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.
Controllable Context Sensitivity and the Knob Behind ItarXiv 2024Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical ProblemsarXiv 20243D Vision and Language Pretraining with Large-Scale Synthetic DataarXiv 2024Improving Translation Faithfulness of Large Language Models via Augmenting InstructionsarXiv 2023Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta InformationarXiv 2021Let Me Choose: From Verbal Context to Font Selectionlet-me-choose-from-verbal-context-to-font-1PoSynDA: Multi-Hypothesis Pose Synthesis Domain Adaptation for Robust 3D Human Pose EstimationarXiv 2023Siamese Vision Transformers are Scalable Audio-visual LearnersarXiv 2024NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series PretrainingarXiv 2023Towards Realistic Ultrasound Fetal Brain Imaging SynthesisarXiv 2023Taxonomy-Structured Domain AdaptationarXiv 2023Rethinking Momentum Knowledge Distillation in Online Continual LearningarXiv 2023Passing the Brazilian OAB Exam: data preparation and some experimentsarXiv 2017LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-TuningarXiv 2023FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real UsersarXiv 2025Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear RepresentationsarXiv 2024Rebuilding ROME : Resolving Model Collapse during Sequential Model EditingarXiv 2024Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-DeploymentFindings (ACL) 2022 5A Unified Audio-Visual Learning Framework for Localization, Separation, and RecognitionarXiv 2023Exploiting Cultural Biases via Homoglyphs in Text-to-Image SynthesisarXiv 2022Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel DecodingarXiv 2024LEMON: Lossless model expansionarXiv 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference LettersarXiv 2023Universal Morphology Control via Contextual ModulationarXiv 2023ESPN: Memory-Efficient Multi-Vector Information RetrievalarXiv 2023Small Language Models Improve Giants by Rewriting Their OutputsarXiv 2023Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationarXiv 2023CodeQueries: A Dataset of Semantic Queries over CodearXiv 2022Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source LocalizationarXiv 2022ContraDoc: Understanding Self-Contradictions in Documents with Large Language ModelsarXiv 2023Corpus-Steered Query Expansion with Large Language ModelsarXiv 2024Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained LearningarXiv 2023xPQA: Cross-Lingual Product Question Answering across 12 LanguagesarXiv 2023AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-TuningarXiv 2024DEPTWEET: A Typology for Social Media Texts to Detect Depression SeveritiesarXiv 2022Ask Again, Then Fail: Large Language Models' Vacillations in JudgmentarXiv 2023Improving Fairness in Deepfake DetectionarXiv 2023Causal Proxy Models for Concept-Based Model ExplanationsarXiv 2022Nearest Neighbor Speculative Decoding for LLM Generation and AttributionarXiv 2024Are Human-generated Demonstrations Necessary for In-context Learning?arXiv 2023Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection ModelarXiv 2022Medical Dialogue Generation via Dual Flow ModelingarXiv 2023Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry NetworkarXiv 2024Privileged Information Distillation for Language ModelsarXiv 2026Realistic Evaluation of Model Merging for Compositional GeneralizationarXiv 2024XFMamba: Cross-Fusion Mamba for Multi-View Medical Image ClassificationarXiv 2025Understanding Figurative Meaning through Explainable Visual EntailmentarXiv 2024CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLarXiv 2023SEABO: A Simple Search-Based Method for Offline Imitation LearningarXiv 2024Language Models for Code Completion: A Practical EvaluationarXiv 2024Understanding Catastrophic Forgetting in Language Models via Implicit InferencearXiv 2023Unlearning Traces the Influential Training Data of Language ModelsarXiv 2024Critical Thinking for Language ModelsIWCS (ACL) 2021 6Towards Constituting Mathematical Structures for Learning to OptimizearXiv 2023Jump to Conclusions: Short-Cutting Transformers With Linear TransformationsarXiv 2023Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL DivergencearXiv 2024FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learningfedpara-low-rank-hadamard-product-forKnowledge Editing through Chain-of-ThoughtarXiv 2024VISEM-Tracking, a human spermatozoa tracking datasetarXiv 2022High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized OptimizationarXiv 2024In-Context Learning State Vector with Inner and Momentum OptimizationarXiv 2024SLING: Sino Linguistic Evaluation of Large Language ModelsarXiv 2022ODA: Observation-Driven Agent for integrating LLMs and Knowledge GraphsarXiv 2024Rigid Body Flows for Sampling Molecular Crystal StructuresarXiv 2023On Information-Theoretic Measures of Predictive UncertaintyarXiv 2024AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval AlignmentarXiv 2024MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction ExpertsarXiv 2023Generalized Few-Shot Point Cloud Segmentation Via Geometric WordsICCV 2023 1Tell me what you see: A zero-shot action recognition method based on natural language descriptionsarXiv 2021Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language ModelsarXiv 2024ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion ProcessarXiv 2023Traveling Waves Encode the Recent Past and Enhance Sequence LearningarXiv 2023ApproxDet: Content and Contention-Aware Approximate Object Detection for MobilesarXiv 2020Improving Simultaneous Machine Translation with Monolingual DataarXiv 2022Vanishing Gradients in Reinforcement Finetuning of Language ModelsarXiv 2023ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability AssessmentarXiv 2023Rationale-Enhanced Language Models are Better Continual Relation LearnersarXiv 2023Towards Discovery and Attribution of Open-world GAN Generated ImagesICCV 2021 10Optimizing Feature Set for Click-Through Rate PredictionarXiv 2023Rich Feature Construction for the Optimization-Generalization DilemmaarXiv 2022CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical ReasoningarXiv 2022FineD-Eval: Fine-grained Automatic Dialogue-Level EvaluationarXiv 2022CAVES: A Dataset to facilitate Explainable Classification and Summarization of Concerns towards COVID VaccinesarXiv 2022FRoundation: Are Foundation Models Ready for Face Recognition?arXiv 2024SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved InformationarXiv 2024Adapters for Enhanced Modeling of Multilingual Knowledge and TextarXiv 2022What Makes Good In-context Demonstrations for Code Intelligence Tasks
with LLMs?arXiv 2023Federated Causal Discovery from Heterogeneous DataarXiv 2024Topology-Informed Graph TransformerarXiv 2024Scaling Evaluation-time Compute with Reasoning Models as EvaluatorsarXiv 2025DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMsarXiv 2026SUG: Single-dataset Unified Generalization for 3D Point Cloud ClassificationarXiv 2023Loop Copilot: Conducting AI Ensembles for Music Generation and Iterative EditingarXiv 2023Towards Neuro-Symbolic Video UnderstandingarXiv 2024Training Unbiased Diffusion Models From Biased DatasetarXiv 2024Automatic Prediction of Discourse Connectivesautomatic-prediction-of-discourse-connectives-1TaCo: Enhancing Cross-Lingual Transfer for Low-Resource Languages in LLMs through Translation-Assisted Chain-of-Thought ProcessesarXiv 2023Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-TuningarXiv 2025WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation ModelsarXiv 2024GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. HumanarXiv 2025Sparse Model Soups: A Recipe for Improved Pruning via Model AveragingarXiv 2023Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Testsfeature-shift-detection-localizing-whichA Retrieve-and-Read Framework for Knowledge Graph Link PredictionarXiv 2022GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based SearcharXiv 2024MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE FrameworkarXiv 2024PromptMix: A Class Boundary Augmentation Method for Large Language Model DistillationarXiv 2023Language Models are Few-Shot ButlersEMNLP 2021 11Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label LearningarXiv 2024Coverage-Guided Tensor Compiler Fuzzing with Joint IR-Pass MutationarXiv 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject StudiesarXiv 2022A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question AnsweringarXiv 2023Towards Event-oriented Long Video UnderstandingarXiv 2024Masked Graph Autoencoder with Non-discrete BandwidthsarXiv 2024Video Object Segmentation in Panoptic Wild ScenesarXiv 2023Emotion-Aware Transformer Encoder for Empathetic Dialogue Generationemotion-aware-transformer-encoder-forPlanning Like Human: A Dual-process Framework for Dialogue PlanningarXiv 2024SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient ChannelsarXiv 2023BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree SearcharXiv 2024PeerQA: A Scientific Question Answering Dataset from Peer ReviewsarXiv 2025Improving reference mining in patents with BERTarXiv 2021To Generate or to Retrieve? On the Effectiveness of Artificial Contexts for Medical Open-Domain Question AnsweringarXiv 2024Column Type Annotation using ChatGPTcolumn-type-annotation-using-chatgpt-1Multiscale Score Matching for Out-of-Distribution Detectionmultiscale-score-matching-for-out-ofMapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical MapsarXiv 2024Distilling Out-of-Distribution Robustness from Vision-Language Foundation Modelsdistilling-out-of-distribution-robustnessLawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLMarXiv 2025Lemur: Integrating Large Language Models in Automated Program VerificationarXiv 2023Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equationsarXiv 2022Generalization on the Unseen, Logic Reasoning and Degree CurriculumarXiv 2023On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement LearningarXiv 2023Eliminating Feature Ambiguity for Few-Shot SegmentationarXiv 2024Roman Numeral Analysis with Graph Neural Networks: Onset-wise Predictions from Note-wise FeaturesarXiv 2023OpenFilter: A Framework to Democratize Research Access to Social Media AR FiltersarXiv 2022Greed is All You Need: An Evaluation of Tokenizer Inference MethodsarXiv 2024High Perceptual Quality Wireless Image Delivery with Denoising Diffusion ModelsarXiv 2023Discovering Spatio-Temporal Rationales for Video Question AnsweringICCV 2023 1Knowledge Restore and Transfer for Multi-label Class-Incremental LearningICCV 2023 1VoxSim: A perceptual voice similarity datasetarXiv 2024An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal ModelsarXiv 2024Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQLarXiv 2025Population Transformer: Learning Population-level Representations of Neural ActivityarXiv 2024Convolutional Recurrent Neural Networks for Music ClassificationarXiv 2016EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsarXiv 2021Green Screen Augmentation Enables Scene Generalisation in Robotic ManipulationarXiv 2024MADE-for-ASD: A Multi-Atlas Deep Ensemble Network for Diagnosing Autism Spectrum DisorderarXiv 2024This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical TextarXiv 2022Rethinking Multi-view Representation Learning via Distilled DisentanglingCVPR 2024 1MIRACLE: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute ControlarXiv 2023Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised LearningarXiv 2023Heterogeneous Forgetting Compensation for Class-Incremental LearningICCV 2023 1The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification TasksarXiv 2023Memory-Based Dual Gaussian Processes for Sequential LearningarXiv 2023Question Answering as Programming for Solving Time-Sensitive QuestionsarXiv 2023Can Forward Gradient Match Backpropagation?arXiv 2023Online Test-Time Adaptation of Spatial-Temporal Traffic Flow ForecastingarXiv 2024Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron AnalysisarXiv 2024DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume ReconstructionarXiv 2023FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle SolvingarXiv 2025A Thorough Examination of Decoding Methods in the Era of LLMsarXiv 2024Source-free Domain Adaptive Human Pose EstimationICCV 2023 1NLPositionality: Characterizing Design Biases of Datasets and ModelsarXiv 2023HerO at AVeriTeC: The Herd of Open Large Language Models for Verifying Real-World ClaimsarXiv 2024Point2SSM: Learning Morphological Variations of Anatomies from Point CloudarXiv 2023Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement LearningarXiv 2024DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingarXiv 2024Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive LearningarXiv 2024Sparse Probabilistic Circuits via Pruning and GrowingarXiv 2022Bi-directional Masks for Efficient N:M Sparse TrainingarXiv 2023Revisiting Neural Networks for Continual Learning: An Architectural PerspectivearXiv 2024Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter EffectCVPR 2021 1PreBit -- A multimodal model with Twitter FinBERT embeddings for extreme price movement prediction of BitcoinarXiv 2022Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?arXiv 2022Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category DiscoveryICCV 2023 1Transformers as Support Vector MachinesarXiv 2023Contrastive Instruction TuningarXiv 2024PSI: A Pedestrian Behavior Dataset for Socially Intelligent Autonomous CararXiv 2021When to Pre-Train Graph Neural Networks? From Data Generation Perspective!arXiv 2023Meta-Task Prompting Elicits Embeddings from Large Language ModelsarXiv 2024Teaching Language Models to Self-Improve through Interactive DemonstrationsarXiv 2023Deep Orthogonal Hypersphere Compression for Anomaly DetectionarXiv 2023Gemini Goes to Med School: Exploring the Capabilities of Multimodal Large Language Models on Medical Challenge Problems & HallucinationsarXiv 2024Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question AnsweringarXiv 2024Marten: Visual Question Answering with Mask Generation for Multi-modal Document UnderstandingCVPR 2025 1What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl CorpusarXiv 2021ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot FillerarXiv 2024Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningarXiv 2022Reconstructing Groups of People with Hypergraph Relational ReasoningICCV 2023 1Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask PredictionCVPR 2022 1One-Shot Federated Conformal PredictionarXiv 2023M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text DetectionarXiv 2024MA-RLHF: Reinforcement Learning from Human Feedback with Macro ActionsarXiv 2024Extracting Latent Steering Vectors from Pretrained Language ModelsFindings (ACL) 2022 5EPO: Hierarchical LLM Agents with Environment Preference OptimizationarXiv 2024Strip-MLP: Efficient Token Interaction for Vision MLPICCV 2023 1Hyper Evidential Deep Learning to Quantify Composite Classification UncertaintyarXiv 2024DebUnc: Improving Large Language Model Agent Communication With Uncertainty MetricsarXiv 2024Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from JailbreakingarXiv 2025Disentangled Ontology Embedding for Zero-shot LearningarXiv 2022Comparison of semi-supervised deep learning algorithms for audio classificationarXiv 2021Reasoning Through Execution: Unifying Process and Outcome Rewards for Code GenerationarXiv 2024