Data science research papers

Asymmetric Flow Models 📅 Publication Date: May 13, 2026 📑 Paper: https://arxiv.org/pdf/2605.12964 💻 Project Page: https://hanshengchen.com/asymflow/ 🔗 Code: https://github.com/Lakonik/LakonLab ⭐️ 324 📊 Models citing this paper: • https://huggingface.co/Lakonik/AsymFLUX.2-klein-9B • https://huggingface.co/Lakonik/AsymFlow-ImageNet • https://huggingface.co/OJ-1/AsymFLUX.2-klein-9B 📝 Description: The paper introduces Asymmetric Flow Modeling, a method for efficient high-dimensional flow-based generation. The problem with existing flow-based generation methods is that they require modeling high-dimensional noise, which is difficult even when the data has a strong low-rank structure. To address this, the authors propose a rank-asymmetric velocity parameterization that restricts noise prediction to a low-rank subspace while keeping data prediction full-dimensional. #AsymmetricFlowModels #FlowBasedGeneration #RankAsymmetricVelocity

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company 📅 Publication Date: Apr 24, 2026 📑 Paper: https://arxiv.org/pdf/2604.22446.pdf 🔗 Code: https://github.com/1mancompany/OneManCompany 📝 Description: OneManCompany (OMC) introduces an organizational framework for multi-agent systems that enables dynamic team assembly, governance, and improvement through portable agent identities and hierarchical decision-making processes.

📢 Advertising in this channel You can place an ad via Telega․io. It takes just a few minutes. Formats and current rates: View details

🔥 Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning 📅 Publication Date: Jun 9, 2026 📑 Paper: https://arxiv.org/pdf/2606.11087 💻Project Page: https://q-guided-flow.github.io/ 📝 Description: The paper proposes a reinforcement learning algorithm called QGF that improves policies at test time by using a value gradient to guide a pre-trained flow policy. The problem addressed is that incorporating flow models into reinforcement learning pipelines for policy improvement can be difficult due to stability and scalability issues. The method involves pre-training a reference flow policy and a value function critic, then using the value gradient to guide the reference policy to generate higher-value actions at test time, without any additional policy learning. #ReinforcementLearningAlgorithms #TestTimePolicyImprovement #QGFAlgorithm

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling 📅 Publication Date: May 8, 2026 📑 Paper: https://arxiv.org/pdf/2605.08083 💻 Project Page: https://zhengkid.github.io/AutoTTS-web/ 🔗 Code: https://github.com/zhengkid/AutoTTS 📝 Description: The paper proposes a novel approach to improve the performance of large language models through test-time scaling, which involves allocating additional computation during inference. Existing test-time scaling strategies are typically hand-crafted, relying on manual design and tuning of reasoning patterns and heuristics. This approach leaves much of the computation-allocation space unexplored, resulting in potential inefficiencies. To address this limitation, the authors introduce AutoTTS, an environment-driven framework that automates the discovery of test-time scaling strategies. Instead of designing individual strategies, researchers can create environments where optimal strategies can be discovered automatically. #LargeLanguageModels

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation 📅 Publication Date: Apr 27, 2026 📑 Paper: https://arxiv.org/pdf/2604.24764.pdf 🔗 Code: https://github.com/microsoft/World-R1 📝 Description: World-R1 framework improves video generation by incorporating 3D constraints through reinforcement learning and specialized text datasets while maintaining visual quality and scalability.

Code as Agent Harness 📅 Publication Date: May 18, 2026 📑 Paper: https://arxiv.org/pdf/2605.18747 🔗 Code: N/A 📝 Description: The paper discusses the concept of code as agent harness, where large language models are used as operational substrates for agent reasoning and execution in agentic systems. The authors argue that code is no longer just a target output, but serves as a unified infrastructure layer across multiple domains and applications. They introduce a unified view that centers code as the basis for agent infrastructure, and organize their survey around three connected layers: the harness interface, harness mechanisms, and scaling the harness. #AgenticSystems #LargeLanguageModels #AgentReasoning

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration 📅 Publication Date: May 19, 2026 📑 Paper: https://arxiv.org/pdf/2605.20025 💻 Project Page: https://github.com/aiming-lab/AutoResearchClaw 🔗 Code: https://github.com/huggingface 🗃Datasets citing this paper: • https://huggingface.co/datasets/AIMING-Lab-UNC/ARC-Bench 📝Description: AutoResearchClaw is a new autonomous research system that improves scientific discovery by incorporating human collaboration and iterative learning. The problem with existing autonomous research systems is that they often model the research process as a linear pipeline, relying on single agent reasoning and stopping when execution fails, without carrying experience across runs. #AutonomousResearchSystems #MultiAgentLearning #SelfReinforcingSystems

AgentSearchBench: A Benchmark for AI Agent Search in the Wild 📅 Publication Date: Apr 24, 2026 📑 Paper: https://arxiv.org/pdf/2604.22436 🔗 Code: N/A 📝 Description: AgentSearchBench is a new benchmark for finding suitable AI agents using execution-grounded performance signals from nearly 10,000 real-world agents. It shows that description-based similarity is insufficient, and lightweight behavioral signals significantly improve agent ranking. #AI #AIAgents #Benchmarking #AgentSearch #MachineLearning

Omnilingual MT: Machine Translation for 1,600 Languages 📅 Publication Date: Mar 17, 2026 📑 Paper: https://arxiv.org/pdf/2603.16309 🗃 Datasets citing this paper: https://huggingface.co/datasets/facebook/bouquet 🔗 Code: N/A 📝 Description: Omnilingual MT OMT is the first system to support over 1,600 languages. It uses specialized smaller LLMs 1B-8B to outperform 70B baselines, achieving high-quality translation and coherent generation in low-compute settings. #AI #DataScience #MachineLearning #HuggingFace #Research

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration 📅 Publication Date: May 4, 2026 📑 Paper: https://arxiv.org/pdf/2605.03042.pdf 🔗 Code: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep 📝 Description: ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.

Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents 📅 Publication Date: Apr 23, 2026 📑 Paper: https://arxiv.org/pdf/2604.22085 💻 Project Page: https://memanto.ai/ 🔗 Code: https://github.com/moorcheh-ai/memanto-evaluation 🗃 Datasets citing this paper: • https://huggingface.co/datasets/moorcheh/memanto-longmem-results • https://huggingface.co/datasets/moorcheh/memanto-locomo-results 📝 Description: Memanto introduces a universal, typed semantic memory layer for AI agents that bypasses complex semantic graphs. It uses an information-theoretic search engine for fast, overhead-free retrieval. This system achieves state-of-the-art accuracy on benchmarks with a single query and no ingestion cost. #AI #SemanticMemory #InformationRetrieval #AIAgents #MachineLearning

Probing Visual Planning in Image Editing Models 📅 Publication Date: Apr 23, 2026 📑 Paper: https://arxiv.org/pdf/2604.22868 💻 Project Page: https://spatigen.github.io/amaze.io/ 🔗 Github: https://github.com/spatigen/amaze 📝 Description: This paper redefines visual planning as a single-step image transformation using abstract puzzles for evaluation. Their EAR paradigm and AMAZE dataset reveal that current AI models, despite finetuning, cannot match human zero-shot efficiency, highlighting a gap in visual reasoning. #VisualPlanning #ImageEditing #ComputerVision #AIResearch #MachineLearning

Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization 📅 Publication Date: Jun 9, 2026 📑 Paper: https://arxiv.org/pdf/2606.11180 💻 Project Page: https://cvlab-kaist.github.io/LipForcing/ 📝 Description: The paper presents Lip Forcing, a novel autoregressive diffusion method for real-time video-to-video lip synchronization. The problem with existing diffusion-based lip synchronization models is that they require full-sequence bidirectional attention and many denoising steps, making them impractical for real-time inference. To address this issue, the authors propose a method that distills a large audio-conditioned bidirectional video diffusion teacher into smaller causal students. #LipSynchronization #AutoregressiveDiffusion #RealTimeVideoProcessing #VideoToVideoSynthesis #DiffusionBasedModels

Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets 📅 Publication Date: Apr 24, 2026 📑 Paper: https://arxiv.org/pdf/2604.22294 🔗 Code: N/A 📝 Description: SLIDERS tackles long-document QA by extracting information into a relational database and using SQL for structured reasoning. This avoids LLM context window issues and aggregation bottlenecks, significantly outperforming traditional methods on various benchmarks. #QuestionAnswering #NLP #AI #SQL #LongDocuments

LLM Safety From Within: Detecting Harmful Content with Internal Representations 📅 Publication Date: Apr 20, 2026 📑 Paper: https://arxiv.org/pdf/2604.18519 🔗 Code: https://github.com/CSSLab/SIREN 📊 Models citing this paper: • https://huggingface.co/UofTCSSLab/SIREN-Qwen3-0.6B • https://huggingface.co/UofTCSSLab/SIREN-Qwen3-4B • https://huggingface.co/UofTCSSLab/SIREN-Llama-3.2-1B 📝 Description: SIREN is a lightweight guard model that uses LLM internal layer features to detect harmful content, outperforming current models. It is more efficient, generalizes better, and requires significantly fewer parameters than existing guard models. #LLMSafety #AIethics #HarmfulContent #DeepLearning #NLP

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