主题图谱 / machine learning cs.lg

machine learning cs.lg

GeneTech 知识引擎共收录 752 篇相关科研实体，横跨 30 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

相关主题

代表性文献（按质量分排序，前 60 条）

• Diff Mining: Logit Differences Reveal Finetuning Objectives
  2026 · AI Agent 生态 · Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more …
• Expected Reward Prediction, with Applications to Model Routing
  2026 · AI 安全与对齐 · Reward models are a standard tool to score responses from LLMs. Reward models are built to rank responses to a fixed prompt sampled from a single model, for example to choose the best of n sampled responses. In this pape…
• Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards
  2026 · AI 安全与对齐 · Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety lan…
• Diff Mining: Logit Differences Reveal Finetuning Objectives
  2026 · AI 驱动科学发现 · Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more …
• FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
  2026 · AI 驱动科学发现 · Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ablation studies yet have never seen a biology reviewer demand contamina…
• First-Principles Atomistic Structure and Dynamics of Polyethylene During High-Pressure Radical Polymerization via Machine Learning Force Fields
  2026 · AI 驱动科学发现 · Polyethylene (PE) is one of the most commonly used synthetic polymers. While the synthesis and processing protocols for PE are well established, precise experimental assignment of microscopic structures at atomistic reso…
• Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning
  2026 · AI 驱动科学发现 · Pre-trained materials foundation models, or machine learning interatomic potentials, leverage general physicochemical knowledge to effectively approximate potential energy surfaces. However, they often require domain-spe…
• From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures
  2026 · AI 驱动科学发现 · Machine Learning Interatomic Potentials (MLIPs) sometimes fail to reproduce the physical smoothness of the quantum potential energy surface (PES), leading to erroneous behavior in downstream simulations that standard ene…
• Connecting Meteorite Spectra to Lunar Surface Composition Using Hyperspectral Imaging and Machine Learning
  2026 · 地外矿物 · We present an innovative, cost-effective framework integrating laboratory Hyperspectral Imaging (HSI) of the Bechar010 Lunar meteorite with ground-based lunar HSI and supervised Machine Learning(ML) to generate high-fide…
• A Bayes-Markov Neuromorphic Model of Cortical Orientation Selectivity: A Computational Re-implementation and Quantitative Simulation Study
  2026 · 生物计算 · The emergence of orientation selectivity in the primary visual cortex (V1) remains a central question in computational neuroscience. Shirazi's Bayes-Markov model proposed a probabilistic explanation for how orientation-s…
• SCOPE: Siamese Contrastive Operon Pair Embeddings for Functional Sequence Representation and Classification
  2026 · 生物计算 · Identifying operons is a fundamental step in understanding prokaryotic gene regulation, as classifying genes into operons supports the reconstruction of regulatory networks, functional annotation of unannotated genes, an…
• What Makes a Bacterial Model a Good Reservoir Computer? Predicting Performance from Separability and Similarity
  2026 · 生物计算 · Biological systems are promising substrates for computation because they naturally process environmental information through complex internal dynamics. In this study, we investigate whether bacterial metabolic models can…
• Scalable Message-Passing Quantum Graph Neural Networks in the Weisfeiler-Leman Hierarchy
  2026 · 生物计算 · Graphs provide a natural language for relational data in chemistry, biology and optimisation. Graph neural networks (GNNs) have driven much of the recent progress in learning from such data through message passing, a sin…
• Redakto - The Incognito Tab for LLMs
  2026 · 医疗人工智能 · Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that pe…
• Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors
  2026 · 医疗人工智能 · MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown that magnitude-only measurements may provide complementar…
• Flow Matching Meets 3D Curvilinear Structure Segmentation in Medical Imaging
  2026 · 医疗人工智能 · Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology. While deep learning…
• A 2-Block Architecture for Real-Time EEG Gait Decoding: A Pilot Study
  2026 · 仿生智能 · Closed-loop lower-limb exoskeleton control via Electroencephalography (EEG) remains limited by motion artifacts, low signal-to-noise ratio, and binary gait formulations that fail to capture full cortical gait complexity.…
• Deep Sleep Classification via EEG Signal Criticality: A Passive BCI Approach for Sleep-Improvement Neurofeedback
  2026 · 仿生智能 · Automated sleep staging is a fundamental application of passive Brain-Computer Interfaces (pBCI), decoding spontaneous neural states to enable closed-loop interventions independent of user intent. This study evaluates cr…
• Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
  2026 · 脑科学 · Recent advances at the intersection of control theory, neuroscience, and machine learning have revealed novel mechanisms by which dynamical systems perform computation. These advances encompass a wide range of conceptual…
• FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes
  2026 · 脑科学 · Scientific peer review datasets have trained AI systems exclusively on Computer Science and Machine Learning venues, producing models that critique ablation studies yet have never seen a biology reviewer demand contamina…
• 3D Underwater Path Planning via Generative Flow Field Surrogates
  2026 · 深海科技 · Autonomous underwater vehicle (AUV) launch and recovery (LAR) into the hull of an advancing host platform requires traversal of a complex, three-dimensional propeller wake whose hydrodynamic structure cannot be character…
• GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction
  2026 · 具身智能 · Whole-body motion tracking policies turn a humanoid into a robust control interface: the teleoperator---or an upstream model---only supplies a coarse movement intent, while the low-level policy keeps the robot balanced a…
• Earth Science Foundation Models: From Perception to Reasoning and Discovery
  2026 · 具身智能 · Large foundation models (FMs) are transforming Earth science by integrating heterogeneous multimodal data, such as multi-platform imagery, gridded reanalysis data, diverse geophysical and geochemical observations, and do…
• From Perception to Action: Spatial AI Agents and World Models
  2026 · 具身智能 · While large language models have become the prevailing approach for agentic reasoning and planning, their success in symbolic domains does not readily translate to the physical world. Spatial intelligence, the ability to…
• RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
  2026 · 具身智能 · Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an effective fix by easing edge-device computing pressure to mee…
• KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
  2026 · 具身智能 · Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an optimization strategy that can boost inference speed. Two key issues emerge when…
• 3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
  2026 · 具身智能 · Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe and ungrounded decisions. Existing infe…
• Towards Miniature Humanoid Tele-Loco-Manipulation Using Virtual Reality and Reinforcement Learning
  2026 · 具身智能 · Full-sized humanoid robot capabilities have grown exponentially in recent years, aiming towards general-purpose deployment in human environments. A popular control method used by manufacturers utilizes Virtual Reality fo…
• Egocentric Tactile and Proximity Sensors as Observation Priors for Humanoid Collision Avoidance
  2026 · 具身智能 · Collision-free motion is often aided by tactile and proximity sensors distributed on the body of the robot due to their resistance to occlusion as opposed to external cameras. However, how to shape the sensor's propertie…
• MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives
  2026 · 具身智能 · Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key challenges in bridging research and prod…
• Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation
  2026 · 具身智能 · State-of-the-art vision-language-action (VLA) models such as $π_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor mismatches in hardwa…
• From Recovery to Drop-off: How Action Post-training Reduces a VLM's Late-Layer Depth Decodability
  2026 · 具身智能 · How much of a vision-language model's (VLM) spatial understanding remains after the action post-training process of building a vision-language-action model (VLA)? We probe depth perception, a primitive of spatiogeometric…
• Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
  2026 · 具身智能 · Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly t…
• SPEAR: A Simulator for Photorealistic Embodied AI Research
  2026 · 具身智能 · Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering s…
• RIBOSPAN: A Long-Context RNA Foundation Model for Versatile RNA Modeling
  2026 · 基因技术工具 · Full-length RNAs, particularly messenger RNAs, often exceed the context lengths used to pretrain existing RNA foundation models, limiting complete-transcript modeling at single-nucleotide resolution. We present RIBOSPAN,…
• Development and Design of FLKit: A Structured Onboarding Toolkit for Federated Learning in Health and Life Sciences
  2026 · 生命科学 · Federated learning lets institutions train shared models without moving their data, which makes it a natural fit for health and life sciences research under strict privacy regulation. The methods are maturing fast, but t…
• Learning Fast Monomial Orders for Gröbner Basis Computations
  2026 · 生命科学 · The efficiency of Gröbner basis computation, the standard engine for solving systems of polynomial equations, depends on the choice of monomial ordering. Despite a near-continuum of possible monomial orders, most impleme…
• eVTOL Aircraft Energy Overhead Estimation under Conflict Resolution in High-Density Airspaces
  2026 · 低空经济 · Electric vertical takeoff and landing (eVTOL) aircraft operating in high-density urban airspace must maintain safe separation through tactical conflict resolution, yet the energy cost of such maneuvers has not been syste…
• Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Design
  2026 · 低空经济 · In this paper, we generate conceptual engineering designs of electric vertical take-off and landing (eVTOL) aircraft. We follow the paradigm of simulation-based inference (SBI), whereby we look to learn a posterior distr…
• Optimistic Online LQR via Intrinsic Rewards
  2026 · 低空经济 · Optimism in the face of uncertainty is a popular approach to balance exploration and exploitation in reinforcement learning. Here, we consider the online linear quadratic regulator (LQR) problem, i.e., to learn the LQR c…
• Integrating spectral and morphological plant features with decision-tree models for early-season cotton biomass and nitrogen status estimation from multi-year UAV data
  2026 · 低空经济 · Precision nitrogen (N) management (PNM) for cotton requires in-season monitoring of crop growth parameters and N status indicators to decide fertilizer timing, placement, and application rates for optimal canopy developm…
• Vision Language Action (VLA) Models for Unmanned Aerial Robotics and Bimanual Manipulation: A Review
  2026 · 低空经济 · Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, allowing a robot to follow instructions such as fold the towel or fly t…
• CRB-Driven Beamforming and Trajectory Optimization for UAV-assisted ISAC System
  2026 · 低空经济 · In this paper, we study an unmanned aerial vehicle (UAV)-assisted integrated sensing and communication (ISAC) system, where a UAV enhances the sensing capability of a base station (BS) towards a target while ensuring rel…
• Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
  2026 · 低空经济 · This paper presents a learning-augmented trajectory planning framework for cooperative unmanned aerial vehicle (UAV) and unmanned ground vehicle (UGV) handover missions. While centralized trajectory optimization ensures …
• Task-free Adaptive Meta Black-box Optimization
  2026 · 低空经济 · Handcrafted optimizers become prohibitively inefficient for complex black-box optimization (BBO) tasks. MetaBBO addresses this challenge by meta-learning to automatically configure optimizers for low-level BBO tasks, the…
• Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent
  2026 · 类脑计算 · The ability to train spiking neural networks is essential for modeling biological neural networks as well as for neuromorphic computing. However, for the extensively used leaky integrate-and-fire (LIF) neurons, arbitrari…
• OceanGym: A Benchmark Environment for Underwater Embodied Agents
  2025 · AI Agent 生态 · We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater…
• Smoothed Embeddings for Robust Language Models
  2025 · AI 安全与对齐 · Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vu…
• Aligning Compound AI Systems via System-level DPO
  2025 · AI 安全与对齐 · Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their e…
• HIP: Hessian Interatomic Potentials without derivatives
  2025 · AI 驱动科学发现 · Molecular Hessians, the second derivatives of the potential energy, are fundamental to many workflows in computational chemistry. Usually, accurate Hessians are computationally expensive to calculate and scale poorly wit…
• OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systems
  2025 · AI 驱动科学发现 · We introduce OrbitAll, a geometry- and physics-informed deep learning framework that encodes any molecular system with arbitrary charges, spins, and environmental effects using electronic structure information. It utiliz…
• FastCSP: Accelerated Molecular Crystal Structure Prediction with Universal Model for Atoms
  2025 · AI 驱动科学发现 · Molecular crystal structure prediction (CSP) is essential for applications in pharmaceuticals and organic electronics. However, CSP remains challenging and computationally intensive due to the need to explore a large sea…
• P-DRUM: Post-hoc Descriptor-based Residual Uncertainty Modeling for Machine Learning Potentials
  2025 · AI 驱动科学发现 · Ensemble method is considered the gold standard for uncertainty quantification (UQ) in machine learning interatomic potentials (MLIPs). However, their high computational cost can limit its practicality. Alternative techn…
• A practical guide to machine learning interatomic potentials -- Status and future
  2025 · AI 驱动科学发现 · The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spir…
• scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
  2025 · 生物计算 · Advances in single-cell sequencing have enabled high-resolution profiling of diverse molecular modalities, while integrating unpaired multi-omics single-cell data remains challenging. Existing approaches either rely on p…
• A Model-Driven Engineering Approach to AI-Powered Healthcare Platforms
  2025 · 医疗人工智能 · Artificial intelligence (AI) has the potential to transform healthcare by supporting more accurate diagnoses and personalized treatments. However, its adoption in practice remains constrained by fragmented data sources, …
• Keeping Medical AI Healthy and Trustworthy: A Review of Detection and Correction Methods for System Degradation
  2025 · 医疗人工智能 · Artificial intelligence (AI) is increasingly integrated into modern healthcare, offering powerful support for clinical decision-making. However, in real-world settings, AI systems may experience performance degradation o…
• EEG-to-Gait Decoding via Phase-Aware Representation Learning
  2025 · 仿生智能 · Accurate decoding of lower-limb motion from EEG signals is essential for advancing brain-computer interface (BCI) applications in movement intent recognition and control. This study presents NeuroDyGait, a two-stage, pha…
• BrainForm: a Serious Game for BCI Training and Data Collection
  2025 · 仿生智能 · $\textit{BrainForm}$ is a gamified Brain-Computer Interface (BCI) training system designed for scalable data collection using consumer hardware and a minimal setup. We investigated (1) how users develop BCI control skill…
• Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet
  2025 · 仿生智能 · Achieving both accurate and interpretable classification of motor-imagery EEG remains a key challenge in brain-computer interface (BCI) research. In this paper, we compare a transparent fuzzy-reasoning approach (ANFIS-FB…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl http://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl http://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。