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.
Guiding Data Collection via Factored Scaling CurvesarXiv 2025S2 Chunking: A Hybrid Framework for Document Segmentation Through Integrated Spatial and Semantic AnalysisarXiv 2025A Feature-space Multimodal Data Augmentation Technique for Text-video RetrievalarXiv 2022Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection BiasarXiv 2023Discovering modular solutions that generalize compositionallyarXiv 2023Learning to Jump: Thinning and Thickening Latent Counts for Generative ModelingarXiv 2023Compositional Generalization for Multi-label Text Classification: A Data-Augmentation ApproacharXiv 2023Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMsarXiv 2024CYCLE: Learning to Self-Refine the Code GenerationarXiv 2024Fair yet Asymptotically Equal Collaborative LearningarXiv 2023Score Priors Guided Deep Variational Inference for Unsupervised Real-World Single Image DenoisingICCV 2023 1Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMsarXiv 2024Reverse Ordering Techniques for Attention-Based Channel PredictionarXiv 2023What If the Input is Expanded in OOD Detection?arXiv 2024How Does Critical Batch Size Scale in Pre-training?arXiv 2024MILDSum: A Novel Benchmark Dataset for Multilingual Summarization of Indian Legal Case JudgmentsarXiv 2023Cosmology with one galaxy?arXiv 2022Label-Driven Denoising Framework for Multi-Label Few-Shot Aspect
Category DetectionarXiv 2022ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat TemplatesarXiv 2024Composer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion ModelsarXiv 2023GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMsarXiv 2024Visual Explanations via Iterated Integrated Attributionsvisual-explanations-via-iterated-integratedStylometric Detection of AI-Generated Text in Twitter TimelinesarXiv 2023Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World KnowledgearXiv 2024Representation Deficiency in Masked Language ModelingarXiv 2023CrAM: A Compression-Aware MinimizerarXiv 2022SegReg: Segmenting OARs by Registering MR Images and CT AnnotationsarXiv 2023Causal Modeling of Twitter Activity During COVID-19arXiv 2020Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot FillingEMNLP (MRL) 2021 11Less Peaky and More Accurate CTC Forced Alignment by Label PriorsarXiv 2024Unsupervised Learning of Neurosymbolic Encodersunsupervised-learning-of-neurosymbolic-1Activation Space Interventions Can Be Transferred Between Large Language ModelsarXiv 2025The ROOTS Search Tool: Data Transparency for LLMsarXiv 2023Improving Query Representations for Dense Retrieval with Pseudo Relevance FeedbackarXiv 2021AttributionBench: How Hard is Automatic Attribution Evaluation?arXiv 2024Improved GUI Grounding via Iterative NarrowingarXiv 2024Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual PromptarXiv 2022MultiTACRED: A Multilingual Version of the TAC Relation Extraction DatasetarXiv 2023Cauchy-Schwarz Divergence Information Bottleneck for RegressionarXiv 2024Debate Helps Supervise Unreliable ExpertsarXiv 2023Prosodic Phrase Alignment for Machine DubbingarXiv 2019CausalLM is not optimal for in-context learningarXiv 2023Emergent Linear Representations in World Models of Self-Supervised Sequence ModelsarXiv 2023Method-Level Bug Severity Prediction using Source Code Metrics and LLMsarXiv 2023Mitigating and Evaluating Static Bias of Action Representations in the Background and the ForegroundICCV 2023 1The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language ModelsarXiv 2024Generator-Retriever-Generator Approach for Open-Domain Question AnsweringarXiv 2023Impact of Co-occurrence on Factual Knowledge of Large Language ModelsarXiv 2023Enhancing Personalized Dialogue Generation with Contrastive Latent Variables: Combining Sparse and Dense PersonaarXiv 2023COHO: Context-Sensitive City-Scale Hierarchical Urban Layout GenerationarXiv 2024Cartoon Explanations of Image Classifierscartoon-explanations-of-image-classifiers-1A Fine-tuning Dataset and Benchmark for Large Language Models for Protein UnderstandingarXiv 2024The Russian Drug Reaction Corpus and Neural Models for Drug Reactions and Effectiveness Detection in User ReviewsarXiv 2020Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!arXiv 2024Monolingual or Multilingual Instruction Tuning: Which Makes a Better AlpacaarXiv 2023LookAhead: Preventing DeFi Attacks via Unveiling Adversarial ContractsarXiv 2024RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World UsersarXiv 2025Selective Attention: Enhancing Transformer through Principled Context ControlarXiv 2024Hallucination Detection in LLMs Using Spectral Features of Attention MapsarXiv 2025Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic DimensionarXiv 2024Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse GradientsarXiv 2024MadDog: A Web-based System for Acronym Identification and DisambiguationEACL 2021 2Asking It All: Generating Contextualized Questions for any Semantic RoleEMNLP 2021 11Language Models are Surprisingly Fragile to Drug Names in Biomedical BenchmarksarXiv 2024AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM AnnotatorsarXiv 2024EPiC: Ensemble of Partial Point Clouds for Robust ClassificationICCV 2023 1VISITRON: Visual Semantics-Aligned Interactively Trained Object-NavigatorFindings (ACL) 2022 5Language Model Uncertainty Quantification with Attention ChainarXiv 2025Adaptive Testing of Computer Vision ModelsICCV 2023 1ETS: Efficient Tree Search for Inference-Time ScalingarXiv 2025Chasing Ghosts: Instruction Following as Bayesian State Trackingchasing-ghosts-instruction-following-as-1CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object CountingICCV 2025Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learningprobabilistic-mixture-of-experts-forLaSER: Internalizing Explicit Reasoning into Latent Space for Dense RetrievalarXiv 2026Training Language Models to Generate Text with Citations via Fine-grained RewardsarXiv 2024Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented DialogarXiv 2023API design for machine learning software: experiences from the scikit-learn projectarXiv 2013Quo Vadis, Anomaly Detection? LLMs and VLMs in the SpotlightarXiv 2024Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other AwarenessarXiv 2022Stealthy and Persistent Unalignment on Large Language Models via Backdoor InjectionsarXiv 2023Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated LearningarXiv 2023Directed Beam Search: Plug-and-Play Lexically Constrained Language GenerationarXiv 2020MDCure: A Scalable Pipeline for Multi-Document Instruction-FollowingarXiv 2024The Unreasonable Effectiveness of Large Language-Vision Models for Source-free Video Domain AdaptationICCV 2023 1Real-time quantum error correction beyond break-evenarXiv 2022Improved Training Technique for Latent Consistency ModelsarXiv 2025CitePrompt: Using Prompts to Identify Citation Intent in Scientific PapersarXiv 2023Predictive Multiplicity in ClassificationICML 2020 1Repulsive Latent Score Distillation for Solving Inverse ProblemsarXiv 2024A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?CVPR 2024 1Perceptual Score: What Data Modalities Does Your Model Perceive?NeurIPS 2021 12CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion ModelsarXiv 2025ReAGent: A Model-agnostic Feature Attribution Method for Generative Language ModelsarXiv 2024Debiasing Algorithm through Model AdaptationarXiv 2023Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation ProblemarXiv 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine TranslationarXiv 2024AlerTiger: Deep Learning for AI Model Health Monitoring at LinkedInarXiv 2023Language with Vision: a Study on Grounded Word and Sentence EmbeddingsarXiv 2022MonaLog: a Lightweight System for Natural Language Inference Based on MonotonicitySCiL 2020 1Measuring Social Biases in Grounded Vision and Language EmbeddingsNAACL 2021 4HR-INR: Continuous Space-Time Video Super-Resolution via Event CameraarXiv 2024What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM UsearXiv 2024VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological ImagesarXiv 2024Enhancing Automated Interpretability with Output-Centric Feature DescriptionsarXiv 2025StageInteractor: Query-based Object Detector with Cross-stage InteractionICCV 2023 1Make-An-Animation: Large-Scale Text-conditional 3D Human Motion GenerationICCV 2023 1Backdoor Attacks on Dense Retrieval via Public and Unintentional
TriggersarXiv 2024Biomedical SAM 2: Segment Anything in Biomedical Images and VideosarXiv 2024Generative modeling, design and analysis of spider silk protein
sequences for enhanced mechanical propertiesarXiv 2023Auditing Prompt Caching in Language Model APIsarXiv 2025Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localizationdual-mean-teacher-an-unbiased-semi-supervisedMitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided SamplingarXiv 2024Pre-training with Random Orthogonal Projection Image ModelingarXiv 2023CT-ADE: An Evaluation Benchmark for Adverse Drug Event Prediction from Clinical Trial ResultsarXiv 2024Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Datasetlarge-language-models-are-fixated-by-redOverlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capabilityCVPR 2023 1SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small ModelsarXiv 2024Facilitating large language model Russian adaptation with Learned Embedding PropagationarXiv 2024Domain Invariant Adversarial Learningdomain-invariant-adversarial-learning-1CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question AnsweringarXiv 2022BenthicNet: A global compilation of seafloor images for deep learning applicationsarXiv 2024Influencer Backdoor Attack on Semantic SegmentationarXiv 2023LIST: Learning Implicitly from Spatial Transformers for Single-View 3D ReconstructionICCV 2023 1ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market DomainarXiv 2023Nudging: Inference-time Alignment of LLMs via Guided DecodingarXiv 2024You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownershipNeurIPS 2021 12What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based AgentsarXiv 2024Attributing Image Generative Models using Latent FingerprintsarXiv 2023Neighbor-Aware Calibration of Segmentation Networks with Penalty-Based ConstraintsarXiv 2024Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuningarXiv 2024Masked Supervised Learning for Semantic SegmentationarXiv 2022Overcoming Language Disparity in Online Content Classification with Multimodal LearningarXiv 2022Effective pruning of web-scale datasets based on complexity of concept clustersarXiv 2024Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language ModelsarXiv 2023A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way ParallelismarXiv 2024Jailbreaking Multimodal Large Language Models via Shuffle InconsistencyICCV 2025FREDOM: Fairness Domain Adaptation Approach to Semantic Scene UnderstandingCVPR 2023 1Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal GroundingarXiv 2024Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task DesignarXiv 2023Deep Ensembles Work, But Are They Necessary?arXiv 2022Detecting Shortcuts in Medical Images -- A Case Study in Chest X-raysarXiv 2022Zero-Shot Detection of LLM-Generated Text using Token CohesivenessarXiv 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in ApplicationarXiv 2024BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language GenerationarXiv 2021Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time StepsarXiv 2023TutorialVQA: Question Answering Dataset for Tutorial Videostutorialvqa-question-answering-dataset-for-1Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in VideosICCV 2023 1Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change AnalysisarXiv 2023On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based MethodarXiv 2022Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained EncodersEMNLP 2021 11Symmetry-Aware Robot Design with Structured SubgroupsarXiv 2023Argument Mining Driven Analysis of Peer-ReviewsarXiv 2020Is this Dialogue Coherent? Learning from Dialogue Acts and EntitiesSIGDIAL (ACL) 2020 7The Numerical Stability of Hyperbolic Representation LearningarXiv 2022Quasi-Monte Carlo for 3D Sliced WassersteinarXiv 2023Sampler Design for Implicit Feedback Data by Noisy-label Robust LearningarXiv 2020ChatEL: Entity Linking with ChatbotsarXiv 2024PINTO: Faithful Language Reasoning Using Prompt-Generated RationalesarXiv 2022DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Modelsdsee-dually-sparsity-embedded-efficientWhat is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?arXiv 2023Tokenization Falling Short: On Subword Robustness in Large Language ModelsarXiv 2024Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?arXiv 2022Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object DetectionarXiv 2022Modal-specific Pseudo Query Generation for Video Corpus Moment RetrievalarXiv 2022COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationarXiv 2024Select and Summarize: Scene Saliency for Movie Script SummarizationarXiv 2024Estimating Conditional Mutual Information for Dynamic Feature SelectionarXiv 2023Augmented Behavioral Cloning from ObservationarXiv 2020Did the Neurons Read your Book? Document-level Membership Inference for Large Language ModelsarXiv 2023Negativity Spreads Faster: A Large-Scale Multilingual Twitter Analysis on the Role of Sentiment in Political CommunicationarXiv 2022Band-wise Hyperspectral Image Pansharpening using CNN Model PropagationarXiv 2023RU-AI: A Large Multimodal Dataset for Machine-Generated Content DetectionarXiv 2024Large Language Model for Verilog Generation with Code-Structure-Guided Reinforcement LearningarXiv 2024A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language ModelsarXiv 2024KazQAD: Kazakh Open-Domain Question Answering DatasetarXiv 2024On Anytime Learning at Macroscaleon-anytime-learning-at-macroscale-1Detecting and Characterizing Bots that Commit CodearXiv 2020When Is Multilinguality a Curse? Language Modeling for 250 High- and Low-Resource LanguagesarXiv 2023On Sampling with Approximate Transport MapsarXiv 2023ProjectTest: A Project-level LLM Unit Test Generation Benchmark and Impact of Error Fixing MechanismsarXiv 2025Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-JudgesarXiv 2024Can Large Language Models Generate High-quality Patent Claims?arXiv 2024PatchCT: Aligning Patch Set and Label Set with Conditional Transport for Multi-Label Image ClassificationICCV 2023 1Differentially Private Sharpness-Aware TrainingarXiv 2023Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte CarloarXiv 2023ViHateT5: Enhancing Hate Speech Detection in Vietnamese With A Unified Text-to-Text Transformer ModelarXiv 2024A Hybrid Quantum-Classical Approach based on the Hadamard Transform for the Convolutional LayerarXiv 2023Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-ExpertsarXiv 2022Inverse Image Frequency for Long-tailed Image RecognitionarXiv 2022Enhancing Abstractive Summarization of Scientific Papers Using Structure InformationarXiv 2025Benchmarking Language Model Creativity: A Case Study on Code GenerationarXiv 2024How susceptible are LLMs to Logical Fallacies?arXiv 2023A Domain-adaptive Pre-training Approach for Language Bias Detection in NewsarXiv 2022A Prompt-Engineered Large Language Model, Deep Learning Workflow for
Materials ClassificationarXiv 2024Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts ConversionarXiv 2023What are the Desired Characteristics of Calibration Sets? Identifying Correlates on Long Form Scientific SummarizationarXiv 2023Learning Multimodal VAEs through Mutual Supervisionlearning-multimodal-vaes-through-mutual-1Video-Language Critic: Transferable Reward Functions for Language-Conditioned RoboticsarXiv 2024Can Large Multimodal Models Uncover Deep Semantics Behind Images?arXiv 2024Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented GenerationarXiv 2025