大学 × 全分野
奈良先端科学技術大学院大学
全分野 / 2022–2026 LIVE
掲載論文 94 本
論文一覧
94 本
このEditionのランキングに掲載している論文です。同じ大学の複数著者による共著は1本にまとめています。
分野をまたぐ同一論文も1本です。総合ポイントは、分野別順位に基づく別の指標です。
2026年
- SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
掲載ID:
doi:10.1609/aaai.v40i40.40733 - VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction
掲載ID:
doi:10.1609/aaai.v40i12.37938 - Corpus-Dependent Subcharacter Encoding via HMM-Guided Code Assignment
掲載ID:
acl-anthology:2026.acl-long.1596 - CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models
掲載ID:
acl-anthology:2026.acl-long.2132 - HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences
掲載ID:
acl-anthology:2026.acl-long.2189 - One Single Hub Text Breaks CLIP: Identifying Vulnerabilities in Cross-Modal Encoders via Hubness
掲載ID:
acl-anthology:2026.acl-long.2186 - Revisiting Non-Verbatim Memorization in Large Language Models: The Role of Entity Surface Forms
掲載ID:
acl-anthology:2026.acl-long.2178 - Challenges in Synchronous & Remote Collaboration Around Visualization
掲載ID:
doi:10.1145/3772318.3791117公立はこだて未来大学 / 北海道情報大学 / 奈良先端科学技術大学院大学 / お茶の水女子大学 / 東京大学
- Estimating Shared Mental Models via Communication-Categorized Directed Graphs
掲載ID:
doi:10.1145/3772318.3791718 - When the World Opens up: Journeys of People with Intellectual Disabilities in Social Virtual Reality
掲載ID:
doi:10.1145/3772318.3791783 - ARMS: Anchor–Relational Motion Streaming for Seamless Solo-Social Motion Transitions
掲載ID:
ecva:eccv2026:05555 - Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion
掲載ID:
ecva:eccv2026:03677 - Consensus Group Relative Policy Optimization for Text Generation
掲載ID:
acl-anthology:2026.emnlp-main.1459 - MobQA: A Benchmark Dataset for Semantic Understanding of Human Mobility Data through Question Answering
掲載ID:
acl-anthology:2026.emnlp-main.2223 - Neuro-Symbolic Reasoning with External Inference Tools Mitigates Bias from Sub-Formula Level Logical Structure
掲載ID:
acl-anthology:2026.emnlp-main.2564 - Once a Tree, Always a Tree? Cross-lingual Transfer of Hierarchical Generalization in Language Models
掲載ID:
acl-anthology:2026.emnlp-main.2682奈良先端科学技術大学院大学 / 静岡大学 / 東北大学
- Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding
掲載ID:
acl-anthology:2026.emnlp-main.2570 - ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws
掲載ID:
acl-anthology:2026.emnlp-main.1080奈良先端科学技術大学院大学 / 大阪大学 / 早稲田大学
- Where Do Vision-Language Models Fail on Abstract Reasoning? An Information Processing Analysis of ARC
掲載ID:
acl-anthology:2026.emnlp-main.2595 - Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs
掲載ID:
acl-anthology:2026.emnlp-main.66 - Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models
掲載ID:
openreview:mvlwhrg71j - Noisy-Channel Minimum Bayes Risk Decoding
掲載ID:
openreview:2qnptcsu7l - RePo: Language Models with Context Re-Positioning
掲載ID:
openreview:rslh9nuykk - OIPP: Object-Adaptive Impact Point Predictor for Catching Diverse In-Flight Objects
掲載ID:
iros:2026:580 - Successive Height Preintegration for a Height-Interdependent Path Formulation of Multiple Bounces in Smith Microfacet BRDFs
掲載ID:
doi:10.1145/3799902.3811194千葉大学 / 京都大学 / 奈良先端科学技術大学院大学
2025年
- CoAM: Corpus of All-Type Multiword Expressions
掲載ID:
acl-anthology:2025.acl-long.1311 - Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
掲載ID:
acl-anthology:2025.acl-long.916 - Disambiguating Reference in Visually Grounded Dialogues through Joint Modeling of Textual and Multimodal Semantic Structures
掲載ID:
acl-anthology:2025.acl-long.547 - Diversity Explains Inference Scaling Laws: Through a Case Study of Minimum Bayes Risk Decoding
掲載ID:
acl-anthology:2025.acl-long.1410 - Graph-Structured Trajectory Extraction from Travelogues
掲載ID:
acl-anthology:2025.acl-long.690 - Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation
掲載ID:
acl-anthology:2025.acl-long.1052 - Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
掲載ID:
acl-anthology:2025.acl-long.1508 - Theoretical Guarantees for Minimum Bayes Risk Decoding
掲載ID:
acl-anthology:2025.acl-long.793 - Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
掲載ID:
acl-anthology:2025.acl-long.149 - Cyberoception: Finding A Painlessly-Measurable New Sense In The Cyberworld Towards Emotion-awareness In Computing
掲載ID:
doi:10.1145/3706598.3713638慶應義塾大学 / 奈良先端科学技術大学院大学 / 東京大学
- UMotion: Uncertainty-driven Human Motion Estimation from Inertial and Ultra-wideband Units
掲載ID:
doi:10.1109/cvpr52734.2025.00664 - FilBench: Can LLMs Understand and Generate Filipino?
掲載ID:
acl-anthology:2025.emnlp-main.127 - Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors
掲載ID:
acl-anthology:2025.emnlp-main.313 - Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark
掲載ID:
acl-anthology:2025.emnlp-main.1018 - LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous Instructions
掲載ID:
acl-anthology:2025.emnlp-main.1734 - Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality
掲載ID:
acl-anthology:2025.emnlp-main.1138東京科学大学 / 名古屋工業大学 / 奈良先端科学技術大学院大学 / 東京大学
- Multilingual Dialogue Generation and Localization with Dialogue Act Scripting
掲載ID:
acl-anthology:2025.emnlp-main.1670 - SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala
掲載ID:
acl-anthology:2025.emnlp-main.1673 - Feasibility-Aware Imitation Learning from Observations Through a Hand-Mounted Demonstration Interface
掲載ID:
doi:10.1109/icra55743.2025.11127364 - Learning Quiet Walking for a Small Home Robot
掲載ID:
doi:10.1109/icra55743.2025.11128174 - ICCO: Learning an Instruction-conditioned Coordinator for Language-guided Task-aligned Multi-robot Control
掲載ID:
doi:10.1109/iros60139.2025.11247312 - Inspiring External Human-Machine Interface Designs for Autonomous Personal Mobility Vehicle: Causal Discovering the Influence of Passengers’ Personality Traits on User Experience
掲載ID:
doi:10.1109/iros60139.2025.11246801 - J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception
掲載ID:
doi:10.1109/iros60139.2025.11246615 - AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising
掲載ID:
acl-anthology:2025.naacl-long.391 - How to Make the Most of LLMs’ Grammatical Knowledge for Acceptability Judgments
掲載ID:
acl-anthology:2025.naacl-long.380 - LegalViz: Legal Text Visualization by Text To Diagram Generation
掲載ID:
acl-anthology:2025.naacl-long.339東京科学大学 / 奈良先端科学技術大学院大学 / 東京大学
- Tonguescape: Exploring Language Models Understanding of Vowel Articulation
掲載ID:
acl-anthology:2025.naacl-long.627 - WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
掲載ID:
acl-anthology:2025.naacl-long.167 - Less is More: Local Intrinsic Dimensions of Contextual Language Models
掲載ID:
neurips:2025:61c2c6338033da68885e0226881cbe71
2024年
- Developer-Applied Accelerations in Continuous Integration: A Detection Approach and Catalog of Patterns
掲載ID:
doi:10.1145/3691620.3695533 - MindTalker: Navigating the Complexities of AI-Enhanced Social Engagement for People with Early-Stage Dementia
掲載ID:
doi:10.1145/3613904.3642538 - ShareYourReality: Investigating Haptic Feedback and Agency in Virtual Avatar Co-embodiment
掲載ID:
doi:10.1145/3613904.3642425 - CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model
掲載ID:
doi:10.1007/978-3-031-73661-2_11奈良先端科学技術大学院大学 / 東京大学 / 早稲田大学
- Are Data Augmentation Methods in Named Entity Recognition Applicable for Uncertainty Estimation?
掲載ID:
acl-anthology:2024.emnlp-main.1049 - Can Language Models Induce Grammatical Knowledge from Indirect Evidence?
掲載ID:
acl-anthology:2024.emnlp-main.1146 - Exploring Intrinsic Language-specific Subspaces in Fine-tuning Multilingual Neural Machine Translation
掲載ID:
acl-anthology:2024.emnlp-main.1177 - LLMs Are Zero-Shot Context-Aware Simultaneous Translators
掲載ID:
acl-anthology:2024.emnlp-main.69 - SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
掲載ID:
acl-anthology:2024.emnlp-main.296 - Simul-MuST-C: Simultaneous Multilingual Speech Translation Corpus Using Large Language Model
掲載ID:
acl-anthology:2024.emnlp-main.1238 - Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Pair
掲載ID:
acl-anthology:2024.emnlp-main.1248 - Generative AI for Pull Request Descriptions: Adoption, Impact, and Developer Interventions
掲載ID:
doi:10.1145/3643773 - "My GitHub Sponsors profile is live!" Investigating the Impact of Twitter/X Mentions on GitHub Sponsors
掲載ID:
doi:10.1145/3597503.3639127 - Domain Randomization-free Sim-to-Real : An Attention-Augmented Memory Approach for Robotic Tasks
掲載ID:
doi:10.1109/iros58592.2024.10801944 - How Powerful is Graph Filtering for Recommendation
掲載ID:
doi:10.1145/3637528.3671789Web, Data Mining & Information Retrieval
九州大学 / 奈良先端科学技術大学院大学 / 大阪成蹊大学
- Does Pre-trained Language Model Actually Infer Unseen Links in Knowledge Graph Completion?
掲載ID:
acl-anthology:2024.naacl-long.447 - Subspace Representations for Soft Set Operations and Sentence Similarities
掲載ID:
acl-anthology:2024.naacl-long.192京都大学 / 奈良先端科学技術大学院大学 / 東北大学
- Selfrionette: A Fingertip Force-Input Controller for Continuous Full-Body Avatar Manipulation and Diverse Haptic Interactions
掲載ID:
doi:10.1145/3654777.3676409
2023年
- Comparative evaluation of boundary-relaxed annotation for Entity Linking performance
掲載ID:
acl-anthology:2023.acl-long.458 - Subset Retrieval Nearest Neighbor Machine Translation
掲載ID:
acl-anthology:2023.acl-long.10 - Repeated Builds During Code Review: An Empirical Study of the OpenStack Community
掲載ID:
doi:10.1109/ase56229.2023.00030 - Para Cima y Pa’ Abajo: Building Bridges Between HCI Research in Latin America and in the Global North
掲載ID:
doi:10.1145/3544548.3581138 - The "Conversation" about Loss: Understanding How Chatbot Technology was Used in Supporting People in Grief.
掲載ID:
doi:10.1145/3544548.3581154 - NLOS-NeuS: Non-line-of-sight Neural Implicit Surface
掲載ID:
doi:10.1109/iccv51070.2023.00966 - RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4D
掲載ID:
doi:10.1109/iccv51070.2023.01396 - Domains as Objectives: Multi-Domain Reinforcement Learning with Convex-Coverage Set Learning for Domain Uncertainty Awareness
掲載ID:
doi:10.1109/iros55552.2023.10342236 - Learning Robotic Powder Weighing from Simulation for Laboratory Automation
掲載ID:
doi:10.1109/iros55552.2023.10342463 - Augmenting Language Models with Long-Term Memory
掲載ID:
neurips:2023:ebd82705f44793b6f9ade5a669d0f0bf - Bridging Discrete and Backpropagation: Straight-Through and Beyond
掲載ID:
neurips:2023:28b5dfc51e5ae12d84fb7c6172a00df4 - Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective
掲載ID:
neurips:2023:e6c2e85db1f1039177c4495ccd399ac4 - eat2pic
掲載ID:
doi:10.1145/3580784
2022年
- Shape From Thermal Radiation: Passive Ranging Using Multi-Spectral LWIR Measurements
掲載ID:
doi:10.1109/cvpr52688.2022.01233 - Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning
掲載ID:
pmlr:v162:kamigaito22a - Disturbance-injected Robust Imitation Learning with Task Achievement
掲載ID:
doi:10.1109/icra46639.2022.9812376 - Gaussian Process Self-triggered Policy Search in Weakly Observable Environments
掲載ID:
doi:10.1109/icra46639.2022.9811781 - Soft-Jig: A Flexible Sensing Jig for Simultaneously Fixing and Estimating Orientation of Assembly Parts
掲載ID:
doi:10.1109/icra46639.2022.9812094 - GitHub sponsors
掲載ID:
doi:10.1145/3510003.3510116 - Multi-Tier Platform for Cognizing Massive Electroencephalogram
掲載ID:
doi:10.24963/ijcai.2022/342 - MOTSLAM: MOT-assisted monocular dynamic SLAM using single-view depth estimation
掲載ID:
doi:10.1109/iros47612.2022.9982280福岡大学 / 九州大学 / 奈良先端科学技術大学院大学 / 東京大学
- Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
掲載ID:
neurips:2022:148c0aeea1c5da82f4fa86a09d4190da
掲載対象外の論文や未反映の論文は、この一覧には含まれません。