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.
SPRING: Situated Conversation Agent Pretrained with Multimodal Questions from Incremental Layout GrapharXiv 2023Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalizationadversarial-vertex-mixup-toward-better-1Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM AssessmentarXiv 2024PDiscoNet: Semantically consistent part discovery for fine-grained recognitionICCV 2023 1FusionCount: Efficient Crowd Counting via Multiscale Feature FusionarXiv 2022SelecMix: Debiased Learning by Contradicting-pair SamplingarXiv 2022Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine BlocksarXiv 2020MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument AnnotationarXiv 2023Enhancing Visually-Rich Document Understanding via Layout Structure ModelingarXiv 2023Tangent Transformers for Composition, Privacy and RemovalarXiv 2023ORES: Open-vocabulary Responsible Visual SynthesisarXiv 2023Eve: Efficient Multimodal Vision Language Models with Elastic Visual ExpertsarXiv 2025Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question AnsweringarXiv 2024Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training StagesarXiv 2023Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024arXiv 2025HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard ModelsarXiv 2024Evaluating the Generation Capabilities of Large Chinese Language ModelsarXiv 2023Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question AnsweringarXiv 2024On Evaluating the Durability of Safeguards for Open-Weight LLMsarXiv 2024Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware RewardsarXiv 2024InstOptima: Evolutionary Multi-objective Instruction Optimization via Large Language Model-based Instruction OperatorsarXiv 2023Do LLMs "know" internally when they follow instructions?arXiv 2024Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMsarXiv 2025BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpusarXiv 2022SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMsarXiv 2024Concise Reasoning via Reinforcement LearningarXiv 2025VectorDefense: Vectorization as a Defense to Adversarial ExamplesarXiv 2018The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language ModelsarXiv 2024R-ACP: Real-Time Adaptive Collaborative Perception Leveraging Robust
Task-Oriented CommunicationsarXiv 2024Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language ModelsarXiv 2024LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-ExplanationsarXiv 2024Federated Conformal Predictors for Distributed Uncertainty QuantificationarXiv 2023Revealing the Barriers of Language Agents in PlanningarXiv 2024Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD GeneralizationarXiv 2024Bayesian active learning for optimization and uncertainty quantification in protein dockingarXiv 2019Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023arXiv 2023RMCBench: Benchmarking Large Language Models' Resistance to Malicious CodearXiv 2024Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text ClassificationarXiv 2024Protecting Language Generation Models via Invisible WatermarkingarXiv 2023RELIEF: Reinforcement Learning Empowered Graph Feature Prompt TuningarXiv 2024Towards Instance-adaptive Inference for Federated LearningICCV 2023 1Phishing URL Detection: A Network-based Approach Robust to EvasionarXiv 2022AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment GrapharXiv 2023Attention-driven GUI Grounding: Leveraging Pretrained Multimodal Large Language Models without Fine-TuningarXiv 2024Exploring Gradient-based Multi-directional Controls in GANsarXiv 2022A Neural Tangent Kernel Perspective of GANsarXiv 2021Clockwork Diffusion: Efficient Generation With Model-Step DistillationCVPR 2024 1Can Question Rewriting Help Conversational Question Answering?insights (ACL) 2022 5FiLM: Fill-in Language Models for Any-Order GenerationarXiv 2023Understanding quantum machine learning also requires rethinking generalizationarXiv 2023ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense RetrievalarXiv 2024Pre-trained Language Models for the Legal Domain: A Case Study on Indian LawarXiv 2022Label-Only Model Inversion Attacks via Knowledge Transferlabel-only-model-inversion-attacks-via-1Rasa: Building Expressive Speech Synthesis Systems for Indian Languages in Low-resource SettingsarXiv 2024ViLA: Efficient Video-Language Alignment for Video Question AnsweringarXiv 2023Graph Neural Networks with Learnable and Optimal Polynomial BasesarXiv 2023Zero-guidance Segmentation Using Zero Segment LabelsICCV 2023 1Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a
Bayesian GamearXiv 2023Newswire: A Large-Scale Structured Database of a Century of Historical NewsarXiv 2024The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT InteractionsarXiv 2023GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing AgentarXiv 2024Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language ModelarXiv 2022What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and EvaluationarXiv 2024Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMsarXiv 2025High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep LearningarXiv 2021From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-TuningarXiv 2025Symbol Preference Aware Generative Models for Recovering Variable Names from Stripped BinaryarXiv 2023LongAgent: Scaling Language Models to 128k Context through Multi-Agent CollaborationarXiv 2024Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few UtterancesNAACL 2022 7CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural RenderingarXiv 2023Pretrained Language Model Embryology: The Birth of ALBERTEMNLP 2020 11Interpreting Embedding Spaces by ConceptualizationarXiv 2022Do Input Gradients Highlight Discriminative Features?NeurIPS 2021 12Unlocking Slot Attention by Changing Optimal Transport CostsarXiv 2023ChroniclingAmericaQA: A Large-scale Question Answering Dataset based on Historical American Newspaper PagesarXiv 2024CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal ModelsarXiv 2024NELEC at SemEval-2019 Task 3: Think Twice Before Going Deepnelec-at-semeval-2019-task-3-think-twice-1Learning Neural PDE Solvers with Parameter-Guided Channel AttentionarXiv 2023What are the best systems? New perspectives on NLP BenchmarkingarXiv 2022Weighted-Reward Preference Optimization for Implicit Model FusionarXiv 2024A Probabilistic Framework for Lifelong Test-Time AdaptationCVPR 2023 1Revisiting non-English Text Simplification: A Unified Multilingual BenchmarkarXiv 2023CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code StructurearXiv 2022TimeSeriesExam: A time series understanding examarXiv 2024X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question AnsweringNAACL 2021 4VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language ModelsarXiv 2024Multimodal Pragmatic Jailbreak on Text-to-image ModelsarXiv 2024Enhancing High-order Interaction Awareness in LLM-based Recommender ModelarXiv 2024Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural NetworksarXiv 2023Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral EntropyarXiv 20234-bit Shampoo for Memory-Efficient Network TrainingarXiv 2024Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix FactorizationarXiv 2022SelectLLM: Can LLMs Select Important Instructions to Annotate?arXiv 2024Deep Reinforcement Learning for Conservation DecisionsarXiv 2021Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under AttacksarXiv 2024Med-MMHL: A Multi-Modal Dataset for Detecting Human- and LLM-Generated
Misinformation in the Medical DomainarXiv 2023Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference OptimizationarXiv 2024SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Modelssa-solver-stochastic-adams-solver-for-fastEntity Tracking in Language ModelsarXiv 2023WIT-UAS: A Wildland-fire Infrared Thermal Dataset to Detect Crew Assets From Aerial ViewsarXiv 2023Joint Shapley values: a measure of joint feature importancejoint-shapley-values-a-measure-of-joint-1Improving Fairness via Federated Learningimproving-fairness-via-federated-learningA Cognitive Writing Perspective for Constrained Long-Form Text GenerationarXiv 2025LazyGNN: Large-Scale Graph Neural Networks via Lazy PropagationarXiv 2023On the Complementarity between Pre-Training and Back-Translation for Neural Machine TranslationFindings (EMNLP) 2021 11T-Projection: High Quality Annotation Projection for Sequence Labeling TasksarXiv 2022Efficient On-device Training via Gradient FilteringCVPR 2023 1A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networksa-context-based-approach-for-dialogue-act-1Jumping through Local Minima: Quantization in the Loss Landscape of Vision TransformersICCV 2023 1Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ ParametersarXiv 2021Statler: State-Maintaining Language Models for Embodied ReasoningarXiv 2023A Simple Contrastive Learning Objective for Alleviating Neural Text DegenerationarXiv 2022CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese NetworkarXiv 2024Multi-Object Navigation with dynamically learned neural implicit representationsICCV 2023 1Frustratingly Easy Label Projection for Cross-lingual TransferarXiv 2022ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical ImagesarXiv 2024Learning correspondences of cardiac motion from images using biomechanics-informed modelingarXiv 2022FaMeSumm: Investigating and Improving Faithfulness of Medical SummarizationarXiv 2023GPT as Knowledge Worker: A Zero-Shot Evaluation of (AI)CPA CapabilitiesarXiv 2023Exploring the Landscape of Natural Language Processing ResearcharXiv 2023Resolving label uncertainty with implicit posterior modelsarXiv 2022Clustering-Aware Negative Sampling for Unsupervised Sentence RepresentationarXiv 2023Categorical Stochastic Processes and LikelihoodarXiv 2020EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casearXiv 2021Which Model Generated This Image? A Model-Agnostic Approach for Origin AttributionarXiv 2024LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation GenerationarXiv 2024CoLoR-Filter: Conditional Loss Reduction Filtering for Targeted Language Model Pre-trainingarXiv 2024UniSA: Unified Generative Framework for Sentiment Analysisunisa-unified-generative-framework-forEventRPG: Event Data Augmentation with Relevance Propagation GuidancearXiv 2024SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over TimearXiv 2024The Effect of Spectrogram Reconstruction on Automatic Music Transcription: An Alternative Approach to Improve Transcription AccuracyarXiv 2020THOUGHTSCULPT: Reasoning with Intermediate Revision and SearcharXiv 2024nach0: Multimodal Natural and Chemical Languages Foundation ModelarXiv 2023BaCaDI: Bayesian Causal Discovery with Unknown InterventionsarXiv 2022MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic ApproximationarXiv 2024CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?arXiv 2024Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early PruningarXiv 2024FENet: Focusing Enhanced Network for Lane DetectionarXiv 2023LLMs Assist NLP Researchers: Critique Paper (Meta-)ReviewingarXiv 2024This is not a Dataset: A Large Negation Benchmark to Challenge Large Language ModelsarXiv 2023CPP-Net: Context-aware Polygon Proposal Network for Nucleus SegmentationarXiv 2021Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and ActivationsarXiv 2024Neuralizer: General Neuroimage Analysis without Re-TrainingCVPR 2023 1MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLarXiv 2024Query Resolution for Conversational Search with Limited SupervisionarXiv 2020ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcondaformer-disassembled-transformer-withCall Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured EnvironmentsarXiv 2024Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language ModelsarXiv 2024Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems ReconstructionarXiv 2024At Which Training Stage Does Code Data Help LLMs Reasoning?arXiv 2023Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised LearningICCV 2023 1Model Inversion Robustness: Can Transfer Learning Help?CVPR 2024 1NAPA-VQ: Neighborhood Aware Prototype Augmentation with Vector Quantization for Continual LearningarXiv 2023StRegA: Unsupervised Anomaly Detection in Brain MRIs using a Compact Context-encoding Variational AutoencoderarXiv 2022A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman TestsarXiv 2023Offline Signature Verification on Real-World DocumentsarXiv 2020NeuroBack: Improving CDCL SAT Solving using Graph Neural NetworksarXiv 2021MLPs Learn In-Context on Regression and Classification TasksarXiv 2024SketchINR: A First Look into Sketches as Implicit Neural RepresentationsCVPR 2024 1Causal Reasoning of Entities and Events in Procedural TextsarXiv 2023CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational SearcharXiv 2024MemeCraft: Contextual and Stance-Driven Multimodal Meme GenerationarXiv 2024Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood DiscrepancyarXiv 2024Leanabell-Prover: Posttraining Scaling in Formal ReasoningarXiv 2025Visual Prompting for Adversarial RobustnessarXiv 2022Learning Anatomically Consistent Embedding for Chest RadiographyarXiv 2023LLM-based Medical Assistant Personalization with Short- and Long-Term Memory CoordinationarXiv 2023Model Balancing Helps Low-data Training and Fine-tuningarXiv 2024Are CLIP features all you need for Universal Synthetic Image Origin Attribution?arXiv 2024Data Contamination Can Cross Language BarriersarXiv 2024LAN: Learning Adaptive Neighbors for Real-Time Insider Threat DetectionarXiv 2024Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) SamplingarXiv 2022Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support ConversationsarXiv 2023QASem Parsing: Text-to-text Modeling of QA-based SemanticsarXiv 2022DeViL: Decoding Vision features into LanguagearXiv 2023Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for MalteseDeepLo 2022 7Learning State-Aware Visual Representations from Audible InteractionsarXiv 2022Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FRONDarXiv 2024How does fake news use a thumbnail? CLIP-based Multimodal Detection on the Unrepresentative News ImageCONSTRAINT (ACL) 2022 5CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language ModelsarXiv 2025LDReg: Local Dimensionality Regularized Self-Supervised LearningarXiv 2024D-Former: A U-shaped Dilated Transformer for 3D Medical Image SegmentationarXiv 2022WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language ModelsarXiv 2024The NANOGrav Nine-year Data Set: Limits on the Isotropic Stochastic
Gravitational Wave BackgroundarXiv 2015RESPER: Computationally Modelling Resisting Strategies in Persuasive ConversationsEACL 2021 2Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularizationeliminating-catastrophic-overfitting-viaCryCeleb: A Speaker Verification Dataset Based on Infant Cry SoundsarXiv 2023UniRAG: Universal Retrieval Augmentation for Large Vision Language ModelsarXiv 2024EX-FEVER: A Dataset for Multi-hop Explainable Fact VerificationarXiv 2023NNSplitter: An Active Defense Solution for DNN Model via Automated Weight ObfuscationarXiv 2023BiDeV: Bilateral Defusing Verification for Complex Claim Fact-CheckingarXiv 2025TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-SoftmaxarXiv 2024ClarifyDelphi: Reinforced Clarification Questions with Defeasibility Rewards for Social and Moral SituationsarXiv 2022ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order OptimizationarXiv 2023A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain AdaptationCVPR 2023 1Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking ModelsarXiv 2022CoRT: Complementary Rankings from TransformersNAACL 2021 4Controllable 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 2024