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.
Overcoming Generic Knowledge Loss with Selective Parameter UpdateCVPR 2024 1Domain Adaptive Few-Shot Open-Set LearningICCV 2023 1A Unified Encoder-Decoder Framework with Entity MemoryarXiv 2022Improving Conversational Recommendation Systems via Counterfactual Data SimulationarXiv 2023SPRING: Studying the Paper and Reasoning to Play GamesarXiv 2023LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wildarXiv 2024ÚFAL at MultiLexNorm 2021: Improving Multilingual Lexical Normalization by Fine-tuning ByT5WNUT (ACL) 2021 11A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language ModelsarXiv 2022Learning High-Quality and General-Purpose Phrase RepresentationsarXiv 2024Quantized Compressed Sensing with Score-based Generative ModelsarXiv 2022MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI AgentsarXiv 2025Multisize Dataset CondensationarXiv 2024DenoSent: A Denoising Objective for Self-Supervised Sentence Representation LearningarXiv 2024It's not Rocket Science : Interpreting Figurative Language in NarrativesarXiv 2021Cyclic-Bootstrap Labeling for Weakly Supervised Object DetectionICCV 2023 1Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic SegmentationICCV 2023 1On the Expressiveness and Length Generalization of Selective State-Space Models on Regular LanguagesarXiv 2024CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming SequencesarXiv 2022QuantumBind-RBFE: Accurate Relative Binding Free Energy Calculations Using Neural Network PotentialsarXiv 2025MetaGCD: Learning to Continually Learn in Generalized Category DiscoveryICCV 2023 1Calibrated Multiple-Output Quantile Regression with Representation LearningarXiv 2021BanglaParaphrase: A High-Quality Bangla Paraphrase DatasetarXiv 2022MEWL: Few-shot multimodal word learning with referential uncertaintyarXiv 2023Erasing Concepts from Text-to-Image Diffusion Models with Few-shot UnlearningarXiv 2024ReMasker: Imputing Tabular Data with Masked AutoencodingarXiv 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question AnsweringarXiv 2023ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image AnalysisICCV 2023 1On the Consistency of Video Large Language Models in Temporal ComprehensionCVPR 2025 1Unsupervised Representation Learning by InvariancePropagationarXiv 2020Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image TranslationarXiv 2024CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-ThoughtarXiv 2025SoccerNet-Echoes: A Soccer Game Audio Commentary DatasetarXiv 2024PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real ImagesarXiv 2023Direct Parameterization of Lipschitz-Bounded Deep NetworksarXiv 2023Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social MediaarXiv 2018Efficient and Scalable Graph Generation through Iterative Local ExpansionarXiv 2023Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation SystemsarXiv 2025Answer Matching Outperforms Multiple Choice for Language Model EvaluationarXiv 2025Anatomical Foundation Models for Brain MRIsarXiv 2024CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error ScenariosarXiv 2025Factify 2: A Multimodal Fake News and Satire News DatasetarXiv 2023DuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehensionduorc-towards-complex-language-understanding-1FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text ProcessingACL 2022 5Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive ReviewarXiv 2024MedSyn: LLM-based Synthetic Medical Text Generation FrameworkarXiv 2024LiveMind: Low-latency Large Language Models with Simultaneous InferencearXiv 2024DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point CloudsICCV 2023 1Aligning Text to Image in Diffusion Models is Easier Than You ThinkarXiv 2025Moral Foundations of Large Language ModelsarXiv 2023HyperFormer: Enhancing Entity and Relation Interaction for Hyper-Relational Knowledge Graph CompletionarXiv 2023Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR ImagesarXiv 2024The Mamba in the Llama: Distilling and Accelerating Hybrid ModelsarXiv 2024Analyzing Vision Transformers for Image Classification in Class Embedding Spaceanalyzing-vision-transformers-for-imageCheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural NetworkICCV 2023 1Modeling PROTAC Degradation Activity with Machine LearningarXiv 2024LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional AdaptationarXiv 2024Self-Supervised Point Cloud Completion via InpaintingarXiv 2021SEA-HELM: Southeast Asian Holistic Evaluation of Language ModelsarXiv 2025SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy LabelsICCV 2023 1Detecting Backdoor Samples in Contrastive Language Image PretrainingarXiv 2025Relevance Filtering for Embedding-based RetrievalarXiv 2024SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural NetworksarXiv 2023Latent Space Smoothing for Individually Fair Representationslatent-space-smoothing-for-individually-fairIPO: Interpretable Prompt Optimization for Vision-Language ModelsarXiv 2024DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational RecommendationEMNLP 2021 11From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video UnderstandingarXiv 2024Self-supervised Representation Learning From Random Data ProjectorsarXiv 2023Training A Small Emotional Vision Language Model for Visual Art ComprehensionarXiv 2024KazParC: Kazakh Parallel Corpus for Machine TranslationarXiv 2024Disentangled Multi-Fidelity Deep Bayesian Active LearningarXiv 2023A Named Entity Based Approach to Model RecipesarXiv 2020Scaling Up Membership Inference: When and How Attacks Succeed on Large Language ModelsarXiv 2024Certifiably Robust Image WatermarkarXiv 2024Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?arXiv 2025Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language ModelsarXiv 2024Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget RegimesarXiv 2020REAM: Merging Improves Pruning of Experts in LLMsarXiv 2026Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram IterationarXiv 2023NTIRE 2026 Challenge on Video Saliency Prediction: Methods and ResultsarXiv 2026Domain Adaptation with Adversarial Training and Graph Embeddingsdomain-adaptation-with-adversarial-training-1SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image GenerationarXiv 2026XMoE: Sparse Models with Fine-grained and Adaptive Expert SelectionarXiv 2024Confidence Regulation Neurons in Language ModelsarXiv 2024S3E: A Multi-Robot Multimodal Dataset for Collaborative SLAMarXiv 2022Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot LearningECCV 2020 8HiNER: A Large Hindi Named Entity Recognition DatasetLREC 2022 6A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and ApplicationsarXiv 2024MAPPO-PIS: A Multi-Agent Proximal Policy Optimization Method with Prior
Intent Sharing for CAVs' Cooperative Decision-MakingarXiv 2024Proper Laplacian Representation LearningarXiv 2023ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning ExamplesarXiv 2022Data Contamination Calibration for Black-box LLMsarXiv 2024To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasetsarXiv 2023Counting Guidance for High Fidelity Text-to-Image SynthesisarXiv 2023Image Enhancement for Remote Photoplethysmography in a Low-Light EnvironmentarXiv 2023SC2EGSet: StarCraft II Esport Replay and Game-state DatasetarXiv 2022BaDLAD: A Large Multi-Domain Bengali Document Layout Analysis DatasetarXiv 2023Contrastive Active InferenceNeurIPS 2021 12Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain PromptingICCV 2023 1RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid NetworkarXiv 2022Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image ReconstructionarXiv 2023TopViewRS: Vision-Language Models as Top-View Spatial ReasonersarXiv 2024Lyra: A Benchmark for Turducken-Style Code GenerationarXiv 2021Where's Waldo: Diffusion Features for Personalized Segmentation and RetrievalarXiv 2024Towards Reasoning in Large Language Models via Multi-Agent Peer Review CollaborationarXiv 2023MediViSTA: Medical Video Segmentation via Temporal Fusion SAM Adaptation for EchocardiographyarXiv 2023An Error-Guided Correction Model for Chinese Spelling Error CorrectionarXiv 2023Can Large Language Models Unlock Novel Scientific Research Ideas?arXiv 2024JaCappella Corpus: A Japanese a Cappella Vocal Ensemble CorpusarXiv 2022Non-myopic Generation of Language Models for Reasoning and PlanningarXiv 2024CDFSL-V: Cross-Domain Few-Shot Learning for VideosICCV 2023 1Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial ImagearXiv 2024Personalized Image Generation with Large Multimodal ModelsarXiv 2024Addressing cognitive bias in medical language modelsarXiv 2024A Neural PDE Solver with Temporal Stencil ModelingarXiv 2023ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural
LanguagearXiv 2023Psychologically-informed chain-of-thought prompts for metaphor understanding in large language modelsarXiv 2022CMTA: Cross-Modal Temporal Alignment for Event-guided Video DeblurringarXiv 2024Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated LearningarXiv 2023Collective Critics for Creative Story GenerationarXiv 2024Towards Large-Scale Interpretable Knowledge Graph Reasoning for Dialogue SystemsFindings (ACL) 2022 5ManiSkill2: A Unified Benchmark for Generalizable Manipulation SkillsarXiv 2023Parameter-Efficient Fine-Tuning of LLaMA for the Clinical DomainarXiv 2023Selective Fairness in Recommendation via PromptsarXiv 2022HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic WorkflowsarXiv 2024Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine TranslationFindings (EMNLP) 2021 11DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object DetectionarXiv 2024ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific WritingarXiv 2023HeadlineCause: A Dataset of News Headlines for Detecting CausalitiesLREC 2022 63D Weakly Supervised Semantic Segmentation with 2D Vision-Language
GuidancearXiv 2024Improving Neural Language Models by Segmenting, Attending, and Predicting the Futureimproving-neural-language-models-by-1W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question AnsweringarXiv 2024GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary GenerationarXiv 2023Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied AgentsICCV 2023 1Improving Token-Based World Models with Parallel Observation PredictionarXiv 2024Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media ForensicsarXiv 2024Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple InteractionsarXiv 2025ConPET: Continual Parameter-Efficient Tuning for Large Language ModelsarXiv 2023TempSAL -- Uncovering Temporal Information for Deep Saliency PredictionarXiv 2023CLoVe: Encoding Compositional Language in Contrastive Vision-Language ModelsarXiv 2024Online Adversarial Attacksonline-adversarial-attacks-1Blind Justice: Fairness with Encrypted Sensitive Attributesblind-justice-fairness-with-encrypted-1PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language ModelsarXiv 2024Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language ModelsarXiv 2023MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language ModelsarXiv 2023A Unified and General Framework for Continual LearningarXiv 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box IdentificationarXiv 2024AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncodersarXiv 2026Locating and Editing Factual Associations in MambaarXiv 2024DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor QueriesarXiv 2024Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame BenchmarkarXiv 2024Towards Calibrated Robust Fine-Tuning of Vision-Language ModelsarXiv 2023ITALIC: An Italian Intent Classification DatasetarXiv 2023Multi-View Causal Representation Learning with Partial ObservabilityarXiv 2023A Dataset for Statutory Reasoning in Tax Law Entailment and Question AnsweringarXiv 2020BEV-CV: Birds-Eye-View Transform for Cross-View Geo-LocalisationarXiv 2023LILA: Language-Informed Latent ActionsarXiv 2021Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaborationarXiv 2023Exploring the Promise and Limits of Real-Time Recurrent LearningarXiv 2023NorBench -- A Benchmark for Norwegian Language ModelsarXiv 2023DELIFT: Data Efficient Language model Instruction Fine TuningarXiv 2024Decoding Speculative DecodingarXiv 2024Zero-Shot Recommendation as Language ModelingarXiv 2021FIRE: Fact-checking with Iterative Retrieval and VerificationarXiv 2024DASH: Detection and Assessment of Systematic Hallucinations of VLMsICCV 2025When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation DataLNLS (ACL) 2022 5SAFE: Sensitivity-Aware Features for Out-of-Distribution Object DetectionICCV 2023 1Representation Bending for Large Language Model SafetyarXiv 2025GMML is All you NeedarXiv 2022Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributionsact-asymptotic-conditional-transportEnd-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021ACL (IWSLT) 2021 8Best Practices for 2-Body Pose ForecastingarXiv 2023PLUG: Leveraging Pivot Language in Cross-Lingual Instruction TuningarXiv 2023HyperTab: Hypernetwork Approach for Deep Learning on Small Tabular DatasetsarXiv 2023MiRAGeNews: Multimodal Realistic AI-Generated News DetectionarXiv 2024DirectQuote: A Dataset for Direct Quotation Extraction and Attribution in News ArticlesLREC 2022 6Accurate Retraining-free Pruning for Pretrained Encoder-based Language ModelsarXiv 2023ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style TransferarXiv 2023Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean ImagesarXiv 2021Directional Bias AmplificationarXiv 2021Design of Chain-of-Thought in Math Problem SolvingarXiv 2023Words or Vision: Do Vision-Language Models Have Blind Faith in Text?CVPR 2025 1ReMoDetect: Reward Models Recognize Aligned LLM's GenerationsarXiv 2024Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion ProcessesarXiv 2023MapQA: A Dataset for Question Answering on Choropleth MapsarXiv 2022Concrete Subspace Learning based Interference Elimination for Multi-task Model FusionarXiv 2023Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative DecodingarXiv 2025WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from ParagraphsarXiv 2022Evaluating ChatGPT as a Recommender System: A Rigorous ApproacharXiv 2023VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web TasksarXiv 2024Learning to Generate Task-Specific Adapters from Task DescriptionACL 2021 5Mechanistic Mode ConnectivityarXiv 2022SeisFusion: Constrained Diffusion Model with Input Guidance for 3D Seismic Data Interpolation and ReconstructionarXiv 2024Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech DatasetarXiv 2021MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive ScaleEMNLP 2020 11Scaling for Training Time and Post-hoc Out-of-distribution Detection EnhancementarXiv 2023Divide-or-Conquer? Which Part Should You Distill Your LLM?arXiv 2024Unveiling the Implicit Toxicity in Large Language ModelsarXiv 2023ACE: Anti-Editing Concept Erasure in Text-to-Image ModelsCVPR 2025 1AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data FiltersarXiv 2024MPIrigen: MPI Code Generation through Domain-Specific Language ModelsarXiv 2024