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.
Real-Time Violence Detection Using CNN-LSTMarXiv 2021EEEA-Net: An Early Exit Evolutionary Neural Architecture SearcharXiv 2021Opening the AI black box: program synthesis via mechanistic interpretabilityarXiv 2024MACP: Efficient Model Adaptation for Cooperative PerceptionarXiv 2023Policy Regularization with Dataset Constraint for Offline Reinforcement LearningarXiv 2023Will we run out of data? Limits of LLM scaling based on human-generated dataarXiv 2022Understanding Addition in TransformersarXiv 2023Speech Resources in the Tamasheq LanguageLREC 2022 6Survey of Cultural Awareness in Language Models: Text and BeyondarXiv 2024When does dough become a bagel? Analyzing the remaining mistakes on ImageNetarXiv 2022Stack Attention: Improving the Ability of Transformers to Model Hierarchical PatternsarXiv 2023Direct Preference Optimization with an OffsetarXiv 2024Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic GrapharXiv 2024Learning to Assist Humans without Inferring RewardsarXiv 2024Do These LLM Benchmarks Agree? Fixing Benchmark Evaluation with BenchBencharXiv 2024OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued PretrainingarXiv 2023AdaRefiner: Refining Decisions of Language Models with Adaptive FeedbackarXiv 2023MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization TaskarXiv 2022Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery DetectionarXiv 2024C-RAG: Certified Generation Risks for Retrieval-Augmented Language ModelsarXiv 2024SupFusion: Supervised LiDAR-Camera Fusion for 3D Object DetectionICCV 2023 1DMoERM: Recipes of Mixture-of-Experts for Effective Reward ModelingarXiv 2024Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic ChangearXiv 2022Making Long-Context Language Models Better Multi-Hop ReasonersarXiv 2024WhyAct: Identifying Action Reasons in Lifestyle VlogsEMNLP 2021 11Graph Self-supervised Learning with Accurate Discrepancy LearningarXiv 2022Insights into LLM Long-Context Failures: When Transformers Know but Don't TellarXiv 2024NIPQ: Noise proxy-based Integrated Pseudo-Quantizationnipq-noise-proxy-based-integrated-pseudoUnderstanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench BenchmarkarXiv 2024RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World ScenariosarXiv 2024Image Inpainting with Learnable Bidirectional Attention Mapsimage-inpainting-with-learnable-bidirectional-1DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena GamesarXiv 2022Long Text and Multi-Table Summarization: Dataset and MethodarXiv 2023Token-Scaled Logit Distillation for Ternary Weight Generative Language Modelstoken-scaled-logit-distillation-for-ternaryLike hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense ExpansionsEMNLP 2020 11Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference OptimizationarXiv 2024Exploring Backdoor Vulnerabilities of Chat ModelsarXiv 2024OptEmbed: Learning Optimal Embedding Table for Click-through Rate PredictionarXiv 2022Language Models Learn to Mislead Humans via RLHFarXiv 2024Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and BeyondarXiv 2023Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype NetworksICCV 2023 1Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language ModelsarXiv 2023LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive ModelsarXiv 2025Learning to Deceive with Attention-Based Explanationslearning-to-deceive-with-attention-based-1Parameter-Efficient Fine-Tuning of State Space ModelsarXiv 2024Online Graph Dictionary LearningarXiv 2021STARD: A Chinese Statute Retrieval Dataset with Real Queries Issued by Non-professionalsarXiv 2024E2E-LOAD: End-to-End Long-form Online Action DetectionICCV 2023 1How Far are We from Robust Long Abstractive Summarization?arXiv 2022UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D ReconstructionICCV 2023 1GameEval: Evaluating LLMs on Conversational GamesarXiv 2023STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory ReplayarXiv 2024LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual LexiconsarXiv 2024Engagement Detection with Multi-Task Training in E-Learning EnvironmentsarXiv 2022Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationarXiv 2023Lightweight Transformers for Clinical Natural Language ProcessingarXiv 2023EPIE Dataset: A Corpus For Possible Idiomatic ExpressionsarXiv 2020Towards Training-free Open-world Segmentation via Image Prompt Foundation ModelsarXiv 2023ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language ModelsarXiv 2024Optimizing the Collaboration Structure in Cross-Silo Federated LearningarXiv 2023CAST: Character labeling in Animation using Self-supervision by TrackingarXiv 2022Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path PredictionarXiv 2023Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model EnsemblesarXiv 2024MFAQ: a Multilingual FAQ DatasetEMNLP (MRQA) 2021 11SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing DeepfakesICCV 2023 1Generating Persona Consistent Dialogues by Exploiting Natural Language InferencearXiv 2019Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in RussianarXiv 2022One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latencyone-timestep-is-all-you-need-training-spikingThe effectiveness of feature attribution methods and its correlation with automatic evaluation scoresNeurIPS 2021 12In-Context Symbolic Regression: Leveraging Large Language Models for Function DiscoveryarXiv 2024TransICD: Transformer Based Code-wise Attention Model for Explainable ICD CodingarXiv 2021German Text Embedding Clustering BenchmarkarXiv 2024X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot AgentsarXiv 2023LoCoCo: Dropping In Convolutions for Long Context CompressionarXiv 2024Long-tailed Instance Segmentation using Gumbel Optimized LossarXiv 2022PsyGUARD: An Automated System for Suicide Detection and Risk Assessment in Psychological CounselingarXiv 2024Real-Time Machine-Learning-Based Optimization Using Input Convex Long Short-Term Memory NetworkarXiv 2023DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action LocalizationICCV 2023 1CreoleVal: Multilingual Multitask Benchmarks for CreolesarXiv 2023BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book ReviewsarXiv 2023Emergency Department Decision Support using Clinical Pseudo-notesarXiv 2024Characterizing Multi-Domain False News and Underlying User Effects on Chinese WeiboarXiv 2022ProTrix: Building Models for Planning and Reasoning over Tables with Sentence ContextarXiv 2024Dual-Branch Network for Portrait Image Quality AssessmentarXiv 2024MELTing point: Mobile Evaluation of Language TransformersarXiv 2024Subequivariant Graph Reinforcement Learning in 3D EnvironmentsarXiv 2023Towards Robust Named Entity Recognition for Historic Germantowards-robust-named-entity-recognition-for-1DANLI: Deliberative Agent for Following Natural Language InstructionsarXiv 2022Enhancing Visual Question Answering through Question-Driven Image Captions as PromptsarXiv 2024A Neural Span-Based Continual Named Entity Recognition ModelarXiv 2023SpecDec++: Boosting Speculative Decoding via Adaptive Candidate LengthsarXiv 2024Localizing Moments in Long Video Via Multimodal GuidanceICCV 2023 1Image-free Classifier Injection for Zero-Shot ClassificationICCV 2023 1Global Proxy-based Hard Mining for Visual Place RecognitionarXiv 2023LoRA Learns Less and Forgets LessarXiv 2024Location-aware Adaptive Normalization: A Deep Learning Approach For
Wildfire Danger ForecastingarXiv 2022Swift: An Autoregressive Consistency Model for Efficient Weather
ForecastingarXiv 2025The MAMe Dataset: On the relevance of High Resolution and Variable Shape image propertiesarXiv 2020BookSQL: A Large Scale Text-to-SQL Dataset for Accounting DomainarXiv 2024Hallucinations in Large Multilingual Translation ModelsarXiv 2023Learning Robust Global Representations by Penalizing Local Predictive Powerlearning-robust-global-representations-byAGG-Net: Attention Guided Gated-convolutional Network for Depth Image CompletionICCV 2023 1Adversarial Representation Engineering: A General Model Editing Framework for Large Language ModelsarXiv 2024Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context LearningarXiv 2023Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?arXiv 2024CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT ImagearXiv 2020RyanSpeech: A Corpus for Conversational Text-to-Speech SynthesisarXiv 2021Distracting Downpour: Adversarial Weather Attacks for Motion EstimationICCV 2023 1StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative ModelICCV 2023 1Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to DoarXiv 2021Automated Identification of Toxic Code Reviews Using ToxiCRarXiv 2022The Forecast TraparXiv 2022LGV: Boosting Adversarial Example Transferability from Large Geometric VicinityarXiv 2022Subclass-balancing Contrastive Learning for Long-tailed RecognitionICCV 2023 1VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language ModelsarXiv 2023Generating Data for Symbolic Language with Large Language ModelsarXiv 2023Preserving Linear Separability in Continual Learning by Backward Feature ProjectionCVPR 2023 1PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic ApproacharXiv 2025Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language ModelsarXiv 2025Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language ModelsarXiv 2024T2IShield: Defending Against Backdoors on Text-to-Image Diffusion ModelsarXiv 2024Citekit: A Modular Toolkit for Large Language Model Citation GenerationarXiv 2024AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP TasksFindings (NAACL) 2022 7From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot ContextsarXiv 2023Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMsarXiv 2024Early Weight Averaging meets High Learning Rates for LLM Pre-trainingarXiv 2023Cache Me If You Must: Adaptive Key-Value Quantization for Large Language ModelsarXiv 2025Flexible Model Aggregation for Quantile RegressionarXiv 2021Deep contextualized word representations for detecting sarcasm and ironydeep-contextualized-word-representations-for-1NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial PerturbationsarXiv 2023TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly DetectionICCV 2023 1Forcing Diffuse Distributions out of Language ModelsarXiv 2024How to Trust Your Diffusion Model: A Convex Optimization Approach to Conformal Risk ControlarXiv 2023CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modallyarXiv 2025When Reasoning Meets Information Aggregation: A Case Study with Sports NarrativesarXiv 2024AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision TasksarXiv 2024Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guidingarXiv 2021Mitigating Open-Vocabulary Caption HallucinationsarXiv 2023PersonalLLM: Tailoring LLMs to Individual PreferencesarXiv 2024DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsarXiv 2025CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based VerificationarXiv 2024Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLMarXiv 2024OCD: Learning to Overfit with Conditional Diffusion ModelsarXiv 2022DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion ModelsICCV 2023 1FedLoGe: Joint Local and Generic Federated Learning under Long-tailed DataarXiv 2024Contrastive Vicinal Space for Unsupervised Domain AdaptationarXiv 2021Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-EncodersarXiv 2024NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDFnu-mcc-multiview-compressive-coding-withTraining-free Composite Scene Generation for Layout-to-Image SynthesisarXiv 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table DecompositionarXiv 2024Continual Learning and Private UnlearningarXiv 2022Streaming Video Diffusion: Online Video Editing with Diffusion ModelsarXiv 2024Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report GenerationarXiv 2023Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual DescriptionsarXiv 2024Regularization by Texts for Latent Diffusion Inverse SolversarXiv 2023Prompt Optimization with Human FeedbackarXiv 2024Structuring Representation Geometry with Rotationally Equivariant Contrastive LearningarXiv 2023Real or Fake Text?: Investigating Human Ability to Detect Boundaries Between Human-Written and Machine-Generated TextarXiv 2022Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial RobustnessarXiv 2020Erasing Undesirable Concepts in Diffusion Models with Adversarial PreservationarXiv 2024COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsarXiv 2023Single Image Backdoor Inversion via Robust Smoothed ClassifiersCVPR 2023 1Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face RecognitionNeurIPS 2023 11Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and ChallengesarXiv 2022Modeling Caption Diversity in Contrastive Vision-Language PretrainingarXiv 2024Language Models are Universal EmbeddersarXiv 2023ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object DetectionICCV 2023 1Simple Baselines for Interactive Video Retrieval with Questions and AnswersICCV 2023 1Time Series Analysis for Education: Methods, Applications, and Future DirectionsarXiv 2024o3-mini vs DeepSeek-R1: Which One is Safer?arXiv 2025Is Imitation All You Need? Generalized Decision-Making with Dual-Phase TrainingICCV 2023 1Improving Sequence-to-Sequence Pre-training via Sequence Span RewritingEMNLP 2021 11EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart UnderstandingarXiv 2024Toward quantitative fractography using convolutional neural networksarXiv 2019Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual SpacearXiv 2024Preference-grounded Token-level Guidance for Language Model Fine-tuningpreference-grounded-token-level-guidance-forExploiting Pretrained Biochemical Language Models for Targeted Drug DesignarXiv 2022This Looks Like That, Because ... Explaining Prototypes for Interpretable Image RecognitionarXiv 2020MPMQA: Multimodal Question Answering on Product ManualsarXiv 2023SPADE: Synthesizing Assertions for Large Language Model PipelinesarXiv 2024Synth-Empathy: Towards High-Quality Synthetic Empathy DataarXiv 2024MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late
InteractionarXiv 2025Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?arXiv 2023Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory WeightingarXiv 2023Differentiable Discrete Elastic Rods for Real-Time Modeling of
Deformable Linear ObjectsarXiv 2024The Truth Lies Somewhere in the Middle (of the Generated Tokens)arXiv 2026CSGCL: Community-Strength-Enhanced Graph Contrastive LearningarXiv 2023Better Neural PDE Solvers Through Data-Free Mesh MoversarXiv 2023How to Select Datapoints for Efficient Human Evaluation of NLG Models?arXiv 2025Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection ModelsNAACL (WOAH) 2022 7Ada-Instruct: Adapting Instruction Generators for Complex ReasoningarXiv 2023CLEAR: Character Unlearning in Textual and Visual ModalitiesarXiv 2024Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern RecognitionarXiv 2024Face Aging With Conditional Generative Adversarial NetworksarXiv 2017Interactive Medical Image Analysis with Concept-based Similarity ReasoningCVPR 2025 1Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical ReasoningarXiv 2023Towards Compositionality in Concept LearningarXiv 2024Latent Autoregressive Source SeparationarXiv 2023Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and FeedbackarXiv 2024ReDi: Efficient Learning-Free Diffusion Inference via Trajectory RetrievalarXiv 2023