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.
Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information MaximizationarXiv 2020Auto-Regressive Next-Token Predictors are Universal LearnersarXiv 2023Linear-Time Graph Neural Networks for Scalable RecommendationsarXiv 2024Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy InstructionsarXiv 2023GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point CloudsICCV 2023 1Large Language Models Are Neurosymbolic ReasonersarXiv 2024Spatiotemporal Entropy Model is All You Need for Learned Video CompressionarXiv 2021MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought PromptingarXiv 2023LipSim: A Provably Robust Perceptual Similarity MetricarXiv 2023ELLA: Exploration through Learned Language AbstractionNeurIPS 2021 12Getting the most out of your tokenizer for pre-training and domain adaptationarXiv 2024Ask-before-Plan: Proactive Language Agents for Real-World PlanningarXiv 2024Contrastive Learning Is Spectral Clustering On Similarity GrapharXiv 2023Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive DialoguearXiv 2023Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term ConversationsarXiv 2024VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence NormalizationCVPR 2023 1Data Poisoning Attacks Against Multimodal EncodersarXiv 2022Transforming Sentiment Analysis in the Financial Domain with ChatGPTarXiv 2023Joint Multi-Person Body Detection and Orientation Estimation via One Unified EmbeddingarXiv 2022CurbNet: Curb Detection Framework Based on LiDAR Point Cloud SegmentationarXiv 2024Foundational Large Language Models for Materials ResearcharXiv 2024Writing Polishment with Simile: Task, Dataset and A Neural ApproacharXiv 2020Can Language Models Understand Physical Concepts?arXiv 2023ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement LearningarXiv 2026Don't Play Favorites: Minority Guidance for Diffusion ModelsarXiv 2023Attention Meets Post-hoc Interpretability: A Mathematical PerspectivearXiv 2024Themis: A Reference-free NLG Evaluation Language Model with Flexibility and InterpretabilityarXiv 2024Multimodal LLMs Can Reason about Aesthetics in Zero-ShotarXiv 2025Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile AgentsarXiv 2024TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language ModelsarXiv 2024ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in ImagesarXiv 2024Pretraining Data Detection for Large Language Models: A Divergence-based Calibration MethodarXiv 2024HIVE: Evaluating the Human Interpretability of Visual ExplanationsarXiv 2021LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity OptimizationarXiv 2023MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better TranslatorsACL 2022 5Scaling Sparse Fine-Tuning to Large Language ModelsarXiv 2024Training Consistency Models with Variational Noise CouplingarXiv 2025AugESC: Dialogue Augmentation with Large Language Models for Emotional Support ConversationarXiv 2022Robust Models are less Over-ConfidentarXiv 2022EZ-CLIP: Efficient Zeroshot Video Action RecognitionarXiv 2023DANIEL: A fast Document Attention Network for Information Extraction and Labelling of handwritten documentsarXiv 2024QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-CorrectionarXiv 2024Among Us: Adversarially Robust Collaborative Perception by ConsensusICCV 2023 1IndoNLI: A Natural Language Inference Dataset for IndonesianEMNLP 2021 11HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event SequencesarXiv 2022Entropy-Regularized Process Reward ModelarXiv 2024UltraIF: Advancing Instruction Following from the WildarXiv 2025AutoRAG: Automated Framework for optimization of Retrieval Augmented Generation PipelinearXiv 2024Large Language Models for Multi-Robot Systems: A SurveyarXiv 2025Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror ReflectionsarXiv 2024KANQAS: Kolmogorov-Arnold Network for Quantum Architecture SearcharXiv 2024CoReS: Orchestrating the Dance of Reasoning and SegmentationarXiv 2024Supervised Metric Learning to Rank for Retrieval via Contextual Similarity OptimizationarXiv 2022LFS-GAN: Lifelong Few-Shot Image GenerationICCV 2023 1Leveraging Spatio-Temporal Dependency for Skeleton-Based Action RecognitionICCV 2023 1BS-LDM: Effective Bone Suppression in High-Resolution Chest X-Ray Images with Conditional Latent Diffusion ModelsarXiv 20243DRegNet: A Deep Neural Network for 3D Point Registration3dregnet-a-deep-neural-network-for-3d-point-1Decentralized SGD and Average-direction SAM are Asymptotically EquivalentarXiv 2023Beyond KV Caching: Shared Attention for Efficient LLMsarXiv 2024MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM IntegrationarXiv 2024How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed QuestionsarXiv 20193D molecule generation by denoising voxel grids3d-molecule-generation-by-denoising-voxelValue Augmented Sampling for Language Model Alignment and PersonalizationarXiv 2024Constrained Synthesis with Projected Diffusion ModelsarXiv 2024U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point CloudsICCV 2023 1KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language ModelsarXiv 2024CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin LesionsarXiv 2022Can LLMs be Good Graph Judge for Knowledge Graph Construction?arXiv 2024AutoGluon-Tabular: Robust and Accurate AutoML for Structured DataarXiv 2020An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt LearningarXiv 2023AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM InferencearXiv 2025Evaluating Multiview Object Consistency in Humans and Image ModelsarXiv 2024NELA-GT-2022: A Large Multi-Labelled News Dataset for The Study of Misinformation in News ArticlesarXiv 2022Large Language Models are In-Context Semantic Reasoners rather than Symbolic ReasonersarXiv 2023ReconResNet: Regularised Residual Learning for MR Image Reconstruction of Undersampled Cartesian and Radial DataarXiv 2021CLIPTrans: Transferring Visual Knowledge with Pre-trained Models for Multimodal Machine TranslationICCV 2023 1Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene UnderstandingCVPR 2025 1Bias in Multimodal AI: Testbed for Fair Automatic RecruitmentarXiv 2020RELIC: Retrieving Evidence for Literary ClaimsACL 2022 5Long-Sequence Recommendation Models Need Decoupled EmbeddingsarXiv 2024Samudra: An AI Global Ocean Emulator for ClimatearXiv 2024Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward PassesarXiv 2024Acoustic Prompt Tuning: Empowering Large Language Models with Audition CapabilitiesarXiv 2023VPO: Aligning Text-to-Video Generation Models with Prompt OptimizationICCV 2025HYPE: Hyperbolic Entailment Filtering for Underspecified Images and TextsarXiv 2024Poro 34B and the Blessing of MultilingualityarXiv 2024Label-Efficient Online Continual Object Detection in Streaming VideoICCV 2023 1ZeroSCROLLS: A Zero-Shot Benchmark for Long Text UnderstandingarXiv 2023Membrane Potential Batch Normalization for Spiking Neural NetworksICCV 2023 1Demystifying Domain-adaptive Post-training for Financial LLMsarXiv 2025DC-Former: Diverse and Compact Transformer for Person Re-IdentificationarXiv 2023Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and BenchmarkingarXiv 2024Regulatory DNA sequence Design with Reinforcement LearningarXiv 2025Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear RegressionarXiv 2023FakeSound: Deepfake General Audio DetectionarXiv 2024Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal DataarXiv 2022Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM NetworkarXiv 2020InstructG2I: Synthesizing Images from Multimodal Attributed GraphsarXiv 2024Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine TranslationarXiv 2022Removing Biases from Molecular Representations via Information MaximizationarXiv 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled DataarXiv 2023CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-IdentificationarXiv 2024Controllable Text Generation with Neurally-Decomposed OraclearXiv 2022Detecting Edit Failures In Large Language Models: An Improved Specificity BenchmarkarXiv 2023Can Language Models Learn to Skip Steps?arXiv 2024The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant UnitsarXiv 2024Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language NavigationICCV 2023 1LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-PlayarXiv 2024Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-AugmentationarXiv 2024DevFormer: A Symmetric Transformer for Context-Aware Device PlacementarXiv 2022Graph-based Multi-ODE Neural Networks for Spatio-Temporal Traffic ForecastingarXiv 2023CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy RewardarXiv 2025A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised LearningEMNLP 2020 11SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter PruningarXiv 2022MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-EntropiesarXiv 2023Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting MethodarXiv 2023FlamePINN-1D: Physics-informed neural networks to solve forward and inverse problems of 1D laminar flamesarXiv 2024SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question AnsweringCVPR 2022 1RuleBert: Teaching Soft Rules to Pre-trained Language ModelsEMNLP 2021 11RPMArt: Towards Robust Perception and Manipulation for Articulated ObjectsarXiv 2024Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion ModelsICCV 2025EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented GenerationarXiv 2024InstructPix2NeRF: Instructed 3D Portrait Editing from a Single ImagearXiv 2023CREAK: A Dataset for Commonsense Reasoning over Entity KnowledgearXiv 2021Fine-tuning Whisper on Low-Resource Languages for Real-World ApplicationsarXiv 2024Great Models Think Alike and this Undermines AI OversightarXiv 2025Differential Evolution for Neural Architecture SearcharXiv 2020One-bit Flip is All You Need: When Bit-flip Attack Meets Model TrainingICCV 2023 1Referring Atomic Video Action RecognitionarXiv 2024GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority LanguagesarXiv 2024UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANsCVPR 2024 1Bit Allocation using OptimizationarXiv 2022Efficiently Serving Large Multimodal Models Using EPD DisaggregationarXiv 2024Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning SystemsarXiv 2022Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic CompositionalityarXiv 2024A Periodic Bayesian Flow for Material GenerationarXiv 2025DSRC: Learning Density-insensitive and Semantic-aware Collaborative Representation against CorruptionsarXiv 2024ClimateBert: A Pretrained Language Model for Climate-Related TextarXiv 2021Fine-Tuning Transformers: Vocabulary TransferarXiv 2021STA-V2A: Video-to-Audio Generation with Semantic and Temporal AlignmentarXiv 2024Balancing reconstruction error and Kullback-Leibler divergence in Variational AutoencodersarXiv 2020Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference LabelsarXiv 2024Towards Robust Offline Reinforcement Learning under Diverse Data CorruptionarXiv 2023LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical ReportarXiv 2024SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene ReconstructionarXiv 2024Understanding Points of Correspondence between Sentences for Abstractive Summarizationunderstanding-points-of-correspondence-1AI Control: Improving Safety Despite Intentional SubversionarXiv 2023Long Horizon Temperature ScalingarXiv 2023LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model DevelopmentarXiv 2023Deep Image Harmonization with Globally Guided Feature Transformation and Relation DistillationICCV 2023 1Dehazing Ultrasound using Diffusion ModelsarXiv 2023Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-trainingEMNLP 2021 11Gradient is All You Need?arXiv 2023Dataset Decomposition: Faster LLM Training with Variable Sequence Length CurriculumarXiv 2024Resolving Discrepancies in Compute-Optimal Scaling of Language ModelsarXiv 2024Length-Aware Motion Synthesis via Latent DiffusionarXiv 2024The Expressive Power of Low-Rank AdaptationarXiv 2023DPO Meets PPO: Reinforced Token Optimization for RLHFarXiv 2024TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning ModelsarXiv 2021Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph EntitiesarXiv 2020Contrastive Learning of User Behavior Sequence for Context-Aware Document RankingarXiv 2021PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic SegmentationarXiv 2023POV-Surgery: A Dataset for Egocentric Hand and Tool Pose Estimation During Surgical ActivitiesarXiv 2023BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation EvaluationarXiv 2023Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic InterpretationsarXiv 2024Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine TranslationarXiv 2022TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned DecisionarXiv 2024Total Variation Graph Neural NetworksarXiv 2022A Lie Group Approach to Riemannian Batch NormalizationarXiv 2024DomainMix: Learning Generalizable Person Re-Identification Without Human AnnotationsarXiv 2020Textually Pretrained Speech Language ModelsNeurIPS 2023 11Does Biomedical Training Lead to Better Medical Performance?arXiv 2024Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument ExtractionACL 2022 5Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentationrewrite-caption-semantics-bridging-semanticA Simple Early Exiting Framework for Accelerated Sampling in Diffusion ModelsarXiv 2024GEAR: Augmenting Language Models with Generalizable and Efficient Tool ResolutionarXiv 2023RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution RobustnessarXiv 2022Anatomically-aware Uncertainty for Semi-supervised Image SegmentationarXiv 2023Measuring and Controlling Instruction (In)Stability in Language Model DialogsarXiv 2024On Optimal Caching and Model Multiplexing for Large Model InferencearXiv 2023CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language ModelsarXiv 2024IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code GeneratorsarXiv 2024NutriBench: A Dataset for Evaluating Large Language Models on Nutrition Estimation from Meal DescriptionsarXiv 2024DeliveryBench: Can Agents Earn Profit in Real World?arXiv 2025CHEAT: A Large-scale Dataset for Detecting ChatGPT-writtEn AbsTractsarXiv 2023Continuous-Time Functional Diffusion Processescontinuous-time-functional-diffusionDialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State TrackingFindings (ACL) 2022 5Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Language ModelsarXiv 2023TransHP: Image Classification with Hierarchical Promptingtranshp-image-classification-withFedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated LearningICCV 2023 1Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley ValuesarXiv 2021Addressing Loss of Plasticity and Catastrophic Forgetting in Continual LearningarXiv 2024Detector Guidance for Multi-Object Text-to-Image GenerationarXiv 2023SILG: The Multi-environment Symbolic Interactive Language Grounding BenchmarkarXiv 2021A semantic embedding space based on large language models for modelling human beliefsarXiv 2024Anchor-based Large Language ModelsarXiv 2024CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response GenerationarXiv 2022An Embarrassingly Simple Backdoor Attack on Self-supervised LearningICCV 2023 1Label-Noise Learning with Intrinsically Long-Tailed DataICCV 2023 1Reward Shaping to Mitigate Reward Hacking in RLHFarXiv 2025