✨UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory

📝 Summary:
A unified framework for memory extraction and management in LLM-based agents that improves generalization through semantic neighborhood modeling and marginal utility rewards. AI-generated summary Self...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10652
• PDF: https://arxiv.org/pdf/2602.10652
• Github: https://github.com/AIDC-AI/Marco-DeepResearch

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation

📝 Summary:
V-STAR improves generative recommendation by addressing the probability-reward mismatch that causes poor exploration and weak learning signals. It uses value-guided decoding for efficient exploration and sibling-relative advantages to focus reinforcement learning. This framework enhances accuracy...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10699
• PDF: https://arxiv.org/pdf/2602.10699

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨PhyCritic: Multimodal Critic Models for Physical AI

📝 Summary:
PhyCritic is a multimodal critic model designed for physical AI tasks through a two-stage RLVR pipeline that enhances perception and reasoning capabilities. AI-generated summary With the rapid develop...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11124
• PDF: https://arxiv.org/pdf/2602.11124
• Project Page: https://research.nvidia.com/labs/lpr/phycritic

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FeatureBench: Benchmarking Agentic Coding for Complex Feature Development

📝 Summary:
FeatureBench evaluates agentic coding performance in comprehensive feature-oriented development through execution-based assessments and automated task derivation from code repositories. AI-generated s...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10975
• PDF: https://arxiv.org/pdf/2602.10975
• Project Page: https://libercoders.github.io/FeatureBench/
• Github: https://github.com/LiberCoders/FeatureBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

📝 Summary:
Omni Dense Captioning introduces a six-dimensional structural schema for generating time-aware audio-visual narratives with explicit timestamps, along with a unified evaluation metric and strong basel...

🔹 Publication Date: Published on Feb 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08711
• PDF: https://arxiv.org/pdf/2602.08711
• Github: https://github.com/yaolinli/TimeChat-Captioner

🔹 Models citing this paper:
• https://huggingface.co/yaolily/TimeChat-Captioner-GRPO-7B

✨ Datasets citing this paper:
• https://huggingface.co/datasets/yaolily/TimeChat-OmniCap-42K
• https://huggingface.co/datasets/yaolily/OmniDCBench

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ASA: Training-Free Representation Engineering for Tool-Calling Agents

📝 Summary:
A training-free method called Activation Steering Adapter corrects tool calling behavior in language models by using mid-layer activation interventions guided by a probe and router-conditioned steerin...

🔹 Publication Date: Published on Feb 4

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.04935
• PDF: https://arxiv.org/pdf/2602.04935

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Free(): Learning to Forget in Malloc-Only Reasoning Models

📝 Summary:
Free()LM addresses reasoning model limitations by introducing a self-forgetting mechanism through a Free-Module plug-and-play LoRA adapter, improving performance across scales and long-horizon tasks. ...

🔹 Publication Date: Published on Feb 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08030
• PDF: https://arxiv.org/pdf/2602.08030
• Github: https://github.com/TemporaryLoRA/FreeLM

🔹 Models citing this paper:
• https://huggingface.co/ldsjmdy/Qwen3-8B-FreeLM-LoRA
• https://huggingface.co/ldsjmdy/Qwen3-30B-A3B-Thinking-2507-FreeLM-LoRA
• https://huggingface.co/ldsjmdy/Qwen3-235B-A22B-Thinking-2507-FreeLM-LoRA

✨ Datasets citing this paper:
• https://huggingface.co/datasets/ldsjmdy/FreeLM

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Beyond Correctness: Learning Robust Reasoning via Transfer

📝 Summary:
Reinforcement Learning with Transferable Reward (RLTR) enhances LLM reasoning robustness by ensuring reasoning stability and generalizability through transfer rewards that test cross-model guidance ca...

🔹 Publication Date: Published on Feb 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08489
• PDF: https://arxiv.org/pdf/2602.08489

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨UI-Venus Technical Report: Building High-performance UI Agents with RFT

📝 Summary:
UI-Venus achieves state-of-the-art performance in UI grounding and navigation tasks using reinforcement fine-tuning and a self-evolving framework that enhances trajectory history alignment and action ...

🔹 Publication Date: Published on Aug 14, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10833
• PDF: https://arxiv.org/pdf/2508.10833
• Project Page: https://github.com/inclusionAI/UI-Venus
• Github: https://github.com/inclusionAI/UI-Venus

🔹 Models citing this paper:
• https://huggingface.co/inclusionAI/UI-Venus-Ground-7B
• https://huggingface.co/inclusionAI/UI-Venus-1.5-8B
• https://huggingface.co/inclusionAI/UI-Venus-1.5-30B-A3B

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

📝 Summary:
Ex-Omni enhances omni-modal LLMs for speech-accompanied 3D facial animation. It solves the representation mismatch by decoupling semantic reasoning from temporal generation and using speech units as scaffolding. This enables stable, aligned speech and facial animation.

🔹 Publication Date: Published on Feb 6

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07106
• PDF: https://arxiv.org/pdf/2602.07106
• Project Page: https://haoyu-ha.github.io/Ex-Omni-Project-Page

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Weight Decay Improves Language Model Plasticity

📝 Summary:
Pretraining with larger weight decay values improves model plasticity and downstream fine-tuning performance by encouraging linearly separable representations and reducing overfitting. AI-generated su...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11137
• PDF: https://arxiv.org/pdf/2602.11137

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression

📝 Summary:
ROCKET is a training-free model compression method that formulates layer-wise compression as a knapsack problem and uses single-step sparse matrix factorization. It achieves state-of-the-art performance, retaining over 90 percent of original performance at 30 percent compression without fine-tuning.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11008
• PDF: https://arxiv.org/pdf/2602.11008
• Github: https://github.com/mts-ai/ROCKET

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies

📝 Summary:
EcoGym introduces a new benchmark for evaluating LLM agents long-horizon planning in interactive economic environments. It features three diverse scenarios with persistent dynamics and business-relevant metrics. Experiments reveal LLMs struggle with either high-level strategy or efficient action ...

🔹 Publication Date: Published on Feb 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.09514
• PDF: https://arxiv.org/pdf/2602.09514
• Github: https://github.com/OPPO-PersonalAI/EcoGym

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

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

#LLM #AIPlanning #EconomicSimulation #AI #Benchmark

✨Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning

📝 Summary:
Training reasoning language models benefits from data repetition. For a fixed update budget, more epochs on smaller datasets beat single-pass training on larger datasets. Token accuracy signals optimal training duration.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11149
• PDF: https://arxiv.org/pdf/2602.11149
• Github: https://github.com/dkopi/data-repetition

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

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

#LLM #FineTuning #DataStrategy #MachineLearning #AIResearch

✨Benchmarking Large Language Models for Knowledge Graph Validation

📝 Summary:
This paper introduces FactCheck, a benchmark to evaluate LLMs for knowledge graph fact validation. Experiments show LLMs are not yet stable or reliable, and RAG or multi-model consensus offer inconsistent improvements, highlighting the need for such a benchmark.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10748
• PDF: https://arxiv.org/pdf/2602.10748
• Github: https://github.com/FactCheck-AI

✨ Datasets citing this paper:
• https://huggingface.co/datasets/FactCheck-AI/FactCheck

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

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

#LLMs #KnowledgeGraphs #FactChecking #AIResearch #Benchmarking

✨Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation

📝 Summary:
Bielik Guard is a compact Polish language safety classifier family with two variants that effectively categorize content across five safety domains while maintaining high efficiency and accuracy. AI-g...

🔹 Publication Date: Published on Feb 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07954
• PDF: https://arxiv.org/pdf/2602.07954
• Project Page: https://guard.bielik.ai/

🔹 Models citing this paper:
• https://huggingface.co/speakleash/Bielik-Guard-0.1B-v1.0
• https://huggingface.co/speakleash/Bielik-Guard-0.1B-v1.1
• https://huggingface.co/speakleash/Bielik-Guard-0.5B-v1.1

✨ Spaces citing this paper:
• https://huggingface.co/spaces/jglowa/bielik-czat

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨FedPS: Federated data Preprocessing via aggregated Statistics

📝 Summary:
FedPS is a federated data preprocessing framework for collaborative machine learning. It uses aggregated statistics and data-sketching for efficient privacy-preserving data preparation in FL, covering tasks like scaling and imputation.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10870
• PDF: https://arxiv.org/pdf/2602.10870
• Project Page: https://xuefeng-xu.github.io/fedps.html
• Github: https://github.com/xuefeng-xu/fedps

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

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

#FederatedLearning #DataPreprocessing #MachineLearning #PrivacyPreservingAI #DataScience

✨Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards

📝 Summary:
Blockwise Advantage Estimation BAE solves reward interference in multi-objective RL for structured generations. It assigns distinct advantages to text blocks, using an Outcome-Conditioned Baseline to estimate them without nested rollouts. This mitigates interference and scales to new objectives.

🔹 Publication Date: Published on Feb 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10231
• PDF: https://arxiv.org/pdf/2602.10231

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

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

#ReinforcementLearning #MultiObjectiveRL #NLP #MachineLearning #AIResearch

✨GoodVibe: Security-by-Vibe for LLM-Based Code Generation

📝 Summary:
GoodVibe secures LLM-generated code by precisely fine-tuning only a small subset of security-relevant neurons. This neuron-level framework greatly enhances code security and preserves utility with significantly fewer parameters and training costs than traditional methods.

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10778
• PDF: https://arxiv.org/pdf/2602.10778

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

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

#LLM #CodeGeneration #Cybersecurity #AIsecurity #MachineLearning

✨Large Language Lobotomy: Jailbreaking Mixture-of-Experts via Expert Silencing

📝 Summary:
This paper introduces Large Language Lobotomy L3, an attack on Mixture-of-Experts LLMs. L3 exploits routing dynamics to identify and silence safety-critical experts, achieving high jailbreaking success while retaining language utility. This highlights a fundamental tension in MoE design.

🔹 Publication Date: Published on Feb 9

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.08741
• PDF: https://arxiv.org/pdf/2602.08741
• Github: https://github.com/jonatelintelo/LargeLanguageLobotomy

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

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

#LLM #MixtureOfExperts #Jailbreaking #AISafety #AIResearch

✨Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents

📝 Summary:
This study finds that agent-generated tests for LLM software engineering agents may have limited value. Test writing frequency doesnt correlate with issue resolution, and agents prefer informal print statements. Varying test volume showed little impact, suggesting marginal utility in current prac...

🔹 Publication Date: Published on Feb 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.07900
• PDF: https://arxiv.org/pdf/2602.07900

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

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

#LLMAgents #SoftwareEngineering #AutomatedTesting #AIResearch #GenerativeAI