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.
Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee CrisisarXiv 2017KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social MediaSEMEVAL 2020Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley SoundarXiv 2024WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for
Authenticity VerificationarXiv 2024GPIoT: Tailoring Small Language Models for IoT Program Synthesis and DevelopmentarXiv 2025I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement ParadigmarXiv 2024Multi-Objective GFlowNetsarXiv 2022Audio Entailment: Assessing Deductive Reasoning for Audio UnderstandingarXiv 2024Sketch-in-Latents: Eliciting Unified Reasoning in MLLMsarXiv 2025Pruning Large Language Models with Semi-Structural Adaptive Sparse TrainingarXiv 2024AnyStar: Domain randomized universal star-convex 3D instance segmentationarXiv 2023Klexikon: A German Dataset for Joint Summarization and SimplificationLREC 2022 6Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic ModelsarXiv 2024Uncovering the Connections Between Adversarial Transferability and Knowledge TransferabilityarXiv 2020Open-vocabulary Semantic Segmentation with Frozen Vision-Language ModelsarXiv 2022Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt EngineeringarXiv 2023Preference Tuning For Toxicity Mitigation Generalizes Across LanguagesarXiv 2024HybridAugment++: Unified Frequency Spectra Perturbations for Model RobustnessICCV 2023 1Advanced computer vision for extracting georeferenced vehicle trajectories from drone imageryarXiv 2024K-QA: A Real-World Medical Q&A BenchmarkarXiv 2024BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language ModelsarXiv 2023Machine Unlearning for Image-to-Image Generative ModelsarXiv 2024Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci CurvaturearXiv 2022Advancing Mobile GUI Agents: A Verifier-Driven Approach to Practical DeploymentarXiv 2025Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a MeasurementarXiv 2025Articulated Object Manipulation using Online Axis Estimation with SAM2-Based TrackingarXiv 2024Balancing Diversity and Risk in LLM Sampling: How to Select Your Method
and Parameter for Open-Ended Text GenerationarXiv 2024CUTE: Measuring LLMs' Understanding of Their TokensarXiv 2024An Improved Evaluation Framework for Generative Adversarial NetworksarXiv 2018Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-PrefixesarXiv 2021From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial InjectionarXiv 2024Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog SystemsarXiv 2023TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular DataarXiv 2022Advancements in Arabic Grammatical Error Detection and Correction: An Empirical InvestigationarXiv 2023Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation LearningarXiv 2024An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented GenerationarXiv 2024Transport meets Variational Inference: Controlled Monte Carlo DiffusionsarXiv 2023RankE: End-to-End Post-Training for Discrete Text-to-Image Generation with Decoder Co-EvolutionarXiv 2026Multimodal Foundation Models for Material Property Prediction and DiscoveryarXiv 2023Rewriting the Code: A Simple Method for Large Language Model Augmented Code SearcharXiv 2024Imagination-Augmented Natural Language UnderstandingNAACL 2022 7Can LLMs' Tuning Methods Work in Medical Multimodal Domain?arXiv 2024Learning Spoken Language Representations with Neural Lattice Language Modelinglearning-spoken-language-representations-withUnified Language-driven Zero-shot Domain AdaptationCVPR 2024 1HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid NormalizationarXiv 2025SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language ModelsarXiv 2024Re-basin via implicit Sinkhorn differentiationCVPR 2023 1SportsHHI: A Dataset for Human-Human Interaction Detection in Sports VideosCVPR 2024 1NAS-LID: Efficient Neural Architecture Search with Local Intrinsic DimensionarXiv 2022Measurement Scheduling for Cooperative Localization in
Resource-Constrained ConditionsarXiv 2019SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report GenerationarXiv 2024PETGEN: Personalized Text Generation Attack on Deep Sequence Embedding-based Classification ModelsarXiv 2021Class-Incremental Grouping Network for Continual Audio-Visual LearningICCV 2023 1One Adapter for All Programming Languages? Adapter Tuning for Code Search and SummarizationarXiv 2023EfficientTDNN: Efficient Architecture Search for Speaker RecognitionarXiv 2021Harmony: Overcoming the Hurdles of GPU Memory Capacity to Train Massive DNN Models on Commodity ServersarXiv 2022Perceptual Quality Improvement in Videoconferencing using Keyframes-based GANarXiv 2023Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal ModelsarXiv 2025Normalized Attention Without Probability Cagenormalized-attention-without-probability-cage-1A Study on Incorporating Whisper for Robust Speech AssessmentarXiv 2023Toward a Visual Concept Vocabulary for GAN Latent Spacetoward-a-visual-concept-vocabulary-for-ganMuirBench: A Comprehensive Benchmark for Robust Multi-image UnderstandingarXiv 2024A Bayesian Approach To Analysing Training Data Attribution In Deep Learninga-bayesian-approach-to-analysing-trainingPATE: Proximity-Aware Time series anomaly EvaluationarXiv 2024ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learningforkmerge-mitigating-negative-transfer-inCBA: Improving Online Continual Learning via Continual Bias AdaptorICCV 2023 1Prediction of the Position of External Markers Using a Recurrent Neural Network Trained With Unbiased Online Recurrent Optimization for Safe Lung Cancer RadiotherapyarXiv 2021Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-TuningCOLING 2022 10LQER: Low-Rank Quantization Error Reconstruction for LLMsarXiv 2024K-HATERS: A Hate Speech Detection Corpus in Korean with Target-Specific RatingsarXiv 2023Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequencesarXiv 2024TWEAC: Transformer with Extendable QA Agent ClassifiersarXiv 2021Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language ModelsarXiv 2023On zero-shot recognition of generic objectson-zero-shot-recognition-of-generic-objects-1Differentiable Euler Characteristic Transforms for Shape ClassificationarXiv 2023M-FAC: Efficient Matrix-Free Approximations of Second-Order InformationNeurIPS 2021 12Neural Optimal Transport with General Cost FunctionalsarXiv 2022Beyond Homophily: Reconstructing Structure for Graph-agnostic ClusteringarXiv 2023ComFact: A Benchmark for Linking Contextual Commonsense KnowledgearXiv 2022A quantitative analysis of knowledge-learning preferences in large language models in molecular sciencearXiv 2024MS-DETR: Natural Language Video Localization with Sampling Moment-Moment InteractionarXiv 2023DiffuSETS: 12-lead ECG Generation Conditioned on Clinical Text Reports and Patient-Specific InformationarXiv 2025Safer-Instruct: Aligning Language Models with Automated Preference DataarXiv 2023Match, Compare, or Select? An Investigation of Large Language Models for Entity MatchingarXiv 2024Unbalancedness in Neural Monge Maps Improves Unpaired Domain TranslationarXiv 2023Identifying Machine-Paraphrased PlagiarismarXiv 2021Optimal Transport for Offline Imitation LearningarXiv 2023Leveraging Multimodal Features and Item-level User Feedback for Bundle ConstructionarXiv 2023VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMsarXiv 2024Quality-Aware Decoding for Neural Machine TranslationNAACL 2022 7Towards Few-Shot Adaptation of Foundation Models via Multitask FinetuningarXiv 2024How Large Language Models Encode Context Knowledge? A Layer-Wise Probing StudyarXiv 2024Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style TransfersICCV 2023 1Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex ReasoningarXiv 2023Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining ApproacharXiv 2023Design of Negative Sampling Strategies for Distantly Supervised Skill ExtractionarXiv 2022BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity AllocationarXiv 2024Generalized Teacher Forcing for Learning Chaotic DynamicsarXiv 2023HarsanyiNet: Computing Accurate Shapley Values in a Single Forward PropagationarXiv 2023Towards Attack-tolerant Federated Learning via Critical Parameter AnalysisICCV 2023 1UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES AlignmentarXiv 2024Context-NER : Contextual Phrase Generation at ScalearXiv 2021Towards Practical Preferential Bayesian Optimization with Skew Gaussian ProcessesarXiv 2023Learned Thresholds Token Merging and Pruning for Vision TransformersarXiv 2023ZeroMimic: Distilling Robotic Manipulation Skills from Web VideosarXiv 2025Unfamiliar Finetuning Examples Control How Language Models HallucinatearXiv 2024Instruct, Not Assist: LLM-based Multi-Turn Planning and Hierarchical Questioning for Socratic Code DebuggingarXiv 2024Graph Generative Model for Benchmarking Graph Neural NetworksarXiv 2022TSCMamba: Mamba Meets Multi-View Learning for Time Series ClassificationarXiv 2024Revisiting Transformer-based Models for Long Document ClassificationarXiv 2022Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for AutoencodersarXiv 2020Beyond Pixels: Enhancing LIME with Hierarchical Features and
Segmentation Foundation ModelsarXiv 2024AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document SummarizationarXiv 2020Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary TaskarXiv 2022DETA: Denoised Task Adaptation for Few-Shot LearningICCV 2023 1ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and FeedbackarXiv 2024WyckoffDiff -- A Generative Diffusion Model for Crystal SymmetryarXiv 2025LFQ: Online Learning of Per-flow Queuing Policies using Deep Reinforcement LearningarXiv 2020TESS: Text-to-Text Self-Conditioned Simplex DiffusionarXiv 2023DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialoguesdialograph-incorporating-interpretableMed-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised LearningarXiv 2024Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoningevaluating-and-improving-tool-augmentedOne Ontology to Rule Them All: Corner Case Scenarios for Autonomous
DrivingarXiv 2022Intra-Document Cascading: Learning to Select Passages for Neural Document RankingarXiv 2021Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?arXiv 2023Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothingarXiv 2024HYPO: Hyperspherical Out-of-Distribution GeneralizationarXiv 2024The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine LearningarXiv 2023MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question AnsweringCVPR 2023 1When should we prefer Decision Transformers for Offline Reinforcement Learning?arXiv 2023Interactive Text-to-SQL Generation via Editable Step-by-Step ExplanationsarXiv 2023Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and PruningarXiv 2023Extending Source Code Pre-Trained Language Models to Summarise Decompiled BinariesarXiv 2023On the Stability of Expressive Positional Encodings for GraphsarXiv 2023MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema ModelingarXiv 2023Neural Pipeline for Zero-Shot Data-to-Text GenerationACL 2022 5On the Multi-turn Instruction Following for Conversational Web AgentsarXiv 2024Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language ModelsCVPR 2025 1Mixing and Shifting: Exploiting Global and Local Dependencies in Vision MLPsarXiv 2022Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language ModelsarXiv 2023Trustworthiness in Retrieval-Augmented Generation Systems: A SurveyarXiv 2024CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive LearningarXiv 2022Towards Optimal Feature-Shaping Methods for Out-of-Distribution DetectionarXiv 2024Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse LanguagesarXiv 2025EffiCoder: Enhancing Code Generation in Large Language Models through Efficiency-Aware Fine-tuningarXiv 2024LEMMA: Learning from Errors for MatheMatical Advancement in LLMsarXiv 2025Can Unconfident LLM Annotations Be Used for Confident Conclusions?arXiv 2024Tutorial: Remote entanglement protocols for stationary qubits with
photonic interfacesarXiv 2023ProSec: Fortifying Code LLMs with Proactive Security AlignmentarXiv 2024Multiplication-Free Transformer Training via Piecewise Affine Operationsmultiplication-free-transformer-training-viaFair Normalizing Flowsfair-normalizing-flows-1Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept SpacearXiv 2024Learning by Sorting: Self-supervised Learning with Group Ordering ConstraintsICCV 2023 1Evaluating Spatial Understanding of Large Language ModelsarXiv 2023Out of the BLEU: how should we assess quality of the Code Generation models?arXiv 2022Lossless Compression with Probabilistic Circuitslossless-compression-with-probabilisticHyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge ManagementFindings (ACL) 2021 8Audio-Language Datasets of Scenes and Events: A SurveyarXiv 2024Isometric Representation Learning for Disentangled Latent Space of
Diffusion ModelsarXiv 2024Learning to Fuse Sentences with Transformers for SummarizationEMNLP 2020 11Extrapolative Controlled Sequence Generation via Iterative RefinementarXiv 2023On Distribution Shift in Learning-based Bug DetectorsarXiv 2022Robust Weight Perturbation for Adversarial Trainingrobust-weight-perturbation-for-adversarialImprovable Gap Balancing for Multi-Task LearningarXiv 2023Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model InferencearXiv 2024USAT: A Universal Speaker-Adaptive Text-to-Speech ApproacharXiv 2024SpartQA: : A Textual Question Answering Benchmark for Spatial ReasoningarXiv 2021Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMsarXiv 2023Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and BeyondarXiv 2025Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentationsplug-in-inversion-model-agnostic-inversionEnquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy ExpansionarXiv 2021Cross-lingual Argumentation Mining: Machine Translation (and a bit of Projection) is All You Need!cross-lingual-argumentation-mining-machine-1Best-First Beam SearcharXiv 2020AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric KnowledgearXiv 2024Artificial Generational Intelligence: Cultural Accumulation in Reinforcement LearningarXiv 2024CREPE: Open-Domain Question Answering with False PresuppositionsarXiv 2022RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference AlignmentarXiv 2024When Prompt-based Incremental Learning Does Not Meet Strong PretrainingICCV 2023 1Fast and Memory-Efficient Video Diffusion Using Streamlined InferencearXiv 2024Scaling FP8 training to trillion-token LLMsarXiv 2024Iterative Superquadric Recomposition of 3D Objects from Multiple ViewsICCV 2023 1An Efficient Membership Inference Attack for the Diffusion Model by Proximal InitializationarXiv 2023Improving LLM Safety Alignment with Dual-Objective OptimizationarXiv 2025Learning to Generate Unit Tests for Automated DebuggingarXiv 2025Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world CorruptionsICCV 2023 1Cooperative Self-training of Machine Reading ComprehensionNAACL 2022 7No More Manual Tests? Evaluating and Improving ChatGPT for Unit Test
GenerationarXiv 2023SentiPers: A Sentiment Analysis Corpus for PersianarXiv 2018On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement LearningarXiv 2022LoGU: Long-form Generation with Uncertainty ExpressionsarXiv 2024PromptBoosting: Black-Box Text Classification with Ten Forward PassesarXiv 2022Online GNN Evaluation Under Test-time Graph Distribution ShiftsarXiv 2024Investigating and Explaining the Frequency Bias in Image ClassificationarXiv 2022Does CLIP Know My Face?arXiv 2022The Benefits of Bad Advice: Autocontrastive Decoding across Model LayersarXiv 2023BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsarXiv 2021Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate PairsarXiv 2024MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal GenerationarXiv 2025Looking Inward: Language Models Can Learn About Themselves by IntrospectionarXiv 2024WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language ModelsarXiv 2024