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.
A Dataset for Greek Traditional and Folk Music: LyraarXiv 2022AQuA: A Benchmarking Tool for Label Quality Assessmentaqua-a-benchmarking-tool-for-label-qualityVision Relation Transformer for Unbiased Scene Graph GenerationICCV 2023 1Ensemble everything everywhere: Multi-scale aggregation for adversarial robustnessarXiv 2024Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object DetectionarXiv 2023OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye SemanticsarXiv 2022ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language GenerationarXiv 2023Won't Get Fooled Again: Answering Questions with False PremisesarXiv 2023A Dataset for N-ary Relation Extraction of Drug CombinationsNAACL 2022 7NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning ChallengearXiv 2022A Language Model's Guide Through Latent SpacearXiv 2024Exploring Conditional Multi-Modal Prompts for Zero-shot HOI DetectionarXiv 2024Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text RecognitionarXiv 2021Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement LearningEACL 2021 2Private and Reliable Neural Network InferencearXiv 2022SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data AugmentationarXiv 2024PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for RecommendationarXiv 2024Understanding Bias in Large-Scale Visual DatasetsarXiv 2024SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of AdaptersarXiv 2022DS6, Deformation-aware Semi-supervised Learning: Application to Small Vessel Segmentation with Noisy Training DataarXiv 2020FETA: Towards Specializing Foundation Models for Expert Task ApplicationsarXiv 2022Principled Training of Neural Networks with Direct Feedback AlignmentarXiv 2019Training Language Models to Explain Their Own ComputationsarXiv 2025Fight Back Against Jailbreaking via Prompt Adversarial TuningarXiv 2024VoxLingua107: a Dataset for Spoken Language RecognitionarXiv 2020Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language ModelsarXiv 2024Learning to Watermark LLM-generated Text via Reinforcement LearningarXiv 2024SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary
Learning for Closed-Loop Scenario GenerationarXiv 2024SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentimentsemaxis-a-lightweight-framework-to-1UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language ModelarXiv 2024The Cascade Transformer: an Application for Efficient Answer Sentence Selectionthe-cascade-transformer-an-application-for-1MPCHAT: Towards Multimodal Persona-Grounded ConversationarXiv 2023From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule DiscoveryarXiv 2023MINDE: Mutual Information Neural Diffusion EstimationarXiv 2023Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline DataarXiv 2023Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target DetectionICCV 2023 1Plancraft: an evaluation dataset for planning with LLM agentsarXiv 2024Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive LossarXiv 2022FastVID: Dynamic Density Pruning for Fast Video Large Language ModelsarXiv 2025MILU: A Multi-task Indic Language Understanding BenchmarkarXiv 2024The RealHumanEval: Evaluating Large Language Models' Abilities to Support ProgrammersarXiv 2024Self-Supervised GANs with Label AugmentationNeurIPS 2021 12Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context LearningarXiv 2023Conformal Prediction via Regression-as-ClassificationarXiv 2024General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite HistoryarXiv 2023Unlearnable Clusters: Towards Label-agnostic Unlearnable ExamplesCVPR 2023 1Towards Practical Plug-and-Play Diffusion ModelsCVPR 2023 1Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal InputsarXiv 2024RePO: Replay-Enhanced Policy OptimizationarXiv 2025AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web TextarXiv 2024Probing Across Time: What Does RoBERTa Know and When?Findings (EMNLP) 2021 11LLM-Detector: Improving AI-Generated Chinese Text Detection with Open-Source LLM Instruction TuningarXiv 2024Memory-aided Contrastive Consensus Learning for Co-salient Object DetectionarXiv 2023BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and MappingarXiv 2023Free-Editor: Zero-shot Text-driven 3D Scene EditingarXiv 2023ESRL: Efficient Sampling-based Reinforcement Learning for Sequence GenerationarXiv 2023STBench: Assessing the Ability of Large Language Models in Spatio-Temporal AnalysisarXiv 2024Computer Science Named Entity Recognition in the Open Research Knowledge GrapharXiv 2022PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image TranslationarXiv 2022Loki: Low-rank Keys for Efficient Sparse AttentionarXiv 2024FRAKE: Fusional Real-time Automatic Keyword ExtractionarXiv 2021LOVM: Language-Only Vision Model SelectionNeurIPS 2023 11C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender SystemarXiv 2022Multilingual and code-switching ASR challenges for low resource Indian languagesarXiv 2021ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoningimagescope-unifying-language-guided-imageMicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable ConvergencearXiv 2024Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsarXiv 2024Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM PersonalizationarXiv 2025Do VSR Models Generalize Beyond LRS3?arXiv 2023Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and BeyondarXiv 2024Multi-LexSum: Real-World Summaries of Civil Rights Lawsuits at Multiple GranularitiesarXiv 2022A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from DataarXiv 2023Structural Re-weighting Improves Graph Domain AdaptationarXiv 2023COPEN: Probing Conceptual Knowledge in Pre-trained Language ModelsarXiv 2022Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object DetectionarXiv 2023AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language ModelsarXiv 2024Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary GeometriesarXiv 2024Spinning Language Models: Risks of Propaganda-As-A-Service and CountermeasuresarXiv 2021Bridging the Gap between Model Explanations in Partially Annotated Multi-label ClassificationCVPR 2023 1CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language ModelsarXiv 2024Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-TuningNeurIPS 2021 12Roto-translated Local Coordinate Frames For Interacting Dynamical SystemsNeurIPS 2021 12Uncertainty is Fragile: Manipulating Uncertainty in Large Language ModelsarXiv 2024Attributable and Scalable Opinion SummarizationarXiv 2023Reflected Flow MatchingarXiv 2024VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style PriorsarXiv 2024Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual TransferarXiv 2022Spatial Mixture-of-ExpertsarXiv 2022Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and LanguagesACL 2022 5API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMsarXiv 2024PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain GeneralizationICCV 2023 1Wyckoff Transformer: Generation of Symmetric CrystalsarXiv 2025WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language ModelarXiv 2024Breaking the Data Barrier -- Building GUI Agents Through Task GeneralizationarXiv 2025On the Connection Between MPNN and Graph TransformerarXiv 2023ResNLS: An Improved Model for Stock Price ForecastingarXiv 2023Pruning by Explaining: A Novel Criterion for Deep Neural Network PruningarXiv 2019RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with AnomaliesarXiv 2024T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question AnsweringarXiv 2023CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual WorldsarXiv 2024Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned PolicyCVPR 2025 1PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task AdaptationarXiv 2024Data-to-text Generation with Variational Sequential PlanningarXiv 2022Adaptive Superpixel for Active Learning in Semantic SegmentationICCV 2023 1HyperionSolarNet: Solar Panel Detection from Aerial ImagesarXiv 2022From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data SynthesisarXiv 2024Behavior Contrastive Learning for Unsupervised Skill DiscoveryarXiv 2023Text2Chart31: Instruction Tuning for Chart Generation with Automatic FeedbackarXiv 2024Dynamic Sparse Training with Structured SparsityarXiv 2023Modeling Multi-Task Model Merging as Adaptive Projective Gradient DescentarXiv 2025Continual Task Allocation in Meta-Policy Network via Sparse PromptingarXiv 2023Corrective Machine UnlearningarXiv 2024Alias-Free Convnets: Fractional Shift Invariance via Polynomial ActivationsCVPR 2023 1Benchmarking Cognitive Biases in Large Language Models as EvaluatorsarXiv 2023Outlier-Efficient Hopfield Layers for Large Transformer-Based ModelsarXiv 2024Probabilistically Rewired Message-Passing Neural NetworksarXiv 2023Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted DataarXiv 2024HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyarXiv 2024GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative ModelsarXiv 2023KGym: A Platform and Dataset to Benchmark Large Language Models on Linux
Kernel Crash ResolutionarXiv 2024What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task LearningarXiv 2023FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic PlanningarXiv 2022PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video SegmentationarXiv 2023Image Understanding Makes for A Good Tokenizer for Image GenerationarXiv 2024MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerarXiv 2023Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionarXiv 2023Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad CreativearXiv 2019Domain Generalization via Rationale InvarianceICCV 2023 1Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric SummarizationACL 2022 5MIND Your Language: A Multilingual Dataset for Cross-lingual News RecommendationarXiv 2024Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language ModelsarXiv 2023From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake NewsarXiv 2024Depth Any Canopy: Leveraging Depth Foundation Models for Canopy Height EstimationarXiv 2024Multi-User Large Language Model AgentsarXiv 2026Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt TemplatesarXiv 2024GlotScript: A Resource and Tool for Low Resource Writing System IdentificationarXiv 2023Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-SamplingarXiv 2024Can Editing LLMs Inject Harm?arXiv 2024Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and CommunicationarXiv 2024SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing ImageryarXiv 2024ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT modelsarXiv 2023Zero-Shot Reinforcement Learning from Low Quality DataarXiv 2023Radio Map Estimation -- An Open Dataset with Directive Transmitter Antennas and Initial ExperimentsarXiv 2024Large-Scale QA-SRL Parsinglarge-scale-qa-srl-parsing-1The impact of internal variability on benchmarking deep learning climate emulatorsarXiv 2024MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific WorkflowsarXiv 2024Rethinking the Spatial Inconsistency in Classifier-Free Diffusion GuidanceCVPR 2024 1Fast and Accurate Factual Inconsistency Detection Over Long DocumentsarXiv 2023Exploiting Novel GPT-4 APIsarXiv 2023AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody InteractionsNeurIPS 2023 11Graphically Structured Diffusion ModelsarXiv 2022MATE: Masked Autoencoders are Online 3D Test-Time LearnersICCV 2023 1Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model CommunicationarXiv 2023LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic SegmentationCVPR 2025 1A Simple and Scalable Representation for Graph GenerationarXiv 2023Local Context-Aware Active Domain AdaptationICCV 2023 1Node-weighted Graph Convolutional Network for Depression Detection in Transcribed Clinical InterviewsarXiv 2023Evading Black-box Classifiers Without Breaking EggsarXiv 2023Adaptive Self-training Framework for Fine-grained Scene Graph GenerationarXiv 2024Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought ReasoningarXiv 2024Are More Layers Beneficial to Graph Transformers?arXiv 2023On Data Fabrication in Collaborative Vehicular Perception: Attacks and CountermeasuresarXiv 2023GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in TransformersNAACL 2022 7Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical ImagingarXiv 2023Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language ModelsarXiv 2023AutoVP: An Automated Visual Prompting Framework and BenchmarkarXiv 2023Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality AssessmentarXiv 2024Deep Latent State Space Models for Time-Series GenerationarXiv 2022SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language ModelsarXiv 2024GenUP: Generative User Profilers as In-Context Learners for Next POI Recommender SystemsarXiv 2024ConditionalQA: A Complex Reading Comprehension Dataset with Conditional AnswersACL 2022 5Zero-shot Triplet Extraction by Template InfillingarXiv 2022Translating Natural Language to Planning Goals with Large-Language ModelsarXiv 2023CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Modelcbow-is-not-all-you-need-combining-cbow-with-1Watermarking Makes Language Models RadioactivearXiv 2024InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language ModelsarXiv 2024Textured-GS: Gaussian Splatting with Spatially Defined Color and OpacityarXiv 2024Taming Overconfidence in LLMs: Reward Calibration in RLHFarXiv 2024FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI MethodsICCV 2023 1Security Attacks on LLM-based Code Completion ToolsarXiv 2024StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem SolvingarXiv 2023EmTract: Extracting Emotions from Social MediaarXiv 2021ActMAD: Activation Matching to Align Distributions for Test-Time-TrainingCVPR 2023 1SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perceptionsignet-semantic-instance-aided-unsupervised-1VeLoRA: Memory Efficient Training using Rank-1 Sub-Token ProjectionsarXiv 2024Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-AnalysisCVPR 2025 1Spatiality-guided Transformer for 3D Dense Captioning on Point CloudsarXiv 2022What do neural networks learn in image classification? A frequency shortcut perspectiveICCV 2023 1Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from EventsICCV 2023 1ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred ImagesICCV 2023 1PartDistill: 3D Shape Part Segmentation by Vision-Language Model DistillationCVPR 2024 1Towards Neural Scaling Laws for Time Series Foundation ModelsarXiv 2024Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representationslearning-efficient-coding-of-natural-imagesSlovakBERT: Slovak Masked Language ModelarXiv 2021The AI Cosmologist I: An Agentic System for Automated Data AnalysisarXiv 2025Not All Contexts Are Equal: Teaching LLMs Credibility-aware GenerationarXiv 2024The Conversation is the Command: Interacting with Real-World Autonomous
Robot Through Natural LanguagearXiv 2024You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Samplingyou-only-sample-almost-once-linear-cost-selfConvergent Graph Solversconvergent-graph-solvers-1Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and DatasetsarXiv 2020