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.
Ex3: Automatic Novel Writing by Extracting, Excelsior and ExpandingarXiv 2024Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language ModelsarXiv 2024DarwinLM: Evolutionary Structured Pruning of Large Language ModelsarXiv 2025DEAL: Disentangle and Localize Concept-level Explanations for VLMsarXiv 2024UVMap-ID: A Controllable and Personalized UV Map Generative ModelarXiv 2024Mastering Rate based Curriculum LearningarXiv 2020LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary SearcharXiv 2026BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language ModelsarXiv 2024VSTAR: Generative Temporal Nursing for Longer Dynamic Video SynthesisarXiv 2024CUDA: Convolution-based Unlearnable DatasetsCVPR 2023 1SigFormer: Signature Transformers for Deep HedgingarXiv 2023EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsarXiv 2024Improving Fake News Detection of Influential Domain via Domain- and Instance-Level TransferCOLING 2022 10Crosslingual Reasoning through Test-Time ScalingarXiv 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated LearningCVPR 2025 1UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked ModelingarXiv 2024Meta-Prompting for Automating Zero-shot Visual Recognition with LLMsarXiv 2024Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage RetrievalEMNLP 2021 11On Path to Multimodal Generalist: General-Level and General-BencharXiv 2025Physics-aware registration based auto-encoder for convection dominated PDEsarXiv 2020Editing Massive Concepts in Text-to-Image Diffusion ModelsarXiv 2024Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation VectorsarXiv 2020ANEA: Distant Supervision for Low-Resource Named Entity RecognitionarXiv 2021One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space ShrinkingCVPR 2021 1OntoZSL: Ontology-enhanced Zero-shot LearningarXiv 2021MediaSpeech: Multilanguage ASR Benchmark and DatasetarXiv 2021Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion ModelsarXiv 2023Certified Robust Neural Networks: Generalization and Corruption ResistancearXiv 2023ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient UpdatearXiv 2024Augmenting Document Representations for Dense Retrieval with Interpolation and PerturbationACL 2022 5Robustifying Token Attention for Vision TransformersICCV 2023 1Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time SeriesarXiv 2021KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text DetectionarXiv 2024Iteratively Prompt Pre-trained Language Models for Chain of ThoughtarXiv 2022PELA: Learning Parameter-Efficient Models with Low-Rank ApproximationCVPR 2024 1EgoNight: Towards Egocentric Vision Understanding at Night with a
Challenging BenchmarkarXiv 2025RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image CustomizationCVPR 2024 1Manifold Learning by Mixture Models of VAEs for Inverse ProblemsarXiv 2023GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data ExplorationarXiv 2023TarGEN: Targeted Data Generation with Large Language ModelsarXiv 2023Intention Analysis Makes LLMs A Good Jailbreak DefenderarXiv 2024Reconstructing Interacting Hands with Interaction Prior from Monocular ImagesICCV 2023 1CgT-GAN: CLIP-guided Text GAN for Image CaptioningarXiv 2023MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and LearningarXiv 2024Guitar Effects Recognition and Parameter Estimation with Convolutional Neural NetworksarXiv 2020Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory ForecastingICCV 2023 1Learning to Reason for Text Generation from Scientific TablesarXiv 2021When to Learn What: Model-Adaptive Data Augmentation CurriculumICCV 2023 1Paper Abstract Writing through Editing Mechanismpaper-abstract-writing-through-editing-1Few-shot Image Generation via Adaptation-Aware Kernel ModulationarXiv 2022JCoLA: Japanese Corpus of Linguistic AcceptabilityarXiv 2023Towards Stability of Autoregressive Neural OperatorsarXiv 2023Number Cookbook: Number Understanding of Language Models and How to Improve ItarXiv 2024ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable CompressionarXiv 2024NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API CallsarXiv 2024Fast LiDAR Data Generation with Rectified FlowsarXiv 2024The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and ModalitiesarXiv 2024ERASE: Error-Resilient Representation Learning on Graphs for Label Noise TolerancearXiv 2023A Frustratingly Simple Decoding Method for Neural Text GenerationarXiv 2023Toward Adaptive Reasoning in Large Language Models with Thought RollbackarXiv 2024CAT-Walk: Inductive Hypergraph Learning via Set WalksNeurIPS 2023 11FactAlign: Long-form Factuality Alignment of Large Language ModelsarXiv 2024It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbationsit-s-morphin-time-combating-linguistic-1Fine-grained Audio-Visual Joint Representations for Multimodal Large Language ModelsarXiv 2023Code Recommendation for Open Source Software DevelopersarXiv 2022Inverse Approximation Theory for Nonlinear Recurrent Neural NetworksarXiv 2023Neural Implicit Morphing of Face ImagesCVPR 2024 1RuBLiMP: Russian Benchmark of Linguistic Minimal PairsarXiv 2024CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language ModelsarXiv 2024Towards Understanding and Improving GFlowNet TrainingarXiv 2023How Do We Answer Complex Questions: Discourse Structure of Long-form AnswersACL 2022 5Open-Vocabulary Argument Role Prediction for Event ExtractionarXiv 2022Compositional Generalization in Multilingual Semantic Parsing over WikidataarXiv 2021One-Shot Imitation under Mismatched ExecutionarXiv 2024ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditionsarXiv 2021Unprocessing Seven Years of Algorithmic FairnessarXiv 2023OTTers: One-turn Topic Transitions for Open-Domain DialogueACL 2021 5ImageNet3D: Towards General-Purpose Object-Level 3D UnderstandingarXiv 2024Guarding Barlow Twins Against Overfitting with Mixed SamplesarXiv 2023Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare QueriesarXiv 2023On the Effectiveness of Compact Biomedical TransformersarXiv 2022LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language ModelsarXiv 2024CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual ExamplesarXiv 2024BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXamsarXiv 2023Multimodal Neural DatabasesarXiv 2023Generation of microbial colonies dataset with deep learning style transferarXiv 2021Differentiable Causal Discovery Under Latent InterventionsarXiv 2022Ionospheric activity prediction using convolutional recurrent neural networksarXiv 2018Diversified in-domain synthesis with efficient fine-tuning for few-shot classificationarXiv 2023ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language ModelsarXiv 2025Global-Local Tree Search in VLMs for 3D Indoor Scene GenerationCVPR 2025 1EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gatedense-to-sparse-gate-for-mixture-of-expertsOn the Posterior Distribution in Denoising: Application to Uncertainty QuantificationarXiv 2023Can Language Models Employ the Socratic Method? Experiments with Code DebuggingarXiv 2023Compositional 4D Dynamic Scenes Understanding with Physics Priors for
Video Question AnsweringarXiv 2024Exact Diffusion Inversion via Bi-directional Integration ApproximationarXiv 2023Towards Metamerism via Foveated Style Transfertowards-metamerism-via-foveated-style-1Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasksarXiv 2024Challenges in Automated Debiasing for Toxic Language DetectionEACL 2021 2GAP: A Graph-aware Language Model Framework for Knowledge Graph-to-Text GenerationCOLING 2022 10Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language ModelsCOLING 2022 10MoMo: Momentum Models for Adaptive Learning RatesarXiv 2023The Remarkable Robustness of LLMs: Stages of Inference?arXiv 2024Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard ContextsarXiv 2022Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-DistillationNeurIPS 2021 12MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African LanguagesarXiv 2023EffiVED:Efficient Video Editing via Text-instruction Diffusion ModelsarXiv 2024Personalized Federated Learning under Mixture of DistributionsarXiv 2023Efficient Process Reward Model Training via Active LearningarXiv 2025Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion ClassificationarXiv 2022CMP: Cooperative Motion Prediction with Multi-Agent CommunicationarXiv 2024Course-Correction: Safety Alignment Using Synthetic PreferencesarXiv 2024Human Feedback is not Gold StandardarXiv 2023A Closer Look at In-Context Learning under Distribution ShiftsarXiv 2023Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claimsarticle-reranking-by-memory-enhanced-keyMagicEraser: Erasing Any Objects via Semantics-Aware ControlarXiv 2024Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute ManipulationarXiv 2023Cyberbullying Detection with Fairness ConstraintsarXiv 2020Attentive Illumination Decomposition Model for Multi-Illuminant White BalancingCVPR 2024 1Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive LossarXiv 2024PRODIGy: a PROfile-based DIalogue Generation datasetarXiv 2023Improving Question Generation with Multi-level Content PlanningarXiv 2023Revisiting pre-trained remote sensing model benchmarks: resizing and normalization mattersarXiv 2023Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk DecodingarXiv 2022How good are Large Language Models on African Languages?arXiv 2023StackEval: Benchmarking LLMs in Coding AssistancearXiv 2024The Trickle-down Impact of Reward (In-)consistency on RLHFarXiv 2023Eliminating Position Bias of Language Models: A Mechanistic ApproacharXiv 2024Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognitionmultilingual-twitter-corpus-and-baselines-for-1Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-TuningarXiv 2024CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual GroundingarXiv 2023BatchEval: Towards Human-like Text EvaluationarXiv 2023GAMA: Generative Adversarial Multi-Object Scene AttacksarXiv 2022Correlated Proxies: A New Definition and Improved Mitigation for Reward HackingarXiv 2024Good Teachers Explain: Explanation-Enhanced Knowledge DistillationarXiv 2024Co-Salient Object Detection with Co-Representation PurificationarXiv 2023SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language ModelsarXiv 2024KMM: Key Frame Mask Mamba for Extended Motion GenerationarXiv 2024Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active LearningarXiv 2019A Data Source for Reasoning Embodied AgentsarXiv 2023Goal-Oriented Prompt Attack and Safety Evaluation for LLMsarXiv 2023Segmenting Text and Learning Their Rewards for Improved RLHF in Language ModelarXiv 2025Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEsarXiv 2023STDAN: Deformable Attention Network for Space-Time Video Super-ResolutionarXiv 2022Multi-Head Mixture-of-ExpertsarXiv 2024Large Language Models are Few-Shot Summarizers: Multi-Intent Comment
Generation via In-Context LearningarXiv 2023SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation ModelsarXiv 2025TUNIZI: a Tunisian Arabizi sentiment analysis DatasetarXiv 2020Revisiting the Minimalist Approach to Offline Reinforcement LearningNeurIPS 2023 11Learning the Solution Operator of Boundary Value Problems using Graph Neural NetworksarXiv 2022Can MLLMs Understand the Deep Implication Behind Chinese Images?arXiv 20244Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging ConditionsarXiv 2022Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and SegmentationICCV 2023 1A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation AnalysisarXiv 2023Towards Multi-modal Transformers in Federated LearningarXiv 2024Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model UnlearningICCV 2025Using a KG-Copy Network for Non-Goal Oriented DialoguesarXiv 2019Learning Inner-Group Relations on Point CloudsarXiv 2021Understanding Hessian Alignment for Domain GeneralizationICCV 2023 1Improving Semi-Supervised Semantic Segmentation with Dual-Level Siamese Structure NetworkarXiv 2023Minimizing FLOPs to Learn Efficient Sparse RepresentationsICLR 2020 1With a Little Help from your own Past: Prototypical Memory Networks for Image CaptioningICCV 2023 1SSumM: Sparse Summarization of Massive GraphsarXiv 2020Streaming keyword spotting on mobile devicesarXiv 2020QGEval: Benchmarking Multi-dimensional Evaluation for Question GenerationarXiv 2024Studying How to Efficiently and Effectively Guide Models with Explanationsstudying-how-to-efficiently-and-effectivelyEvaluation and Analysis of Hallucination in Large Vision-Language ModelsarXiv 2023OR-Bench: An Over-Refusal Benchmark for Large Language ModelsarXiv 2024Visual Analytics in Deep Learning: An Interrogative Survey for the Next FrontiersarXiv 2018OCTET: Object-aware Counterfactual ExplanationsCVPR 2023 1T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text ClassificationarXiv 2021PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud RegistrationICCV 2023 1A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference ResolutionNAACL 2021 4Learning to Revise References for Faithful SummarizationarXiv 2022Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement LearningarXiv 2022TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic TasksarXiv 2024VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language ModelsarXiv 2023On Penalty-based Bilevel Gradient Descent MethodarXiv 2023Eigen Attention: Attention in Low-Rank Space for KV Cache CompressionarXiv 2024Context-Aware Sparse Deep Coordination Graphscontext-aware-sparse-deep-coordination-graphs-1Transformer-based Image Generation from Scene GraphsarXiv 2023$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory ConsolidationarXiv 2025Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion ModelsarXiv 2024Probabilistic Concept Bottleneck ModelsarXiv 2023hmBERT: Historical Multilingual Language Models for Named Entity RecognitionarXiv 2022Out-of-Town Recommendation with Travel Intention ModelingarXiv 2021Source-Aware Training Enables Knowledge Attribution in Language ModelsarXiv 2024Multi-task Hierarchical Adversarial Inverse Reinforcement LearningarXiv 2023Beyond Single-Event Extraction: Towards Efficient Document-Level Multi-Event Argument ExtractionarXiv 2024Unveiling the Key Factors for Distilling Chain-of-Thought ReasoningarXiv 2025A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal ReasoningarXiv 2024Quantifying and Enhancing Multi-modal Robustness with Modality PreferencearXiv 2024Connecting Consistency Distillation to Score Distillation for Text-to-3D GenerationarXiv 2024MedConceptsQA: Open Source Medical Concepts QA BenchmarkarXiv 2024ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language ModelsarXiv 2023MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their UsabilityarXiv 2024Prototype-based Dataset ComparisonarXiv 2023ArabicaQA: A Comprehensive Dataset for Arabic Question AnsweringarXiv 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language ModelsarXiv 2024Whitening-based Contrastive Learning of Sentence EmbeddingsarXiv 2023