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.
Balanced Data Sampling for Language Model Training with ClusteringarXiv 2024PolyIE: A Dataset of Information Extraction from Polymer Material Scientific LiteraturearXiv 2023A variational autoencoder for music generation controlled by tonal
tensionarXiv 2020Going Beyond Nouns With Vision & Language Models Using Synthetic DataICCV 2023 1Explainable Data-Driven Optimization: From Context to Decision and Back AgainarXiv 2023In-BoXBART: Get Instructions into Biomedical Multi-Task LearningFindings (NAACL) 2022 7ComFormer: Code Comment Generation via Transformer and Fusion
Method-based Hybrid Code RepresentationarXiv 2021Out-of-Domain Robustness via Targeted AugmentationsarXiv 2023Large Language Models as Biomedical Hypothesis Generators: A Comprehensive EvaluationarXiv 2024A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint GenerationarXiv 2024Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web DataACL 2022 5ImplicitAVE: An Open-Source Dataset and Multimodal LLMs Benchmark for Implicit Attribute Value ExtractionarXiv 2024End-to-End Learning of Flowchart Grounded Task-Oriented DialogsEMNLP 2021 11Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-DesignarXiv 2024Direct parsing to sentiment graphsACL 2022 5EffiLearner: Enhancing Efficiency of Generated Code via Self-OptimizationarXiv 2024Grounding Conversations with Improvised Dialoguesgrounding-conversations-with-improvised-1Prompted Contextual Vectors for Spear-Phishing DetectionarXiv 2024TAVGBench: Benchmarking Text to Audible-Video GenerationarXiv 2024NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical NotesarXiv 2023A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and EnglisharXiv 2021Zero-Shot and Few-Shot Video Question Answering with Multi-Modal PromptsarXiv 2023EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inferenceequate-a-benchmark-evaluation-framework-for-1AnoVox: A Benchmark for Multimodal Anomaly Detection in Autonomous DrivingarXiv 2024ChatGPT in the Age of Generative AI and Large Language Models: A Concise SurveyarXiv 2023An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text GenerationarXiv 2022PEEB: Part-based Image Classifiers with an Explainable and Editable Language BottleneckarXiv 2024Empirical Analysis of Model Selection for Heterogeneous Causal Effect EstimationarXiv 2022LLM-Supported Natural Language to Bash TranslationarXiv 2025Mitigating Gender Bias in Captioning SystemsarXiv 2020Don't Say No: Jailbreaking LLM by Suppressing RefusalarXiv 2024GIO: Gradient Information Optimization for Training Dataset SelectionarXiv 2023Byzantine-Robust Learning on Heterogeneous Data via Gradient SplittingarXiv 2023ConR: Contrastive Regularizer for Deep Imbalanced RegressionarXiv 2023LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual ContextsarXiv 2024Multi-property Steering of Large Language Models with Dynamic Activation CompositionarXiv 2024MetaMetrics: Calibrating Metrics For Generation Tasks Using Human PreferencesarXiv 2024MoreHopQA: More Than Multi-hop ReasoningarXiv 2024Label-Noise Robust Diffusion ModelsarXiv 2024Diverse Cotraining Makes Strong Semi-Supervised SegmentorICCV 2023 1AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge ReasoningarXiv 2024Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?arXiv 2022From heavy rain removal to detail restoration: A faster and better networkarXiv 2022LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image GenerationICCV 2025Learning the greatest common divisor: explaining transformer predictionsarXiv 2023Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud SegmentationarXiv 2024Learning Representations for New Sound Classes With Continual Self-Supervised LearningarXiv 2022Conditional Drums Generation using Compound Word RepresentationsarXiv 2022D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance AnnotationICCV 2023 1ReCorD: Reasoning and Correcting Diffusion for HOI GenerationarXiv 2024Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-ThoughtarXiv 2024Streaming Active Learning with Deep Neural NetworksarXiv 2023Working Memory Capacity of ChatGPT: An Empirical StudyarXiv 2023CDConv: A Benchmark for Contradiction Detection in Chinese ConversationsarXiv 2022Towards Hierarchical Rectified FlowarXiv 2025ChatGPT and Software Testing Education: Promises & PerilsarXiv 2023Step Differences in Instructional VideoCVPR 2024 1CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksarXiv 2023Token-Level Adaptation of LoRA Adapters for Downstream Task GeneralizationarXiv 2023Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language ModelsICCV 2025Image Shortcut Squeezing: Countering Perturbative Availability Poisons with CompressionarXiv 2023Photon-Starved Scene Inference using Single Photon CamerasarXiv 2021MINERS: Multilingual Language Models as Semantic RetrieversarXiv 2024Robust RGB-D Fusion for Saliency DetectionarXiv 2022Generating Summaries with Controllable Readability LevelsarXiv 2023NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated DataarXiv 2024Disentangled Generative Models for Robust Prediction of System Dynamicsdisentangled-generative-models-for-robustMoExtend: Tuning New Experts for Modality and Task ExtensionarXiv 2024Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom InstructionarXiv 2023TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion ModelsICCV 2025SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-AgentsarXiv 2024Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model PredictionsarXiv 2024Semi-Supervised Exaggeration Detection of Health Science Press ReleasesEMNLP 2021 11LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory UnitsarXiv 2024Transformed Distribution Matching for Missing Value ImputationarXiv 2023An Analysis and Mitigation of the Reversal CursearXiv 2023Masked Images Are Counterfactual Samples for Robust Fine-tuningCVPR 2023 1Simple and Scalable Nearest Neighbor Machine TranslationarXiv 2023Expansion and Shrinkage of Localization for Weakly-Supervised Semantic
SegmentationarXiv 2022Data-to-Text Generation with Iterative Text EditingINLG (ACL) 2020 12Dataset Distillation with Convexified Implicit GradientsarXiv 2023Semixup: In- and Out-of-Manifold Regularization for Deep Semi-Supervised Knee Osteoarthritis Severity Grading from Plain Radiographssemixup-in-and-out-of-manifold-regularizationCommunityLM: Probing Partisan Worldviews from Language ModelsCOLING 2022 10FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental RegularizationarXiv 2023NL2Plan: Robust LLM-Driven Planning from Minimal Text DescriptionsarXiv 2024NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language ModelsICCV 2025Transformers Meet ACT-R: Repeat-Aware and Sequential Listening Session RecommendationarXiv 2024Submodular Reinforcement LearningarXiv 2023When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM ReasoningarXiv 2025Comparative Evaluation of Pretrained Transfer Learning Models on Automatic Short Answer GradingarXiv 2020RoT: Enhancing Large Language Models with Reflection on Search TreesarXiv 2024CRAB: Assessing the Strength of Causal Relationships Between Real-world EventsarXiv 2023ALTER: Augmentation for Large-Table-Based ReasoningarXiv 2024Self-Guided Generation of Minority Samples Using Diffusion ModelsarXiv 2024Learning Visually Guided Latent Actions for Assistive TeleoperationarXiv 2021KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing DetectionarXiv 2024IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph
LearningarXiv 2024TransESC: Smoothing Emotional Support Conversation via Turn-Level State TransitionarXiv 2023Team Enigma at ArgMining-EMNLP 2021: Leveraging Pre-trained Language Models for Key Point MatchingEMNLP (ArgMining) 2021 11InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style AdviserarXiv 2023Smoothie: Label Free Language Model RoutingarXiv 2024RaDeR: Reasoning-aware Dense Retrieval ModelsarXiv 2025Training-free Neural Architecture Search for RNNs and TransformersarXiv 2023Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement LearningarXiv 2022FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem SolvingarXiv 2023Texture Learning Domain Randomization for Domain Generalized SegmentationICCV 2023 1Strike a Balance in Continual Panoptic SegmentationarXiv 2024Enhancing the Geometric Problem-Solving Ability of Multimodal LLMs via Symbolic-Neural IntegrationarXiv 2025Explaining How Transformers Use Context to Build PredictionsarXiv 2023Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous PromptsNAACL 2022 7Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object DetectionarXiv 2023Cascade Reward Sampling for Efficient Decoding-Time AlignmentarXiv 2024LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video ReconstructionICCV 2023 1ReAttention: Training-Free Infinite Context with Finite Attention ScopearXiv 2024Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical FindingsarXiv 2024AutoML: A Survey of the State-of-the-ArtarXiv 2019Context-aware Decoding Reduces Hallucination in Query-focused SummarizationarXiv 2023DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing ConstraintsarXiv 2024Towards Trustworthy Dataset DistillationarXiv 2023Deep Regression UnlearningarXiv 2022Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-SteparXiv 2023A Sea of Words: An In-Depth Analysis of Anchors for Text DataarXiv 2022Judge Anything: MLLM as a Judge Across Any ModalityarXiv 2025A machine learning route between band mapping and band structurearXiv 2020Latent Space Factorisation and Manipulation via Matrix Subspace ProjectionICML 2020 1Interpreting and Improving Diffusion Models from an Optimization PerspectivearXiv 2023Every Sample Matters: Leveraging Mixture-of-Experts and High-Quality Data for Efficient and Accurate Code LLMarXiv 2025Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual GroundingICCV 2023 1Co-Transport for Class-Incremental LearningarXiv 2021Measuring Progress in Fine-grained Vision-and-Language UnderstandingarXiv 2023Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic PuzzlesarXiv 2024DependEval: Benchmarking LLMs for Repository Dependency UnderstandingarXiv 2025COVID Detection and Severity Prediction with 3D-ConvNeXt and Custom PretrainingsarXiv 2022Confronting Reward Model Overoptimization with Constrained RLHFarXiv 2023D2Match: Leveraging Deep Learning and Degeneracy for Subgraph MatchingarXiv 2023Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT ScansarXiv 2021Synthetic Data Generation Framework, Dataset, and Efficient Deep Model for Pedestrian Intention PredictionarXiv 2024Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?arXiv 2024Tokenization Is More Than CompressionarXiv 2024Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong GeneralizationarXiv 2024OpenTab: Advancing Large Language Models as Open-domain Table ReasonersarXiv 2024DITTO: Demonstration Imitation by Trajectory TransformationarXiv 2024GUing: A Mobile GUI Search Engine using a Vision-Language ModelarXiv 2024VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video GenerationarXiv 2025BEAR: A Unified Framework for Evaluating Relational Knowledge in Causal and Masked Language ModelsarXiv 2024LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers ContentarXiv 2024Tackling Data Heterogeneity in Federated Learning via Loss DecompositionarXiv 2024Factored Verification: Detecting and Reducing Hallucination in Summaries of Academic PapersarXiv 2023Query-Policy Misalignment in Preference-Based Reinforcement LearningarXiv 2023An Empirical Study of Memorization in NLPACL 2022 5BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual CuesarXiv 2024Truncation Sampling as Language Model DesmoothingarXiv 2022The impact of Audio input representations on neural network based music
transcriptionarXiv 2020Neural Implicit Surface EvolutionICCV 2023 1On Expressivity and Trainability of Quadratic NetworksarXiv 2021Federated Reconnaissance: Efficient, Distributed, Class-Incremental LearningarXiv 2021UATVR: Uncertainty-Adaptive Text-Video RetrievalICCV 2023 1Hiding Visual Information via Obfuscating Adversarial PerturbationsICCV 2023 1Visual Data-Type Understanding does not emerge from Scaling Vision-Language ModelsarXiv 2023Ranking LLM-Generated Loop Invariants for Program VerificationarXiv 2023Quantifying Contamination in Evaluating Code Generation Capabilities of Language ModelsarXiv 2024Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative DecodingarXiv 2024SIESTA: Efficient Online Continual Learning with SleeparXiv 2023Easy-to-Hard Learning for Information ExtractionarXiv 2023Planning-Driven Programming: A Large Language Model Programming WorkflowarXiv 2024Introduction to Multi-Armed BanditsarXiv 2019Can Biases in ImageNet Models Explain Generalization?CVPR 2024 1Lightweight Diffusion Models for Resource-Constrained Semantic CommunicationarXiv 2024Curiosity-Driven Reinforcement Learning from Human FeedbackarXiv 2025Remote sensing framework for geological mapping via stacked autoencoders and clusteringarXiv 2024Internally Rewarded Reinforcement LearningarXiv 2023Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward HackingarXiv 2023Character-level Chinese-English Translation through ASCII Encodingcharacter-level-chinese-english-translation-1DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language ModelsarXiv 2023FastSpec: Scalable Generation and Detection of Spectre Gadgets Using Neural EmbeddingsarXiv 2020How Does Unlabeled Data Provably Help Out-of-Distribution Detection?arXiv 2024DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue DatasetarXiv 2022Coverage-based Example Selection for In-Context LearningarXiv 2023Nonparametric Generative Modeling with Conditional Sliced-Wasserstein FlowsarXiv 2023LiCoEval: Evaluating LLMs on License Compliance in Code GenerationarXiv 2024SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure InterpretationarXiv 2024PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningarXiv 2024Online Continual Learning Without the Storage ConstraintarXiv 2023Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage ClassificationarXiv 2024CABINET: Content Relevance based Noise Reduction for Table Question AnsweringarXiv 2024FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document UnderstandingarXiv 2025KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and KirundiCOLING 2020 8Source Code Clone Detection Using Unsupervised Similarity MeasuresarXiv 2024Efficient 3-D Near-Field MIMO-SAR Imaging for Irregular Scanning GeometriesarXiv 2023Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation RecognitionarXiv 2022FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop DataarXiv 2025Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language ModelsarXiv 2024OFVL-MS: Once for Visual Localization across Multiple Indoor ScenesICCV 2023 1PCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit BoardsarXiv 2024Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMsarXiv 2024RefEgo: Referring Expression Comprehension Dataset from First-Person Perception of Ego4DICCV 2023 1Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor AttacksarXiv 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step ReasoningarXiv 2024Towards Sustainable Learning: Coresets for Data-efficient Deep LearningarXiv 2023This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for PolisharXiv 2022