✨When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning

📝 Summary:
GRU-Mem addresses long-context reasoning challenges in LLMs by incorporating text-controlled gates and reinforcement learning rewards to stabilize memory updates and improve computational efficiency. ...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10560
• PDF: https://arxiv.org/pdf/2602.10560
• Project Page: https://alphalab-ustc.github.io/grumem-alphalab/

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Towards Autonomous Mathematics Research

📝 Summary:
Aletheia, a math research agent, demonstrates advanced reasoning capabilities by generating and verifying solutions end-to-end in natural language, achieving autonomous research outcomes from Olympiad...

🔹 Publication Date: Published on Feb 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10177
• PDF: https://arxiv.org/pdf/2602.10177

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion

📝 Summary:
CLI-Gym enables scalable derivation of environment-intensive tasks by simulating and exploring environment histories, while LiberCoder achieves significant performance improvements on Terminal-Bench t...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10999
• PDF: https://arxiv.org/pdf/2602.10999
• Github: https://github.com/LiberCoders/CLI-Gym

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨QP-OneModel: A Unified Generative LLM for Multi-Task Query Understanding in Xiaohongshu Search

📝 Summary:
A unified generative large language model approach for social network search query processing that improves semantic understanding through multi-task learning and reinforcement learning while enhancin...

🔹 Publication Date: Published on Feb 10

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.09901
• PDF: https://arxiv.org/pdf/2602.09901

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨Online Causal Kalman Filtering for Stable and Effective Policy Optimization

📝 Summary:
Online Causal Kalman Filtering addresses high-variance token-level importance sampling in reinforcement learning for large language models by modeling IS ratios as evolving latent states and using Kal...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.10609
• PDF: https://arxiv.org/pdf/2602.10609

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨GENIUS: Generative Fluid Intelligence Evaluation Suite

📝 Summary:
GENIUS evaluates multimodal models' generative fluid intelligence through pattern induction, constraint execution, and contextual adaptation tasks, revealing deficiencies in context comprehension rath...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11144
• PDF: https://arxiv.org/pdf/2602.11144

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

📝 Summary:
DataChef-32B automates data recipe generation for LLM adaptation through reinforcement learning with proxy rewards, achieving performance comparable to human-crafted recipes. AI-generated summary In t...

🔹 Publication Date: Published on Feb 11

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2602.11089
• PDF: https://arxiv.org/pdf/2602.11089
• Github: https://github.com/yichengchen24/DataChef

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

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

#AI #DataScience #MachineLearning #HuggingFace #Research

✨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