✨GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

📝 Summary:
Group Fine-Tuning addresses limitations in supervised fine-tuning by using diverse response groups and adaptive weight bounding to improve training stability and efficiency. AI-generated summary Large...

🔹 Publication Date: Published on Apr 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.14258
• PDF: https://arxiv.org/pdf/2604.14258
• Project Page: https://arxiv.org/abs/2604.14258
• Github: https://github.com/ZJU-OmniAI/GFT/tree/main

✨ Datasets citing this paper:
• https://huggingface.co/datasets/OmniAI-ZJU/NuminaMath-Cot-Distillation-100K

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Latent Preference Modeling for Cross-Session Personalized Tool Calling

📝 Summary:
Personalized tool calling in LLM-based agents is improved through memory-augmented methods that capture user choice reasoning rather than just choices, using minimal token overhead. AI-generated summa...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17886
• PDF: https://arxiv.org/pdf/2604.17886
• Project Page: https://still-with-you.github.io/pages/prefine/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation

📝 Summary:
Researchers extended one-step MeanFlow image generation from class labels to text inputs. They found that limited refinement steps require highly discriminative text representations. By integrating a powerful LLM-based text encoder, they achieved efficient text-conditioned synthesis and improved ...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18168
• PDF: https://arxiv.org/pdf/2604.18168
• Github: https://github.com/AMAP-ML/EMF

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Modeling Sparse and Bursty Vulnerability Sightings: Forecasting Under Data Constraints

📝 Summary:
Forecasting vulnerability-related activities using time-series models reveals challenges with sparse, bursty data, favoring count-based methods like Poisson regression for more stable predictions. AI-...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16038
• PDF: https://arxiv.org/pdf/2604.16038
• Project Page: https://github.com/vulnerability-lookup/TARDISsight
• Github: https://github.com/vulnerability-lookup/TARDISsight

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

This bot will help you get a course that's available for free for a limited time so you can register before others.

Benefit from it
t.iss.one/UdemySybot

✨Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding

📝 Summary:
This paper improves vision-language models for compositional reasoning by using concreteness-based negative sample selection and a novel margin-based loss. Their framework, Slipform, achieves state-of-the-art accuracy on compositional benchmarks and cross-modal retrieval.

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.13313
• PDF: https://arxiv.org/pdf/2604.13313

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

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

#VisionLanguage #DeepLearning #AIResearch #ComputerVision #NLP

✨GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)

📝 Summary:
GenericAgent is a self-evolving large language model agent system that maximizes context information density through hierarchical memory, reusable SOPs, and efficient compression to overcome long-hori...

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17091
• PDF: https://arxiv.org/pdf/2604.17091
• Github: https://github.com/lsdefine/GenericAgent

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity

📝 Summary:
LLM-based agents fail to exploit discovered unexpected information despite recognizing it, indicating a lack of environmental curiosity that depends on tools, compute, and training data distribution. ...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17609
• PDF: https://arxiv.org/pdf/2604.17609

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability

📝 Summary:
State-of-the-art open-source LLM-based dense retrievers demonstrate varying levels of generalizability and stability, with instruction-tuned models showing better performance but facing specialization...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16576
• PDF: https://arxiv.org/pdf/2604.16576
• Github: https://github.com/liyongkang123/Robust_LLM_Retriever_Eval

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨VoxMind: An End-to-End Agentic Spoken Dialogue System

📝 Summary:
VoxMind enhances spoken dialogue models with agentic capabilities through a "Think-before-Speak" mechanism and dynamic tool management to improve task completion rates while maintaining conversational...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15710
• PDF: https://arxiv.org/pdf/2604.15710
• Github: https://github.com/MM-Speech/VoxMind

🔹 Models citing this paper:
• https://huggingface.co/leungtianle/VoxMind

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models

📝 Summary:
Current full-duplex speech language models struggle with multi-round conversations due to inconsistent performance across different evaluation dimensions, necessitating comprehensive benchmarking. AI-...

🔹 Publication Date: Published on Apr 17

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10262
• PDF: https://arxiv.org/pdf/2511.10262
• Github: https://github.com/ZhangHe0918/MTR-DuplexBench

✨ Datasets citing this paper:
• https://huggingface.co/datasets/Jeff0918/MTR-DuplexBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Continuity Layer: Why Intelligence Needs an Architecture for What It Carries Forward

📝 Summary:
The paper advocates for a continuity layer in AI systems to address the limitation of transient understanding, proposing a Decomposed Trace Convergence Memory storage primitive and a four-layer develo...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17273
• PDF: https://arxiv.org/pdf/2604.17273
• Project Page: https://kenoticlabs.com/thesis
• Github: https://github.com/Kenotic-Labs/continuity-layer

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Significance and Stability Analysis of Gene-Environment Interaction using RGxEStat

📝 Summary:
G e n o t y p e - b y - E n v i r o n m e n t ( G x E ) i n t e r a c t i o n s i n f l u e n c e t h e p e r f o r m a n c e o f g e n o t y p e s a c r o s s d i v e r s e e n v i r o n m e n t s , ...

🔹 Publication Date: Published on Apr 3

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.03337
• PDF: https://arxiv.org/pdf/2604.03337
• Github: https://github.com/mason-ching/RGxEStat

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨On the Reliability of Computer Use Agents

📝 Summary:
Computer-use agents exhibit unreliable performance due to execution stochasticity, task specification ambiguity, and behavioral variability, necessitating repeated evaluation and stable strategies for...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17849
• PDF: https://arxiv.org/pdf/2604.17849
• Github: https://github.com/simular-ai/cua_reliability

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation

📝 Summary:
On-policy distillation suffers from miscalibration due to information mismatch between training and deployment contexts, which is addressed through a calibration-aware framework that improves both per...

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16830
• PDF: https://arxiv.org/pdf/2604.16830
• Project Page: https://github.com/SalesforceAIResearch/CaOPD
• Github: https://github.com/SalesforceAIResearch/CaOPD

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Forge-UGC: FX optimization and register-graph engine for universal graph compiler

📝 Summary:
Forge-UGC is a four-phase compiler for efficient transformer deployment on heterogeneous hardware, offering faster compilation, reduced inference latency, and lower energy consumption compared to exis...

🔹 Publication Date: Published on Apr 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16498
• PDF: https://arxiv.org/pdf/2604.16498

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Protecting Language Models Against Unauthorized Distillation through Trace Rewriting

📝 Summary:
Techniques for modifying teacher-generated reasoning traces to prevent unauthorized knowledge distillation while maintaining answer correctness and enabling detectable watermarks are presented. AI-gen...

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.15143
• PDF: https://arxiv.org/pdf/2602.15143
• Github: https://github.com/xhOwenMa/trace-rewriting

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Symbolic Guardrails for Domain-Specific Agents: Stronger Safety and Security Guarantees Without Sacrificing Utility

📝 Summary:
Symbolic guardrails provide strong safety and security guarantees for AI agents in high-stakes environments. A study found these guardrails can enforce 74% of specified policy requirements, improving safety without sacrificing utility. This makes them a practical solution for domain-specific agents.

🔹 Publication Date: Published on Apr 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.15579
• PDF: https://arxiv.org/pdf/2604.15579
• Github: https://github.com/hyn0027/agent-symbolic-guardrails

✨ Datasets citing this paper:
• https://huggingface.co/datasets/hyn0027D/agent-symbolic-guardrails

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

📝 Summary:
MedFocusLeak enables transferable black-box attacks on vision-language models for medical imaging by injecting imperceptible perturbations that redirect model attention, demonstrating significant vuln...

🔹 Publication Date: Published on Apr 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.17318
• PDF: https://arxiv.org/pdf/2604.17318
• Project Page: https://akashghosh.github.io/MedFocusLeakACL/
• Github: https://github.com/AkashGhosh/When-Background-Matters-Breaking-Medical-Vision-Language-Models-by-Transferable-Attack

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨MARCO: Navigating the Unseen Space of Semantic Correspondence

📝 Summary:
MARCO is a compact, fast model for semantic correspondence that excels at generalizing to unseen keypoints. Its coarse-to-fine objective and self-distillation framework improve fine-grained localization and overall accuracy.

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18267
• PDF: https://arxiv.org/pdf/2604.18267
• Project Page: https://visinf.github.io/MARCO
• Github: https://github.com/visinf/MARCO

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨River-LLM: Large Language Model Seamless Exit Based on KV Share

📝 Summary:
River-LLM enables efficient token-level early exit in LLMs by introducing a KV-Shared Exit River. This mechanism naturally generates and preserves missing historical states, overcoming the KV Cache Absence problem. It achieves 1.71 to 2.16 times practical speedup while maintaining high generation...

🔹 Publication Date: Published on Apr 20

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.18396
• PDF: https://arxiv.org/pdf/2604.18396

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research