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.
Detecting Conversational Mental Manipulation with Intent-Aware PromptingarXiv 2024Little Giants: Synthesizing High-Quality Embedding Data at ScalearXiv 2024HeySQuAD: A Spoken Question Answering DatasetarXiv 2023Auto-Formula: Recommend Formulas in Spreadsheets using Contrastive Learning for Table RepresentationsarXiv 2024Knowledge Distillation of Russian Language Models with Reduction of VocabularyarXiv 2022Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole LanguagesarXiv 2024LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and QuantizationarXiv 2024HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter NotebooksFindings (EMNLP) 2021 11Temporal Supervised Contrastive Learning for Modeling Patient Risk ProgressionarXiv 2023Nonparametric Iterative Machine TeachingarXiv 2023Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-AnsweringarXiv 2023STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural VideosICCV 2023 1MDIA: A Benchmark for Multilingual Dialogue Generation in 46 LanguagesarXiv 2022ChatGPT MT: Competitive for High- (but not Low-) Resource LanguagesarXiv 2023Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion TechniquesarXiv 2024Gradient Weight-normalized Low-rank Projection for Efficient LLM TrainingarXiv 2024Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual InterventionarXiv 2024Spurious Correlations in Machine Learning: A SurveyarXiv 2024CVAD: A generic medical anomaly detector based on Cascade VAEarXiv 2021Benchmarking Large Language Models for Molecule Prediction TasksarXiv 2024Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and SynonymyACL 2021 5A Heat Diffusion Perspective on Geodesic Preserving Dimensionality ReductionNeurIPS 2023 11VASR: Visual Analogies of Situation RecognitionarXiv 2022Personalized Text Generation with Fine-Grained Linguistic ControlarXiv 2024Achieving Model Robustness through Discrete Adversarial TrainingEMNLP 2021 11EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language ModelsarXiv 2024From Uniform to Heterogeneous: Tailoring Policy Optimization to Every
Token's NaturearXiv 2025Evaluating Creative Short Story Generation in Humans and Large Language ModelsarXiv 2024Conveyor: Efficient Tool-aware LLM Serving with Tool Partial ExecutionarXiv 2024HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of ActionsCVPR 2023 1Hierarchical Indexing for Retrieval-Augmented Opinion SummarizationarXiv 2024On the Robustness of Editing Large Language ModelsarXiv 2024Self-Paced Context Evaluation for Contextual Reinforcement LearningarXiv 2021Rethinking VLM Representation for VLA InitializationarXiv 2026Improving Graph Generation by Restricting Graph BandwidtharXiv 2023Graph-based Virtual Sensing from Sparse and Partial Multivariate ObservationsarXiv 2024An Effective Meaningful Way to Evaluate Survival ModelsarXiv 2023Neural Context Flows for Meta-Learning of Dynamical SystemsarXiv 2024Causal Unsupervised Semantic SegmentationarXiv 2023Robust Collaborative Learning with Linear Gradient OverheadarXiv 2022How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text DetectionarXiv 2023PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine TranslationEACL 2021 2Understanding Retrieval Robustness for Retrieval-Augmented Image CaptioningarXiv 2024Dropout is NOT All You Need to Prevent Gradient LeakagearXiv 2022Optimizing Retrieval-augmented Reader Models via Token EliminationarXiv 2023Can Pre-Trained Text-to-Image Models Generate Visual Goals for
Reinforcement Learning?arXiv 2023Beyond In-Domain Scenarios: Robust Density-Aware CalibrationarXiv 2023Diversity Enhanced Narrative Question Generation for StorybooksarXiv 2023Generalizing Neural Wave FunctionsarXiv 2023Rambler: Supporting Writing With Speech via LLM-Assisted Gist ManipulationarXiv 2024Fusing Models with Complementary ExpertisearXiv 2023Fine-Grained Prediction of Reading Comprehension from Eye MovementsarXiv 2024A Modern Perspective on Query Likelihood with Deep Generative Retrieval ModelsarXiv 2021RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuningarXiv 2024ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?arXiv 2024GlobeSumm: A Challenging Benchmark Towards Unifying Multi-lingual, Cross-lingual and Multi-document News SummarizationarXiv 2024ARPA: Armenian Paraphrase Detection Corpus and ModelsarXiv 2020TIDE: Time Derivative Diffusion for Deep Learning on GraphsarXiv 2022Hint-before-Solving Prompting: Guiding LLMs to Effectively Utilize Encoded KnowledgearXiv 2024Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit AccessarXiv 2024ADIMA: Abuse Detection In Multilingual AudioarXiv 2022Synthetic data, real errors: how (not) to publish and use synthetic dataarXiv 2023Geometric Algebra Attention Networks for Small Point Cloudsgeometric-algebra-attention-networks-for-1Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generationdon-t-take-it-literally-an-edit-invariant-1Representation Surgery: Theory and Practice of Affine SteeringarXiv 2024MemeGuard: An LLM and VLM-based Framework for Advancing Content Moderation via Meme InterventionarXiv 2024MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware ClassificationarXiv 2025ParaShoot: A Hebrew Question Answering DatasetEMNLP (MRQA) 2021 11Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluationsequence-tagging-with-contextual-and-non-1Learning Latent Plans from PlayarXiv 2019Confidence Calibration and Rationalization for LLMs via Multi-Agent DeliberationarXiv 2024Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language GenerationarXiv 2024Weight-Inherited Distillation for Task-Agnostic BERT CompressionarXiv 2023Same Author or Just Same Topic? Towards Content-Independent Style RepresentationsRepL4NLP (ACL) 2022 5Combining Static and Contextualised Multilingual EmbeddingsFindings (ACL) 2022 5Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive EstimationarXiv 2023Lifelong Inverse Reinforcement Learninglifelong-inverse-reinforcement-learningDiverse feature visualizations reveal invariances in early layers of deep neural networksdiverse-feature-visualizations-reveal-1Effective Distillation of Table-based Reasoning Ability from LLMsarXiv 2023DyVo: Dynamic Vocabularies for Learned Sparse Retrieval with EntitiesarXiv 2024Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit ReasoningarXiv 2024ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life VideosarXiv 2023IPO: Your Language Model is Secretly a Preference ClassifierarXiv 2025DYNAMICQA: Tracing Internal Knowledge Conflicts in Language ModelsarXiv 2024Experimental Estimation of Quantum State Properties from Classical
ShadowsarXiv 2020Explanation-based Finetuning Makes Models More Robust to Spurious CuesarXiv 2023FairProof : Confidential and Certifiable Fairness for Neural NetworksarXiv 2024StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain AdaptationICCV 2023 1HateBERT: Retraining BERT for Abusive Language Detection in EnglishACL (WOAH) 2021 8Semi-Supervised Knowledge-Grounded Pre-training for Task-Oriented Dialog SystemsarXiv 2022LogPrécis: Unleashing Language Models for Automated Malicious Log AnalysisarXiv 2023Differentiable Simulations for Enhanced Sampling of Rare EventsarXiv 2023RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented DialoguesarXiv 2024FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation FrameworkACL 2022 5Do LLMs Really Adapt to Domains? An Ontology Learning PerspectivearXiv 2024Token-level Correlation-guided Compression for Efficient Multimodal Document UnderstandingarXiv 2024Understanding the Performance and Estimating the Cost of LLM Fine-TuningarXiv 2024NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional GeneralizationarXiv 2024Multi-marginal Schrödinger Bridges with Iterative Reference RefinementarXiv 2024How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?how-much-knowledge-can-you-pack-into-a-loraTiDAL: Learning Training Dynamics for Active LearningICCV 2023 1Lost in Literalism: How Supervised Training Shapes Translationese in LLMsarXiv 2025Generative Sliced MMD Flows with Riesz KernelsarXiv 2023IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information RetrievalarXiv 2025Fully Decentralized, Scalable Gaussian Processes for Multi-Agent Federated LearningarXiv 2022Long-form evaluation of model editingarXiv 2024Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution ImagesarXiv 2024Generating Symbolic World Models via Test-time Scaling of Large Language ModelsarXiv 2025MOROCO: The Moldavian and Romanian Dialectal Corpusmoroco-the-moldavian-and-romanian-dialectal-1Graph2MDA: a multi-modal variational graph embedding model for predicting microbe-drug associationsarXiv 2021Tokenization Impacts Multilingual Language Modeling: Assessing Vocabulary Allocation and Overlap Across LanguagesarXiv 2023Global Counterfactual DirectionsarXiv 2024Hindsight Learning for MDPs with Exogenous InputsarXiv 2022Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT ClassificationarXiv 2021MSI: Maximize Support-Set Information for Few-Shot SegmentationICCV 2023 1Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence EmbeddingsEMNLP 2021 11Tailoring Self-Rationalizers with Multi-Reward DistillationarXiv 2023Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?arXiv 2023The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept UnderstandingarXiv 2025Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative ModelsarXiv 2023Block-Skim: Efficient Question Answering for TransformerarXiv 2021Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language ModelsarXiv 2024Route to Reason: Adaptive Routing for LLM and Reasoning Strategy SelectionarXiv 2025Characterizing, Detecting, and Predicting Online Ban EvasionarXiv 2022How Good is Zero-Shot MT Evaluation for Low Resource Indian Languages?arXiv 2024Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation MetricsarXiv 2022On Surgical Fine-tuning for Language EncodersarXiv 2023Stance Prediction for Russian: Data and AnalysisarXiv 2018Large-kernel Attention for Efficient and Robust Brain Lesion SegmentationarXiv 2023UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMsarXiv 2024Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative DatasetsarXiv 2024EFSA: Towards Event-Level Financial Sentiment AnalysisarXiv 2024A Comparative Study of Text Embedding Models for Semantic Text Similarity in Bug ReportsarXiv 2023Hardware Acceleration for Real-Time Wildfire Detection Onboard Drone NetworksarXiv 2024Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language ModelsarXiv 2024Dynamic Planning for LLM-based Graphical User Interface AutomationarXiv 2024Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge DistillationarXiv 2024Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language ModelsarXiv 2023MBIAS: Mitigating Bias in Large Language Models While Retaining ContextarXiv 2024MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed ClassifiersarXiv 2024Monotonic Location Attention for Length GeneralizationarXiv 2023CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence TranslationarXiv 2022OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-VisionICCV 2023 1Ranking Manipulation for Conversational Search EnginesarXiv 2024Star-Agents: Automatic Data Optimization with LLM Agents for Instruction TuningarXiv 2024Constrained Efficient Global Optimization of Expensive Black-box
FunctionsarXiv 2022Identifying and Mitigating Position Bias of Multi-image Vision-Language ModelsCVPR 2025 1Navigating Rifts in Human-LLM Grounding: Study and BenchmarkarXiv 2025RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation ExtractionarXiv 2023Self-Recognition in Language ModelsarXiv 2024A safety realignment framework via subspace-oriented model fusion for large language modelsarXiv 2024Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual RetrievalCOLING 2022 10Dated Data: Tracing Knowledge Cutoffs in Large Language ModelsarXiv 2024DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy ImagesarXiv 2024Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM InteractionsarXiv 2024CustomTTT: Motion and Appearance Customized Video Generation via Test-Time TrainingarXiv 2024Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and SmoothnessarXiv 2023FreSaDa: A French Satire Data Set for Cross-Domain Satire DetectionarXiv 2021Unified Triplet-Level Hallucination Evaluation for Large Vision-Language ModelsarXiv 2024A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt LearningarXiv 2023When Can Transformers Ground and Compose: Insights from Compositional Generalization BenchmarksarXiv 2022Evidence-backed Fact Checking using RAG and Few-Shot In-Context Learning with LLMsarXiv 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail KnowledgearXiv 2024Tweets Under the Rubble: Detection of Messages Calling for Help in Earthquake DisasterarXiv 2023Language Model Tokenizers Introduce Unfairness Between Languageslanguage-model-tokenizers-introduceAmbigNLG: Addressing Task Ambiguity in Instruction for NLGarXiv 2024Laser: Efficient Language-Guided Segmentation in Neural Radiance FieldsarXiv 2025A step towards understanding why classification helps regressionICCV 2023 1Kompetencer: Fine-grained Skill Classification in Danish Job Postings via Distant Supervision and Transfer LearningLREC 2022 6SwiLTra-Bench: The Swiss Legal Translation BenchmarkarXiv 2025AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and ResultsarXiv 2024Word Form Matters: LLMs' Semantic Reconstruction under TypoglycemiaarXiv 2025A Conversation is Worth A Thousand Recommendations: A Survey of Holistic Conversational Recommender SystemsarXiv 2023A Neural Framework for Generalized Causal Sensitivity AnalysisarXiv 2023Structure from Silence: Learning Scene Structure from Ambient SoundarXiv 2021Learning to Deceive in Multi-Agent Hidden Role GamesarXiv 2022TO-FLOW: Efficient Continuous Normalizing Flows with Temporal
Optimization adjoint with Moving SpeedarXiv 2022EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversationarXiv 2023Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?arXiv 2025Pruning Pre-trained Language Models Without Fine-TuningarXiv 2022Language Models as Inductive ReasonersarXiv 2022Sliced Wasserstein Estimation with Control VariatesarXiv 2023Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Modelwinner-take-all-column-row-sampling-forNADI 2021: The Second Nuanced Arabic Dialect Identification Shared TaskEACL (WANLP) 2021 4Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep HealtharXiv 2025Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node featuresarXiv 2021Talk like a Graph: Encoding Graphs for Large Language ModelsarXiv 2023ProgCo: Program Helps Self-Correction of Large Language ModelsarXiv 2025Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugsarXiv 2024A Strongly-Labelled Polyphonic Dataset of Urban Sounds with
Spatiotemporal ContextarXiv 2021Understanding and Improving Adversarial Collaborative Filtering for Robust RecommendationarXiv 2024DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image SynthesisarXiv 2023Overcoming a Theoretical Limitation of Self-AttentionACL 2022 5Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation ModelsarXiv 2025Memorization in Self-Supervised Learning Improves Downstream GeneralizationarXiv 2024Towards Foundational AI Models for Additive Manufacturing: Language Models for G-Code Debugging, Manipulation, and ComprehensionarXiv 2023Cross-Lingual Auto Evaluation for Assessing Multilingual LLMsarXiv 2024Fine-Tuned Machine Translation Metrics Struggle in Unseen DomainsarXiv 2024USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot InteractionsarXiv 2025TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous MemesSemEval (NAACL) 2022 7