Data science research papers

TexOCR: Advancing Document OCR Models for Compilable Page-to-LaTeX Reconstruction 📅 Publication Date: Apr 24, 2026 📑 Paper: https://arxiv.org/pdf/2604.22880 🔗 Github: https://github.com/QDRhhhh/TexOCR 📝 Description: This research presents TexOCR for reconstructing scientific PDFs into compilable LaTeX, addressing limitations of current OCR. It introduces a new benchmark and trains TexOCR using reinforcement learning with verifiable rewards. #AI #DataScience #MachineLearning #Research

Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving 📅 Publication Date: Apr 1, 2026 📑 Paper: https://arxiv.org/pdf/2604.01483 💻 Project Page: https://axiom.devrashie.space 🔗 Code: https://github.com/arkanemystic/lean-agent-protocol 📝 Description: The Lean-Agent Protocol ensures deterministic regulatory compliance for financial AI. It uses Lean 4 theorem proving to auto-formalize policies, verifying agent actions as mathematical conjectures for cryptographic-level certainty, addressing LLM probabilistic nature. #FormalVerification #AICompliance #FinTech #Lean4 #LLMAgents

Do Audio-Visual Large Language Models Really See and Hear? 📅 Publication Date: Apr 3, 2026 📑 Paper: https://arxiv.org/pdf/2604.02605 💻 Project Page: https://ramaneswaran.github.io/avllm_interpretability/ 🔗 Code: https://github.com/ramaneswaran/avllm_interpretability 📝 Description: AVLLMs exhibit modality bias where visual representations dominate over audio cues during multimodal integration, despite audio semantics being present in intermediate layers. #AI #DataScience #MachineLearning #HuggingFace #Research

Scaling Teams or Scaling Time? Memory Enabled Lifelong Learning in LLM Multi-Agent Systems 📅 Publication Date: Mar 27, 2026 📑 Paper: https://arxiv.org/pdf/2604.03295 🔗 Code: https://github.com/ShanglinWu/MAS_lifelong_learning 📝 Description: This paper introduces LLMA-Mem, a memory framework for LLM multi-agent systems. It finds that scaling is non-monotonic; optimized experience reuse allows smaller teams to outperform larger ones, improving long-term performance and reducing cost. #AI #DataScience #MachineLearning #Research

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs 📅 Publication Date: Apr 2, 2026 📑 Paper: https://arxiv.org/pdf/2604.02045 🔗 Code: N/A 📊 Models citing this paper: • https://huggingface.co/BidirLM/BidirLM-Omni-2.5B-Embedding • https://huggingface.co/BidirLM/BidirLM-0.6B-Embedding • https://huggingface.co/BidirLM/BidirLM-1.7B-Embedding 🗃 Datasets citing this paper: • https://huggingface.co/datasets/BidirLM/BidirLM-Contrastive 📝Description: BidirLM adapts causal LLMs into bidirectional encoders, overcoming catastrophic forgetting and integrating specialized models. It employs a prior masking phase, weight merging, and data mixture, outperforming alternatives on text, vision, and audio benchmarks. #LLM #MultimodalAI #DeepLearning #AIResearch #HuggingFace #ModelAdaptation

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents 📅 Publication Date: Apr 7, 2026 📑 Paper: https://arxiv.org/pdf/2604.06132 💻 Project Page: https://claw-eval.github.io/ 🔗 Code: https://github.com/claw-eval/claw-eval 📝 Description: Claw-Eval addresses limitations in agent benchmarks by providing comprehensive evaluation across multiple modalities with trajectory-aware grading and safety assessments. #AI #DataScience #MachineLearning #Research

Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework 📅 Publication Date: Apr 7, 2026 📑 Paper: https://arxiv.org/pdf/2604.06170 💻 Project Page: https://papercircle.vercel.app/ 🔗 Code: https://github.com/MAXNORM8650/papercircle 📝Description: A multi-agent system called Paper Circle is presented that automates the discovery and analysis of scientific literature through integrated retrieval and knowledge graph construction capabilities. #AI #DataScience #MachineLearning #Research

MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU 📅 Publication Date: Apr 6, 2026 📑 Paper: https://arxiv.org/pdf/2604.05091 🔗 Code: https://github.com/DLYuanGod/MegaTrain 📝 Description: MegaTrain trains large language models with over 100 billion parameters on a single GPU. It stores parameters in host memory and streams them to the GPU using pipelined execution and stateless layer templates to overcome bandwidth. This enables 120 billion parameter training. #AI #DataScience #MachineLearning #Research

Context-Value-Action Architecture for Value-Driven Large Language Model Agents 📅 Publication Date: Apr 7, 2026 📑 Paper: https://arxiv.org/pdf/2604.05939 📝 Description: LLMs show rigid, polarized behavior worsening with reasoning. The Context-Value-Action CVA architecture decouples actions from reasoning using a human-data Value Verifier, mitigating polarization and improving behavioral fidelity. #AI #DataScience #MachineLearning #Research

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization 📅 Publication Date: Apr 7, 2026 📑 Paper: https://arxiv.org/pdf/2604.05963 🔗 Code: https://github.com/kcxain/QiMeng-PRepair 📊 Models citing this paper: • https://huggingface.co/kcxain/Prepair-Python-7B-EA • https://huggingface.co/kcxain/Prepair-Verilog-7B-EA 📝 Description: PRepair tackles over-editing in AI program repair by maximizing correct code reuse. It combines controlled bug injection and edit-aware policy optimization using an edit-aware reward. This framework significantly improves repair precision and decoding throughput. #ProgramRepair #AI #MachineLearning #ReinforcementLearning #SoftwareEngineering

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning 📅 Publication Date: Apr 8, 2026 📑Paper: https://arxiv.org/pdf/2604.04746 🔗 Code: N/A 📝 Description: This paper introduces process-driven image generation, an iterative method with interleaved textual and visual reasoning. It decomposes synthesis into planning, drafting, reflecting, and refining steps. Dense step-wise supervision ensures consistency and interpretability of intermediate states. #ImageGeneration #GenerativeAI #ArtificialIntelligence #DeepLearning #ComputerVision

Watch Before You Answer: Learning from Visually Grounded Post-Training 📅 Publication Date: Apr 6, 2026 📑 Paper: https://arxiv.org/pdf/2604.05117 💻 Project Page: http://vidground.etuagi.com 🔗 Code: https://github.com/reacher-z/vidground 📝 Description: VLMs struggle with video understanding due to text biases in benchmarks and training data. VidGround uses only visually grounded questions for post-training to eliminate these biases. This improves VLM performance and emphasizes the need for high-quality, visually grounded data. #VLMs #VideoUnderstanding #AI #MachineLearning #ComputerVision

Learning to Hint for Reinforcement Learning 📅 Publication Date: Apr 1, 2026 📑 Paper: https://arxiv.org/pdf/2604.00698 🔗 Code: https://github.com/Andree-9/HiLL 📝 Description: HiLL is a reinforcement learning framework that adaptively generates hints conditioned on reasoner errors to improve learning signals and transfer performance in group relative policy optimization. #AI #DataScience #MachineLearning #Research

Online Experiential Learning for Language Models 📅 Publication Date: Mar 17, 2026 📑 Paper: https://arxiv.org/pdf/2603.16856 💻 Project Page: https://github.com/microsoft/LMOps/tree/main/oel 🔗 Code: https://github.com/microsoft/LMOps/tree/main/oel 📝 Description: Online Experiential Learning enables continuous improvement of language models through deployment experience by extracting and consolidating experiential knowledge via on-policy distillation. #AI #DataScience #MachineLearning #Research

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding 📅 Publication Date: Mar 9, 2026 📑 Paper: https://arxiv.org/pdf/2603.13366 💻 Project Page: https://mlrm-lead.github.io/ 🔗 Code: https://github.com/mlrm-LEAD/mlrm-LEAD #AI #DataScience #MachineLearning #Research

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? 📅Publication Date: Mar 16, 2026 📑 Paper: https://arxiv.org/pdf/2603.15401 🔗 Code: https://github.com/GeniusHTX/SWE-Skills-Bench 📝 Description: Research using SWE-Skills-Bench shows agent skills offer limited benefits in real-world software engineering. Most skills yield no improvement, with an average pass-rate gain of only 1.2 percent. Only specialized skills provide meaningful gains, while some can even degrade performance. #SoftwareEngineering #AIagents #Benchmarking #AIresearch #LLM

Mixture of Style Experts for Diverse Image Stylization 📅 Publication Date: Mar 17, 2026 📑 Paper: https://arxiv.org/pdf/2603.16649 💻 Project Page: https://hh-lg.github.io/StyleExpert-Page/ 🔗 Code: https://github.com/HVision-NKU/StyleExpert 📝Description: StyleExpert introduces a Mixture of Experts architecture for image stylization. It uses a unified style encoder and gating mechanism to handle diverse styles across semantic levels. This preserves semantics and material details better than existing methods. #AI #DataScience #MachineLearning #Research

🔥 Qwen3-TTS Technical Report 📅 Publication Date: Jan 22, 2026 📑 Paper: : https://arxiv.org/pdf/2601.15621 🔗 Code: https://github.com/QwenLM/Qwen3-TTS 📊 Models citing this paper: • https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice • https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign 🗃 Datasets citing this paper: • https://huggingface.co/datasets/Izzyzlin/CFSDD 🚀 Spaces citing this paper: • https://huggingface.co/spaces/Qwen/Qwen3-TTS • https://huggingface.co/spaces/Sovenok-Hacker/Qwen3-TTS • https://huggingface.co/spaces/katyado/Qwen3-TTS 📝 Description: The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities. The problem addressed by this research is the need for efficient and high-quality text-to-speech models that can support multiple languages and allow for fine-grained control over the output speech. #MultilingualTextToSpeech #TextToSpeechSynthesis

HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes 📅 Publication Date: Mar 17, 2026 📑 Paper: https://arxiv.org/pdf/2603.16587 💻 Project Page: https://histoatlas.com 🔗 Code: https://github.com/HistoAtlas/HistoAtlas 📝 Description: HistoAtlas is a pan-cancer computational map linking 38 H&E histomic features to patient outcomes and molecular profiles across 21 cancer types. It reveals new biology and allows biomarker discovery from routine slides. #AI #DataScience #MachineLearning #Research

TradingAgents: Multi-Agents LLM Financial Trading Framework 📅 Publication Date: Dec 28, 2024 📑 Paper: https://arxiv.org/pdf/2412.20138 🔗 Code: https://github.com/tauricresearch/tradingagents 🚀 Spaces citing this paper: • https://huggingface.co/spaces/shanghengdu/LLM-Agent-Optimization-PaperList • https://huggingface.co/spaces/tahp0604/ai-stock-watchlist 📝 Description: The paper introduces TradingAgents, a multi-agent framework that utilizes large language models for stock trading, simulating the collaborative dynamics of real-world trading firms. The framework consists of various agents, including fundamental analysts, sentiment analysts, technical analysts, and traders with different risk profiles, all powered by large language models. These agents work together to assess market conditions, manage risk, and make informed trading decisions. The framework also includes researcher agents that evaluate market conditions and a risk management team that monitors exposure.