All papers
Every paper that carries a page of its own here. The Papers page leads with what is trending and lets you filter the recent catalog; this is the plain index of the rest.
Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and DissertationsarXiv 2021Lexically Grounded Subword SegmentationarXiv 2024EcoVerse: An Annotated Twitter Dataset for Eco-Relevance Classification, Environmental Impact Analysis, and Stance DetectionarXiv 2024Bregman Proximal Langevin Monte Carlo via Bregman--Moreau EnvelopesarXiv 2022Presumed Cultural Identity: How Names Shape LLM ResponsesarXiv 2025On the Existence of Universal Lottery Ticketson-the-existence-of-universal-lottery-ticketsPremier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image GenerationarXiv 2026On Evaluating Explanation Utility for Human-AI Decision Making in NLParXiv 2024Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable PerturbationsEMNLP (MRL) 2021 11Exploring LLM Reasoning Through Controlled Prompt VariationsarXiv 2025Effective Structured Prompting by Meta-Learning and Representative VerbalizerarXiv 2023Measuring the Robustness of NLP Models to Domain ShiftsarXiv 2023Generative Classifiers Avoid Shortcut SolutionsarXiv 2025Regularization-based Pruning of Irrelevant Weights in Deep Neural ArchitecturesarXiv 2022Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction TuningarXiv 2024Distilling the Knowledge of Romanian BERTs Using Multiple TeachersLREC 2022 6Learn the Time to Learn: Replay Scheduling in Continual LearningarXiv 2022QuakeSet: A Dataset and Low-Resource Models to Monitor Earthquakes through Sentinel-1arXiv 2024Selection Bias Induced Spurious Correlations in Large Language ModelsarXiv 2022Speaking Multiple Languages Affects the Moral Bias of Language ModelsarXiv 2022Mind the (Belief) Gap: Group Identity in the World of LLMsarXiv 2025EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question
AnsweringarXiv 2024Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Cloudsadaptive-topological-feature-via-persistentMixture Proportion Estimation Beyond IrreducibilityarXiv 2023Towards Semantic Versioning of Open Pre-trained Language Model Releases
on Hugging FacearXiv 2024Max-Affine Spline Insights Into Deep Network Pruningmax-affine-spline-insights-into-deep-networkSpoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language ModelsarXiv 2024Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge PerspectivesarXiv 2024Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based AgentsarXiv 2024[MASK] is All You NeedarXiv 2024WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion ModelsarXiv 2024Interpreting and Steering Protein Language Models through Sparse AutoencodersarXiv 2025Confidence in the Reasoning of Large Language ModelsarXiv 2024Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You NeedCVPR 2023 1MaPa: Text-driven Photorealistic Material Painting for 3D ShapesarXiv 2024Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning AttacksarXiv 2023IsoBench: Benchmarking Multimodal Foundation Models on Isomorphic RepresentationsarXiv 2024CARL: Congestion-Aware Reinforcement Learning for Imitation-based
Perturbations in Mixed Traffic ControlarXiv 2024Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal DataarXiv 2024RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban ScenesarXiv 2024Gotta Detect 'Em All: Fake Base Station and Multi-Step Attack Detection
in Cellular NetworksarXiv 2024CrossAug: A Contrastive Data Augmentation Method for Debiasing Fact Verification ModelsarXiv 2021Revisiting Token Dropping Strategy in Efficient BERT PretrainingarXiv 2023IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian ContextarXiv 2024BUCA: A Binary Classification Approach to Unsupervised Commonsense Question AnsweringarXiv 2023Accelerated Stochastic Optimization Methods under Quasar-convexityarXiv 2023KPE: Keypoint Pose Encoding for Transformer-based Image GenerationarXiv 2022ECBD: Evidence-Centered Benchmark Design for NLParXiv 2024I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionarXiv 2023Predictive Flows for Faster Ford-FulkersonarXiv 2023Bootstrap Embedding on a Quantum ComputerarXiv 2023Convergence of Proximal Point and Extragradient-Based Methods Beyond
Monotonicity: the Case of Negative ComonotonicityarXiv 2022Sharing emotions at scale: The Vent datasetarXiv 2019Identification of Low Surface Brightness Tidal Features in Galaxies
Using Convolutional Neural NetworksarXiv 2018Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net)
for Medical Image SegmentationarXiv 2018MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face RecognitionarXiv 2016AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance LabelsarXiv 2024Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical ReasoningarXiv 2025ChatBench: From Static Benchmarks to Human-AI EvaluationarXiv 2025Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language ModelsarXiv 2024Precise spiking motifs in neurobiological and neuromorphic dataarXiv 2024A Few-shot Approach to Resume Information Extraction via PromptsarXiv 2022Hate Speech and Offensive Language Detection in BengaliarXiv 2022End-to-end Convolutional Network for Saliency PredictionarXiv 2015TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using AgentsarXiv 2026Evaluating Cognitive Age Alignment in Interactive AI AgentsarXiv 2026A Gradient Boosting Approach for Training Convolutional and Deep Neural NetworksarXiv 2023Where is the answer? Investigating Positional Bias in Language Model Knowledge ExtractionarXiv 2024Competition and Diversity in Generative AIarXiv 2024Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop ReasoningarXiv 2024Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge DistillationarXiv 2023Personalized Algorithmic Recourse with Preference ElicitationarXiv 2022The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic TasksarXiv 2025Translation Errors Significantly Impact Low-Resource Languages in Cross-Lingual LearningarXiv 2024LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs - No Silver Bullet for LC or RAG RoutingarXiv 2025Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classificationarXiv 2023OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization ModelingarXiv 2025Investigating Language Preference of Multilingual RAG SystemsarXiv 2025BanglaAbuseMeme: A Dataset for Bengali Abusive Meme ClassificationarXiv 2023Large Language Models and Mathematical Reasoning FailuresarXiv 2025Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?arXiv 2024Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-JudgearXiv 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision ModelsarXiv 2025On-Device LLMs for Home Assistant: Dual Role in Intent Detection and Response GenerationarXiv 2025Are Rules Meant to be Broken? Understanding Multilingual Moral Reasoning as a Computational Pipeline with UniMoralarXiv 2025Escaping saddle points in zeroth-order optimization: the power of
two-point estimatorsarXiv 2022Are Models Biased on Text without Gender-related Language?arXiv 2024Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge TypesarXiv 2024Using Transfer Learning for Code-Related TasksarXiv 2022Optimized Conformal Selection: Powerful Selective Inference After Conformity Score OptimizationarXiv 2024SpiritSight Agent: Advanced GUI Agent with One LookCVPR 2025 1Vision-Language Models Struggle to Align Entities across ModalitiesarXiv 2025Social-ecological feedbacks drive tipping points in farming system
diversificationarXiv 2022Translation Consistent Semi-supervised Segmentation for 3D Medical
ImagesarXiv 2022START: Self-taught Reasoner with ToolsarXiv 2025Think Twice, Click Once: Enhancing GUI Grounding via Fast and Slow SystemsarXiv 2025LOGIN: A Large Language Model Consulted Graph Neural Network Training FrameworkarXiv 2024A Language Agent for Autonomous DrivingarXiv 2023Large language models can consistently generate high-quality content for election disinformation operationsarXiv 2024A benchmark of categorical encoders for binary classificationa-benchmark-of-categorical-encoders-forAnnoLLM: Making Large Language Models to Be Better Crowdsourced AnnotatorsarXiv 2023Target-Agnostic Gender-Aware Contrastive Learning for Mitigating Bias in Multilingual Machine TranslationarXiv 2023Small Language Models Need Strong Verifiers to Self-Correct ReasoningarXiv 2024Why are Some Bugs Non-Reproducible? An Empirical Investigation using
Data FusionarXiv 2021Improving Interpersonal Communication by Simulating Audiences with Language ModelsarXiv 2023DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual VocabulariesarXiv 2025Entity Linking in the Job Market DomainarXiv 2024KaggleDBQA: Realistic Evaluation of Text-to-SQL ParsersarXiv 2021On the Limitations of Temperature Scaling for Distributions with OverlapsarXiv 2023Dive into the Chasm: Probing the Gap between In- and Cross-Topic GeneralizationarXiv 2024Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias ElicitationarXiv 2024SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer SecurityarXiv 2023AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep LearningarXiv 2022Training-free Diffusion Acceleration with Bottleneck SamplingarXiv 2025The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral DilemmasarXiv 2025Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word CamouflagearXiv 2022First Light And Reionisation Epoch Simulations (FLARES) II: The
Photometric Properties of High-Redshift GalaxiesarXiv 2020Doubly Optimal No-Regret Learning in Monotone GamesarXiv 2023Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse ExplorationCVPR 2025 1Hawkeye:Efficient Reasoning with Model CollaborationarXiv 2025PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech RepresentationsarXiv 2022VGGSound: A Large-scale Audio-Visual DatasetarXiv 2020GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI AgentsarXiv 2025UNet++: Redesigning Skip Connections to Exploit Multiscale Features in
Image SegmentationarXiv 2019The Effect of Person-Specific Biometrics in Improving Generic Stress
Predictive ModelsarXiv 2019UER: An Open-Source Toolkit for Pre-training Modelsuer-an-open-source-toolkit-for-pre-training-1Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context LearningarXiv 2023JointViT: Modeling Oxygen Saturation Levels with Joint Supervision on Long-Tailed OCTAarXiv 2024On the SDEs and Scaling Rules for Adaptive Gradient AlgorithmsarXiv 2022Multilingual Previously Fact-Checked Claim RetrievalarXiv 2023Human Decision-making is Susceptible to AI-driven ManipulationarXiv 2025PipeDream: Fast and Efficient Pipeline Parallel DNN TrainingarXiv 2018CrisisMMD: Multimodal Twitter Datasets from Natural DisastersarXiv 2018FD-MobileNet: Improved MobileNet with a Fast Downsampling StrategyarXiv 2018Sentinel: A Hyper-Heuristic for the Generation of Mutant Reduction StrategiesarXiv 2021The iNaturalist Species Classification and Detection Datasetthe-inaturalist-species-classification-and-1Non-convex optimization for self-calibration of direction-dependent
effects in radio interferometric imagingarXiv 2017An OFDM Signal Identification Method for Wireless Communications SystemsarXiv 2014Fractional WKB ApproximationarXiv 2007StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy OptimizationarXiv 2025Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMsarXiv 2024Global Voices, Local Biases: Socio-Cultural Prejudices across LanguagesarXiv 2023Simultaneous Speech Translation for Live Subtitling: from Delay to DisplayMTSummit 2021 8On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale CompetitionarXiv 2021JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language ModelsarXiv 2024Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language ModelingarXiv 2023NSF-SciFy: Mining the NSF Awards Database for Scientific ClaimsarXiv 2026TreeRPO: Tree Relative Policy OptimizationarXiv 2025Continual Learning for Instruction Following from Realtime Feedbackcontinual-learning-for-instruction-followingScent of Knowledge: Optimizing Search-Enhanced Reasoning with Information ForagingarXiv 2025LPO: Towards Accurate GUI Agent Interaction via Location Preference OptimizationarXiv 2025Does fine-tuning GPT-3 with the OpenAI API leak personally-identifiable information?arXiv 2023A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory TextsarXiv 2025VQA Therapy: Exploring Answer Differences by Visually Grounding AnswersICCV 2023 1ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain ConcatenationarXiv 2021Omni-Persona: Systematic Benchmarking and Improving Omnimodal PersonalizationarXiv 2026Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RLarXiv 2023GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMsarXiv 2026Training Curricula for Open Domain Answer Re-RankingarXiv 2020Towards Better Evaluation for Generated Patent ClaimsarXiv 2025Generalized Disparate Impact for Configurable Fairness Solutions in MLarXiv 2023Deterministic equivalent and error universality of deep random features learningarXiv 2023Compressing Chain-of-Thought in LLMs via Step EntropyarXiv 2025AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the WildarXiv 2026Chasing the Tail: Effective Rubric-based Reward Modeling for Large
Language Model Post-TrainingarXiv 2025Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic SpacearXiv 2024Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert MergingarXiv 2025Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language ModelsarXiv 2024The Hidden Space of Transformer Language AdaptersarXiv 2024Counting Ability of Large Language Models and Impact of TokenizationarXiv 2024Out-of-Distribution Detection by Leveraging Between-Layer Transformation SmoothnessarXiv 2023Evaluation of HTR models without Ground Truth MaterialLREC 2022 6Bridging Information-Theoretic and Geometric Compression in Language ModelsarXiv 2023Dynamics of learning to integrate in linear recurrent neural networksarXiv 2025Facial Landmark Points Detection Using Knowledge Distillation-Based Neural NetworksarXiv 2021SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical SummarizationarXiv 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure PriorsarXiv 2024Boosting Few-shot Action Recognition with Graph-guided Hybrid MatchingICCV 2023 1Run-Off Election: Improved Provable Defense against Data Poisoning AttacksarXiv 2023Response: Emergent analogical reasoning in large language modelsarXiv 2023One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial SupportarXiv 2023Prune Once for All: Sparse Pre-Trained Language ModelsarXiv 2021Existence and Estimation of Critical Batch Size for Training Generative Adversarial Networks with Two Time-Scale Update RulearXiv 2022AfriHuBERT: A self-supervised speech representation model for African languagesarXiv 2024Classifying Dyads for Militarized Conflict AnalysisEMNLP 2021 11Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution RegressionarXiv 2022Model Transferability With Responsive Decision SubjectsarXiv 2021Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMsarXiv 2024Fully Authentic Visual Question Answering Dataset from Online CommunitiesarXiv 2023Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label ImbalancearXiv 2020Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time ScalingarXiv 2025CroCo: Cross-Lingual Contrastive Preference Tuning on Self-GenerationsarXiv 2026EgyBERT: A Large Language Model Pretrained on Egyptian Dialect CorporaarXiv 2024On Model Stability as a Function of Random Seedon-model-stability-as-a-function-of-randomSecure Domain Adaptation with Multiple Sourcessecure-domain-adaptation-with-multiple-1From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech DatasetsarXiv 2024Mitigating the Bias of Large Language Model EvaluationarXiv 2024Evaluating Multilingual Long-Context Models for Retrieval and ReasoningarXiv 2024Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMsarXiv 2025Margin Matching Preference Optimization: Enhanced Model Alignment with Granular FeedbackarXiv 2024