuda-agent.github.io/

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

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

#CUDA #ReinforcementLearning #HPC #AI #MachineLearning

✨Memory Caching: RNNs with Growing Memory

📝 Summary:
Memory Caching MC enhances recurrent neural networks by caching memory states, allowing their capacity to grow with sequence length. This bridges the performance gap between RNNs and Transformers in long-context and recall-intensive tasks, outperforming other recurrent models.

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.24281
• PDF: https://arxiv.org/pdf/2602.24281

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

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

#RNNs #Transformers #NeuralNetworks #MemoryCaching #AI

✨Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks

📝 Summary:
Ref-Adv is a challenging benchmark for referring expression comprehension that eliminates shortcut solutions by using complex linguistic expressions with minimal identifying information and hard distr...

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23898
• PDF: https://arxiv.org/pdf/2602.23898
• Project Page: https://ref-adv.github.io
• Github: https://github.com/dddraxxx/Ref-Adv

✨ Datasets citing this paper:
• https://huggingface.co/datasets/dddraxxx/ref-adv-s

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model

📝 Summary:
A new benchmark called DeepLookEditBench is introduced to evaluate instruction-based image editing models' capability in handling small-scale object editing, revealing significant performance gaps in ...

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23622
• PDF: https://arxiv.org/pdf/2602.23622

✨ Datasets citing this paper:
• https://huggingface.co/datasets/SPUH/DLEBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨dLLM: Simple Diffusion Language Modeling

📝 Summary:
dLLM is an open-source framework standardizing core components of diffusion language modeling. It addresses the issue of scattered, hard-to-reproduce DLM implementations, enabling easy reproduction, customization, and development of both small and large diffusion language models.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.22661
• PDF: https://arxiv.org/pdf/2602.22661
• Project Page: https://github.com/ZHZisZZ/dllm
• Github: https://github.com/ZHZisZZ/dllm

🔹 Models citing this paper:
• https://huggingface.co/dllm-hub/ModernBERT-large-chat-v0.1
• https://huggingface.co/dllm-hub/Qwen3-0.6B-diffusion-mdlm-v0.1
• https://huggingface.co/dllm-hub/Qwen3-0.6B-diffusion-bd3lm-v0.1

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

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

#DiffusionModels #LanguageModeling #LLMs #OpenSourceAI #AIResearch

✨CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

📝 Summary:
CiteAudit presents a benchmark and multi-agent pipeline to detect fabricated citations, a risk introduced by LLMs in scientific writing. This framework decomposes citation verification into steps and significantly outperforms prior methods, offering scalable tools for trustworthy references.

🔹 Publication Date: Published on Feb 26

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.23452
• PDF: https://arxiv.org/pdf/2602.23452
• Project Page: https://www.checkcitation.com/

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

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

#LLM #AcademicIntegrity #CitationVerification #AIethics #ResearchTools

✨Mode Seeking meets Mean Seeking for Fast Long Video Generation

📝 Summary:
This paper introduces a Decoupled Diffusion Transformer combining mode seeking and mean seeking for efficient long video generation. It leverages global flow matching for narrative coherence and local distribution matching against a short-video teacher for realism, effectively bridging the fideli...

🔹 Publication Date: Published on Feb 27

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.24289
• PDF: https://arxiv.org/pdf/2602.24289
• Project Page: https://primecai.github.io/mmm/
• Github: https://primecai.github.io/mmm/

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

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

#VideoGeneration #DiffusionModels #AIResearch #MachineLearning #ComputerVision