GroupRank: A Groupwise Reranking Paradigm Driven by Reinforcement Learning
📅 Publication date: Nov 10 2025
📑 Paper: https://arxiv.org/pdf/2511.11653.pdf
🔗 Code: https://github.com/AQ-MedAI/Diver
📅 Publication date: Nov 10 2025
📑 Paper: https://arxiv.org/pdf/2511.11653.pdf
🔗 Code: https://github.com/AQ-MedAI/Diver
WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11434.pdf
🔗 Code: https://github.com/weichow23/weave
📝 Denoscription:
WEAVE introduces a comprehensive suite including a large dataset and a benchmark to assess and improve multi-turn, context-dependent image generation and editing in unified multimodal models.
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11434.pdf
🔗 Code: https://github.com/weichow23/weave
📝 Denoscription:
WEAVE introduces a comprehensive suite including a large dataset and a benchmark to assess and improve multi-turn, context-dependent image generation and editing in unified multimodal models.
❤2
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13704.pdf
🔗 Code: https://github.com/EnVision-Research/TiViBench
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13704.pdf
🔗 Code: https://github.com/EnVision-Research/TiViBench
GitHub
GitHub - EnVision-Research/TiViBench: TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models - EnVision-Research/TiViBench
❤2
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08577.pdf
🔗 Code: https://github.com/thu-nics/TaH
📝 Denoscription:
Think-at-Hard (TaH) dynamically refines only hard tokens in LLMs using a neural decider and LoRA, improving reasoning performance with minimal additional parameters or iterations.
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08577.pdf
🔗 Code: https://github.com/thu-nics/TaH
📝 Denoscription:
Think-at-Hard (TaH) dynamically refines only hard tokens in LLMs using a neural decider and LoRA, improving reasoning performance with minimal additional parameters or iterations.
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13648.pdf
🔗 Code: https://github.com/ziangcao0312/PhysX-Anything
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13648.pdf
🔗 Code: https://github.com/ziangcao0312/PhysX-Anything
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
📅 Publication date: Nov 13 2025
📑 Paper: https://arxiv.org/pdf/2511.10555.pdf
🔗 Code: https://github.com/Kwai-Kolors/CoTyle
📝 Denoscription:
A novel method, CoTyle, generates images in consistent visual styles using unique numerical style codes, filling an academic gap in code-to-style image generation.
📅 Publication date: Nov 13 2025
📑 Paper: https://arxiv.org/pdf/2511.10555.pdf
🔗 Code: https://github.com/Kwai-Kolors/CoTyle
📝 Denoscription:
A novel method, CoTyle, generates images in consistent visual styles using unique numerical style codes, filling an academic gap in code-to-style image generation.
GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11134.pdf
🔗 Code: N/A
📝 Denoscription:
GGBench is introduced to evaluate geometric generative reasoning, addressing the gap in assessing integrated cognitive processes in multimodal models.
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11134.pdf
🔗 Code: N/A
📝 Denoscription:
GGBench is introduced to evaluate geometric generative reasoning, addressing the gap in assessing integrated cognitive processes in multimodal models.
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
📅 Publication date: Nov 16 2025
📑 Paper: https://arxiv.org/pdf/2511.12710.pdf
🔗 Code: https://github.com/dongdongunique/EvoSynth
📅 Publication date: Nov 16 2025
📑 Paper: https://arxiv.org/pdf/2511.12710.pdf
🔗 Code: https://github.com/dongdongunique/EvoSynth
Data science research papers
✅ To be posted in a few minutes⏳
Curated Research Papers: Predicting Student Performance & Physics Exam Results
1. University Admission Prediction using Machine Learning
📅 Publication date: Aug 2022
📑 Paper: Prediction for University Admission using Machine Learning (PDF)
🔗 Code: Admission Prediction with Python (GitHub)
📝 Denoscription:
This crucial paper focuses on predicting the likelihood of a student getting admitted to a university based on various scores (like GRE/TOEFL, which you can replace with Grade 9-11 trannoscripts and Grade 12 regional results). The code repository provides a clean example of using Regression models to predict a continuous score (like an exam result) rather than just a Pass/Fail class.
2. Predicting Physics Students' Achievement Using In-Class Assessment Data
📅 Publication date: Dec 2023
📑 Paper: Predicting Physics Students' Achievement Using In-Class Assessment Data
🔗 Code (Reference Implementation): Student Performance Prediction ML (GitHub)
📝 Denoscription:
This paper is exactly aligned with your topic. It compares two common algorithms (Logistic Regression and Random Forest) to predict high school physics students' final achievements based on their in-class assessment data. The "Code" link above leads to a very similar project implementation on GitHub that uses classifiers to predict student grades, which you can adapt to a specific entrance exam data.
3. Student Performance Prediction Model
📅 Publication date: 2024 (Model Upload)
📑 Paper/Model Card: Student Performance Prediction Model (Hugging Face)
🔗 Code: Model Files & Usage
📝 Denoscription:
This is a pre-trained model hosted on Hugging Face, the leading platform for modern Data Science. Unlike a traditional PDF paper, this resource gives you a working Neural Network model (built with TensorFlow/Keras). It takes socio-economic and academic factors as input to estimate final grades. You can download this to see exactly how a modern data science model is structured and saved.
4. Machine Learning-Driven Student Performance Prediction
📅 Publication date: Feb 05 2025
📑 Paper: Machine Learning-Driven Student Performance Prediction for Enhancing Tiered Instruction
🔗 Code (Similar Architecture): End-to-End Student Performance Prediction
📝 Denoscription:
This is a cutting-edge paper released just this year. It explores using Random Forest and other algorithms to not just predict grades, but to categorize students into "tiers" so teachers can intervene early. For final year thesis, this adds a "recommendation" aspect, you aren't just predicting the physics grade, you are helping the school identify who needs help before the exam.
5. Tuning Data Mining Models to Predict Secondary School Performance
📅 Publication date: Jul 2024
📑 Paper: Tuning Data Mining Models to Predict Secondary School Academic Performance
🔗 Code (Dataset & Notebooks): Student Performance Data Set (UCI/Kaggle Link)
📝 Denoscription:
This paper is excellent for methodology. It details how to "tune" your models (adjusting the settings of the algorithm) to get higher accuracy. It compares Artificial Neural Networks (ANN) and Support Vector Machines (SVM). This data can be used to practice before your own data is ready.
1. University Admission Prediction using Machine Learning
📅 Publication date: Aug 2022
📑 Paper: Prediction for University Admission using Machine Learning (PDF)
🔗 Code: Admission Prediction with Python (GitHub)
📝 Denoscription:
This crucial paper focuses on predicting the likelihood of a student getting admitted to a university based on various scores (like GRE/TOEFL, which you can replace with Grade 9-11 trannoscripts and Grade 12 regional results). The code repository provides a clean example of using Regression models to predict a continuous score (like an exam result) rather than just a Pass/Fail class.
2. Predicting Physics Students' Achievement Using In-Class Assessment Data
📅 Publication date: Dec 2023
📑 Paper: Predicting Physics Students' Achievement Using In-Class Assessment Data
🔗 Code (Reference Implementation): Student Performance Prediction ML (GitHub)
📝 Denoscription:
This paper is exactly aligned with your topic. It compares two common algorithms (Logistic Regression and Random Forest) to predict high school physics students' final achievements based on their in-class assessment data. The "Code" link above leads to a very similar project implementation on GitHub that uses classifiers to predict student grades, which you can adapt to a specific entrance exam data.
3. Student Performance Prediction Model
📅 Publication date: 2024 (Model Upload)
📑 Paper/Model Card: Student Performance Prediction Model (Hugging Face)
🔗 Code: Model Files & Usage
📝 Denoscription:
This is a pre-trained model hosted on Hugging Face, the leading platform for modern Data Science. Unlike a traditional PDF paper, this resource gives you a working Neural Network model (built with TensorFlow/Keras). It takes socio-economic and academic factors as input to estimate final grades. You can download this to see exactly how a modern data science model is structured and saved.
4. Machine Learning-Driven Student Performance Prediction
📅 Publication date: Feb 05 2025
📑 Paper: Machine Learning-Driven Student Performance Prediction for Enhancing Tiered Instruction
🔗 Code (Similar Architecture): End-to-End Student Performance Prediction
📝 Denoscription:
This is a cutting-edge paper released just this year. It explores using Random Forest and other algorithms to not just predict grades, but to categorize students into "tiers" so teachers can intervene early. For final year thesis, this adds a "recommendation" aspect, you aren't just predicting the physics grade, you are helping the school identify who needs help before the exam.
5. Tuning Data Mining Models to Predict Secondary School Performance
📅 Publication date: Jul 2024
📑 Paper: Tuning Data Mining Models to Predict Secondary School Academic Performance
🔗 Code (Dataset & Notebooks): Student Performance Data Set (UCI/Kaggle Link)
📝 Denoscription:
This paper is excellent for methodology. It details how to "tune" your models (adjusting the settings of the algorithm) to get higher accuracy. It compares Artificial Neural Networks (ANN) and Support Vector Machines (SVM). This data can be used to practice before your own data is ready.
❤3
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11793.pdf
🔗 Code: https://github.com/MiroMindAI/MiroThinker
📅 Publication date: Nov 14 2025
📑 Paper: https://arxiv.org/pdf/2511.11793.pdf
🔗 Code: https://github.com/MiroMindAI/MiroThinker
UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08195.pdf
🔗 Code: https://github.com/zai-org/UI2Code_N
📝 Denoscription:
UI2Code^N is a visual language model enhanced through staged pretraining, fine-tuning, and reinforcement learning, achieves superior performance in UI-to-code generation, editing, and polishing with iterative feedback.
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08195.pdf
🔗 Code: https://github.com/zai-org/UI2Code_N
📝 Denoscription:
UI2Code^N is a visual language model enhanced through staged pretraining, fine-tuning, and reinforcement learning, achieves superior performance in UI-to-code generation, editing, and polishing with iterative feedback.
👍1
Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13853.pdf
🔗 Code: N/A
📝 Denoscription:
Gen-ViRe benchmarks video models on reasoning abilities using a framework that decomposes Chain-of-Frames reasoning into cognitive dimensions and subtasks.
📅 Publication date: Nov 17 2025
📑 Paper: https://arxiv.org/pdf/2511.13853.pdf
🔗 Code: N/A
📝 Denoscription:
Gen-ViRe benchmarks video models on reasoning abilities using a framework that decomposes Chain-of-Frames reasoning into cognitive dimensions and subtasks.
ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14366.pdf
🔗 Code: N/A
📝 Denoscription:
ATLAS, a large-scale, cross-disciplinary evaluation suite, addresses the limitations of existing benchmarks by providing high-difficulty, original, and high-fidelity scientific problems to assess the reasoning capabilities of Large Language Models.
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14366.pdf
🔗 Code: N/A
📝 Denoscription:
ATLAS, a large-scale, cross-disciplinary evaluation suite, addresses the limitations of existing benchmarks by providing high-difficulty, original, and high-fidelity scientific problems to assess the reasoning capabilities of Large Language Models.
Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
📅 Publication date: Nov 17 2025
📑 Paper : https://arxiv.org/pdf/2511.13646.pdf
🔗 Code: N/A
📅 Publication date: Nov 17 2025
📑 Paper : https://arxiv.org/pdf/2511.13646.pdf
🔗 Code: N/A
👍1
HI-TransPA: Hearing Impairments Translation Personal Assistant
📅 Publication date: Nov 13 2025
📑 Paper: https://arxiv.org/pdf/2511.09915.pdf
🔗 Code: N/A
📝 Denoscription:
HI-TransPA, an instruction-driven audio-visual personal assistant, uses Omni-Model paradigm to translate and dialogue by fusing speech with lip dynamics, achieving state-of-the-art performance in assistive communication for hearing-impaired individuals.
📅 Publication date: Nov 13 2025
📑 Paper: https://arxiv.org/pdf/2511.09915.pdf
🔗 Code: N/A
📝 Denoscription:
HI-TransPA, an instruction-driven audio-visual personal assistant, uses Omni-Model paradigm to translate and dialogue by fusing speech with lip dynamics, achieving state-of-the-art performance in assistive communication for hearing-impaired individuals.
❤1
Simulating the Visual World with Artificial Intelligence: A Roadmap
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08585.pdf
🔗 Code: https://github.com/ziqihuangg/Awesome-From-Video-Generation-to-World-Model
📝 Denoscription:
Video generation is evolving towards foundation models that integrate world simulation and rendering to produce physically plausible and interactive videos.
📅 Publication date: Nov 11 2025
📑 Paper: https://arxiv.org/pdf/2511.08585.pdf
🔗 Code: https://github.com/ziqihuangg/Awesome-From-Video-Generation-to-World-Model
📝 Denoscription:
Video generation is evolving towards foundation models that integrate world simulation and rendering to produce physically plausible and interactive videos.
❤2
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14659.pdf
🔗 Code: https://github.com/declare-lab/nora-1.5
📝 Denoscription:
NORA-1.5, an enhanced vision-language-action model with a flow-matching-based action expert and reward-driven post-training, improves performance and reliability in both simulated and real-world settings.
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14659.pdf
🔗 Code: https://github.com/declare-lab/nora-1.5
📝 Denoscription:
NORA-1.5, an enhanced vision-language-action model with a flow-matching-based action expert and reward-driven post-training, improves performance and reliability in both simulated and real-world settings.
Media is too big
VIEW IN TELEGRAM
OnSpace Mobile App builder: Build AI Apps in minutes
With OnSpace, you can build website or AI Mobile Apps by chatting with AI, and publish to PlayStore or AppStore.
🔥 What will you get:
• 🤖 Create app or website by chatting with AI;
• 🧠 Integrate with Any top AI power just by giving order (like Sora2, Nanobanan Pro & Gemini 3 Pro);
• 📦 Download APK,AAB file, publish to AppStore.
• 💳 Add payments and monetize like in-app-purchase and Stripe.
• 🔐 Functional login & signup.
• 🗄 Database + dashboard in minutes.
• 🎥 Full tutorial on YouTube and within 1 day customer service
🌐 Visit website:
👉 https://www.onspace.ai/?via=tg_bigdata
📲 Or Download app:
👉 https://onspace.onelink.me/za8S/h1jb6sb9?c=bigdata
With OnSpace, you can build website or AI Mobile Apps by chatting with AI, and publish to PlayStore or AppStore.
🔥 What will you get:
• 🤖 Create app or website by chatting with AI;
• 🧠 Integrate with Any top AI power just by giving order (like Sora2, Nanobanan Pro & Gemini 3 Pro);
• 📦 Download APK,AAB file, publish to AppStore.
• 💳 Add payments and monetize like in-app-purchase and Stripe.
• 🔐 Functional login & signup.
• 🗄 Database + dashboard in minutes.
• 🎥 Full tutorial on YouTube and within 1 day customer service
🌐 Visit website:
👉 https://www.onspace.ai/?via=tg_bigdata
📲 Or Download app:
👉 https://onspace.onelink.me/za8S/h1jb6sb9?c=bigdata
❤1
AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14295.pdf
🔗 Code: N/A
📝 Denoscription:
AraLingBench evaluates Arabic and bilingual LLMs' linguistic competence using a benchmark with expert-designed questions across grammar, morphology, spelling, reading comprehension, and syntax, revealing gaps between surface proficiency and true comprehension.
📅 Publication date: Nov 18 2025
📑 Paper: https://arxiv.org/pdf/2511.14295.pdf
🔗 Code: N/A
📝 Denoscription:
AraLingBench evaluates Arabic and bilingual LLMs' linguistic competence using a benchmark with expert-designed questions across grammar, morphology, spelling, reading comprehension, and syntax, revealing gaps between surface proficiency and true comprehension.