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.
MSViT: Dynamic Mixed-Scale Tokenization for Vision TransformersarXiv 2023Parameter-Efficient Tuning with Special Token AdaptationarXiv 2022How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain SimulationarXiv 2025CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question AnsweringarXiv 2023MM-Claims: A Dataset for Multimodal Claim Detection in Social MediaFindings (NAACL) 2022 7Scientific and Creative Analogies in Pretrained Language ModelsarXiv 2022Adversarial Robustness through the Lens of Convolutional FiltersarXiv 2022Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language ModelsarXiv 2024CREST: Cross-modal Resonance through Evidential Deep Learning for Enhanced Zero-Shot LearningarXiv 2024Can Active Learning Preemptively Mitigate Fairness Issues?arXiv 2021Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion ModelsarXiv 2024Backdoor Contrastive Learning via Bi-level Trigger OptimizationarXiv 2024Optimizing NOTEARS Objectives via Topological SwapsarXiv 2023Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) ModelsarXiv 2024Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case ReformulationarXiv 2024When can transformers reason with abstract symbols?arXiv 2023LingMess: Linguistically Informed Multi Expert Scorers for Coreference ResolutionarXiv 2022Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate GradientsCVPR 2025 1Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine TranslationarXiv 2024HMC with Normalizing FlowsarXiv 2021A Data-Driven Measure of Relative Uncertainty for Misclassification DetectionarXiv 2023Does Writing with Language Models Reduce Content Diversity?arXiv 2023LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language ModelsarXiv 2023FVQ: A Large-Scale Dataset and A LMM-based Method for Face Video Quality AssessmentarXiv 2025World Models for Math Story ProblemsarXiv 2023TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot InteractionarXiv 2026LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low-Resource and Extinct LanguagesarXiv 2024DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented DialoguesarXiv 2024Total Nitrogen Estimation in Agricultural Soils via Aerial Multispectral Imaging and LIBSarXiv 2021Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced RelevancearXiv 2024SPRIG: Improving Large Language Model Performance by System Prompt OptimizationarXiv 2024ICICLE: Interpretable Class Incremental Continual LearningICCV 2023 1Implicit Motion-Compensated Network for Unsupervised Video Object SegmentationarXiv 2022Teaching Llama a New Language Through Cross-Lingual Knowledge TransferarXiv 2024SafePred: A Predictive Guardrail for Computer-Using Agents via World ModelsarXiv 2026CGBA: Curvature-aware Geometric Black-box AttackICCV 2023 1Tokenization counts: the impact of tokenization on arithmetic in frontier LLMsarXiv 2024DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker EmbeddingICCV 2023 1What is the Visual Cognition Gap between Humans and Multimodal LLMs?arXiv 2024Expository Text Generation: Imitate, Retrieve, ParaphrasearXiv 2023Vamos: Versatile Action Models for Video UnderstandingarXiv 2023Comparison of meta-learners for estimating multi-valued treatment heterogeneous effectsarXiv 2022On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine TranslationCOLING 2022 10BLESS: Benchmarking Large Language Models on Sentence SimplificationarXiv 2023Feedback-Driven Automated Whole Bug Report Reproduction for Android AppsarXiv 2024In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided SearcharXiv 2023Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion ModelingarXiv 2023Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?arXiv 2024This before That: Causal Precedence in the Biomedical Domainthis-before-that-causal-precedence-in-the-1Translation Artifacts in Cross-lingual Transfer LearningEMNLP 2020 11Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesissteered-diffusion-a-generalized-framework-forA Joint Model for Definition Extraction with Syntactic Connection and Semantic ConsistencyarXiv 2019Arrows of Time for Large Language ModelsarXiv 2024Foundation Models for Generalist Geospatial Artificial IntelligencearXiv 2023Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to AnalysisarXiv 2023Improving Fairness using Vision-Language Driven Image AugmentationarXiv 2023Beating Backdoor Attack at Its Own GameICCV 2023 1Contextualized Topic Coherence MetricsarXiv 2023AffectNet: A Database for Facial Expression, Valence, and Arousal
Computing in the WildarXiv 2017DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image DetectionarXiv 2022The Z-loss: a shift and scale invariant classification loss belonging to the Spherical FamilyarXiv 2016Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained ModelarXiv 2023AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application WitharXiv 2021Real-Time Vibration-Based Bearing Fault Diagnosis Under Time-Varying Speed ConditionsarXiv 2023Calc-X and Calcformers: Empowering Arithmetical Chain-of-Thought through Interaction with Symbolic SystemsarXiv 2023SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training DataarXiv 2022CREF: An LLM-based Conversational Software Repair Framework for
Programming TutorsarXiv 2024Maximum Independent Set: Self-Training through Dynamic Programmingmaximum-independent-set-self-training-throughVārta: A Large-Scale Headline-Generation Dataset for Indic LanguagesarXiv 2023TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential DynamicsarXiv 2025Truly Scale-Equivariant Deep Nets with Fourier Layerstruly-scale-equivariant-deep-nets-withLearning to Compose: Improving Object Centric Learning by Injecting CompositionalityarXiv 2024Unsupervised Document Expansion for Information Retrieval with Stochastic Text GenerationNAACL (sdp) 2021 6Inferring Functionality of Attention Heads from their ParametersarXiv 2024Comparing the latent space of generative modelsarXiv 2022Multi Resolution Analysis (MRA) for Approximate Self-AttentionarXiv 2022Learning Collective Variables with Synthetic Data Augmentation through Physics-Inspired Geodesic InterpolationarXiv 2024Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global WorkspacearXiv 2023Multi-modal Latent DiffusionarXiv 2023ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference OptimizationarXiv 2025RePBubLik: Reducing the Polarized Bubble Radius with Link InsertionsarXiv 2021MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from ObservationsarXiv 2023WaterMax: breaking the LLM watermark detectability-robustness-quality trade-offarXiv 2024Hierarchical Visual Primitive Experts for Compositional Zero-Shot LearningICCV 2023 1MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRAarXiv 2023From Word Segmentation to POS Tagging for Vietnamesefrom-word-segmentation-to-pos-tagging-for-2Data-Efficient Augmentation for Training Neural Networksdata-efficient-augmentation-for-trainingExploring Model Transferability through the Lens of Potential EnergyICCV 2023 1CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data GenerationarXiv 2023Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG SignalsarXiv 2023Feature Distribution Matching for Federated Domain GeneralizationarXiv 2022Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the WildarXiv 2024Task Difficulty Aware Parameter Allocation & Regularization for Lifelong LearningCVPR 2023 1Syntax-Aware On-the-Fly Code CompletionarXiv 2022TAPE: Assessing Few-shot Russian Language UnderstandingarXiv 2022Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound DetectionarXiv 2023Adversarial Robustness by Design through Analog Computing and Synthetic GradientsarXiv 2021StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical UnderstandingarXiv 2023The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR AngiographyarXiv 2023Understanding Impact of Human Feedback via Influence FunctionsarXiv 2025VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction ModelsarXiv 2025CRISP: Curriculum based Sequential Neural Decoders for Polar Code FamilyarXiv 2022Automatic Personalized Impression Generation for PET Reports Using Large Language ModelsarXiv 2023ColorMAE: Exploring data-independent masking strategies in Masked AutoEncodersarXiv 2024Multi-grained Temporal Prototype Learning for Few-shot Video Object SegmentationICCV 2023 1On the Initialization of Graph Neural NetworksarXiv 2023Stepwise Alignment for Constrained Language Model Policy OptimizationarXiv 2024NormAd: A Framework for Measuring the Cultural Adaptability of Large Language ModelsarXiv 2024Self-Constructed Context Decompilation with Fined-grained Alignment EnhancementarXiv 2024On-device Online Learning and Semantic Management of TinyML SystemsarXiv 2024Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative ReasoningarXiv 2024UltraEdit: Instruction-based Fine-Grained Image Editing at ScalearXiv 2024Instruct-SkillMix: A Powerful Pipeline for LLM Instruction TuningarXiv 2024How Far Can We Extract Diverse Perspectives from Large Language Models?arXiv 2023Towards Answering Climate Questionnaires from Unstructured Climate ReportsarXiv 2023Normalizing Flows for Interventional Density EstimationarXiv 2022PANTHER: Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learningarXiv 2020Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal LearningarXiv 2024Knowledge Hypergraph Embedding Meets Relational AlgebraarXiv 2021LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object IntegrationarXiv 2025ViGoR: Improving Visual Grounding of Large Vision Language Models with Fine-Grained Reward ModelingarXiv 2024On the Challenges of Using Black-Box APIs for Toxicity Evaluation in ResearcharXiv 2023Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based GamesEMNLP 2020 11LLMPC: Large Language Model Predictive ControlarXiv 2025Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy PreservationarXiv 2020Overcome the Fear Of Missing Out: Active Sensing UAV Scanning for Precision AgriculturearXiv 2023Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language UsearXiv 2024MILL: Mutual Verification with Large Language Models for Zero-Shot Query ExpansionarXiv 2023SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models
for Multi-Label Chest X-Ray ClassificationarXiv 2023Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation PatchingarXiv 2023A distributed, plug-n-play algorithm for multi-robot applications with a priori non-computable objective functionsarXiv 2021In-Context Learning through the Bayesian PrismarXiv 2023Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility StudyarXiv 2021A Dataset and Benchmark for Hospital Course Summarization with Adapted Large Language ModelsarXiv 2024Transformers as Algorithms: Generalization and Stability in In-context LearningarXiv 2023JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language ModelsarXiv 2025Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modelingconsidering-likelihood-in-nlp-classification-1Semi-Markov Offline Reinforcement Learning for HealthcarearXiv 2022Vote'n'Rank: Revision of Benchmarking with Social Choice TheoryarXiv 2022SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer LearningarXiv 2024Are You Getting What You Pay For? Auditing Model Substitution in LLM APIsarXiv 2025Deep Learning Based Joint Beamforming Design in IRS-Assisted Secure
CommunicationsarXiv 2023Beyond Classification: Definition and Density-based Estimation of Calibration in Object DetectionarXiv 2023NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and ViolationarXiv 2023In-Context Example Selection via Similarity Search Improves Low-Resource Machine TranslationarXiv 2024Do Language Models Know When They're Hallucinating References?arXiv 2023Byte-Level Grammatical Error Correction Using Synthetic and Curated CorporaarXiv 2023Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarianbeyond-english-only-reading-comprehension-1ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in
TDNN Based Speaker VerificationarXiv 2020Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible CorporaarXiv 2024Event-based Temporally Dense Optical Flow Estimation with Sequential Learningevent-based-temporally-dense-optical-flow-1Automated distribution of quantum circuits via hypergraph partitioningarXiv 2018Iterative Forward Tuning Boosts In-Context Learning in Language ModelsarXiv 2023Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTSarXiv 2024Generating Private Synthetic Data with Genetic AlgorithmsarXiv 2023Model-Aware Contrastive Learning: Towards Escaping the DilemmasarXiv 2022BIOSCAN-5M: A Multimodal Dataset for Insect BiodiversityarXiv 2024How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?arXiv 2024Transferable Persona-Grounded Dialogues via Grounded Minimal EditsEMNLP 2021 11Incremental Randomized Smoothing CertificationarXiv 2023DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based AgentarXiv 2025Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt TuningNeurIPS 2021 12UDALM: Unsupervised Domain Adaptation through Language ModelingNAACL 2021 4Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive DecodingarXiv 2024Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning AbilityarXiv 2023Fuse to Forget: Bias Reduction and Selective Memorization through Model FusionarXiv 2023Zero-Resource Hallucination Prevention for Large Language ModelsarXiv 2023TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human SkillsarXiv 2023Exploring Underexplored Limitations of Cross-Domain Text-to-SQL GeneralizationEMNLP 2021 11AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource LanguagesACL 2022 5Traffic Light Control with Reinforcement LearningarXiv 2023REFACTOR: Learning to Extract Theorems from Proofsrefactor-learning-to-extract-theorems-fromAuto-Sklearn 2.0: Hands-free AutoML via Meta-LearningarXiv 2020ThinkGuard: Deliberative Slow Thinking Leads to Cautious GuardrailsarXiv 2025bgGLUE: A Bulgarian General Language Understanding Evaluation BenchmarkarXiv 2023QASiNa: Religious Domain Question Answering using Sirah NabawiyaharXiv 2023Small Languages, Big Models: A Study of Continual Training on Languages of NorwayarXiv 2024A Deep Learning Framework for Verilog Autocompletion Towards Design and Verification AutomationarXiv 2023Machine Translation Meta Evaluation through Translation Accuracy Challenge SetsarXiv 2024The Benefits of Label-Description Training for Zero-Shot Text ClassificationarXiv 2023HybridFlow: A Flexible and Efficient RLHF FrameworkarXiv 2024Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised LearningarXiv 2024Don't Copy the Teacher: Data and Model Challenges in Embodied DialoguearXiv 2022Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale TranslationarXiv 2022P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic SegmentationarXiv 2023InterroLang: Exploring NLP Models and Datasets through Dialogue-based ExplanationsarXiv 2023One-Shot Safety Alignment for Large Language Models via Optimal DualizationarXiv 2024Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-TuningarXiv 2024Influence-guided Data Augmentation for Neural Tensor CompletionarXiv 2021Can sparse autoencoders be used to decompose and interpret steering vectors?arXiv 2024Predicting Knee Osteoarthritis Progression from Structural MRI using Deep LearningarXiv 2022LoRA Training in the NTK Regime has No Spurious Local MinimaarXiv 2024Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image ClassificationarXiv 2024Can LLMs Reason in the Wild with Programs?arXiv 2024Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?CVPR 2022 1FEDZIP: A Compression Framework for Communication-Efficient Federated LearningarXiv 2021Paying Attention to Multi-Word Expressions in Neural Machine TranslationMTSummit 2017 9Improving Dialog Systems for Negotiation with Personality ModelingACL 2021 5COMPS: Conceptual Minimal Pair Sentences for testing Robust Property Knowledge and its Inheritance in Pre-trained Language ModelsarXiv 2022DOS: Diverse Outlier Sampling for Out-of-Distribution DetectionarXiv 2023