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.
Verifiable Goal Recognition for Autonomous Driving with OcclusionsarXiv 2022Witness Generation for JSON SchemaarXiv 2022Neural Parameter Allocation Searchneural-parameter-allocation-searchSystematic Rectification of Language Models via Dead-end AnalysisarXiv 2023Do Large Language Models Truly Understand Geometric Structures?arXiv 2025Copyright Violations and Large Language ModelsarXiv 2023Zero-shot causal learningzero-shot-causal-learningFAENet: Frame Averaging Equivariant GNN for Materials ModelingarXiv 2023Efficient Document Re-Ranking for Transformers by Precomputing Term RepresentationsarXiv 2020ODE Discovery for Longitudinal Heterogeneous Treatment Effects InferencearXiv 2024"Why did the Model Fail?": Attributing Model Performance Changes to Distribution ShiftsarXiv 2022SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQAarXiv 2024CLIN-X: pre-trained language models and a study on cross-task transfer for concept extraction in the clinical domainarXiv 2021Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma ClassificationarXiv 2021The Many Dimensions of Truthfulness: Crowdsourcing Misinformation Assessments on a Multidimensional ScalearXiv 2021A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizationsa-theoretical-explanation-for-perplexing-1LPViT: Low-Power Semi-structured Pruning for Vision TransformersarXiv 2024Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of ExemplarsarXiv 2024GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognitionbeyond-web-scraping-crowd-sourcing-aHierarchical Softmax for End-to-End Low-resource Multilingual Speech RecognitionarXiv 2022Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corporaarXiv 2023Vertical Federated Graph Neural Network for Recommender SystemarXiv 2023Learning Energy-Based Models by Cooperative Diffusion Recovery LikelihoodarXiv 2023Gasformer: A Transformer-based Architecture for Segmenting Methane Emissions from Livestock in Optical Gas ImagingarXiv 2024Enabling Discriminative Reasoning in LLMs for Legal Judgment PredictionarXiv 2024VLSlice: Interactive Vision-and-Language Slice DiscoveryICCV 2023 1Characterizing and Predicting Social Correction on TwitterarXiv 2023Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to RankEMNLP 2020 11UGMathBench: A Diverse and Dynamic Benchmark for Undergraduate-Level Mathematical Reasoning with Large Language ModelsarXiv 2025Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt TemplatesarXiv 2024ETran: Energy-Based Transferability EstimationICCV 2023 1FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for
Medical domainarXiv 2023Offline Meta Reinforcement Learning with In-Distribution Online AdaptationarXiv 2023What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial NetworkarXiv 2023End-to-end Differentiable Clustering with Associative MemoriesarXiv 2023Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inferencearXiv 2024Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue SystemarXiv 2023WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic SpansSEMEVAL 2021Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary EnhancementarXiv 2026CO2: Efficient Distributed Training with Full Communication-Computation OverlaparXiv 2024Sampling with Mirrored Stein Operatorssampling-with-mirrored-stein-operators-1Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial TrainingarXiv 2020A Notion of Complexity for Theory of Mind via Discrete World ModelsarXiv 2024Online Unsupervised Video Object Segmentation via Contrastive Motion ClusteringarXiv 2023DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning
with Client MomentumarXiv 2023SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical AlterationsarXiv 2024Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary DataarXiv 2023DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse LanguagesarXiv 2022LLaVA Needs More Knowledge: Retrieval Augmented Natural Language Generation with Knowledge Graph for Explaining Thoracic PathologiesarXiv 2024Pruning-aware Sparse Regularization for Network PruningarXiv 2022DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge GraphsarXiv 2024Dealing with Typos for BERT-based Passage Retrieval and RankingEMNLP 2021 11Reasoning with LLMs for Zero-Shot Vulnerability DetectionarXiv 2025Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse ProblemsarXiv 2024DE-COP: Detecting Copyrighted Content in Language Models Training DataarXiv 2024HoloNets: Spectral Convolutions do extend to Directed GraphsarXiv 2023Long-Short History of Gradients is All You Need: Detecting Malicious and Unreliable Clients in Federated LearningarXiv 2022Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax ReductionarXiv 2024Pathways on the Image Manifold: Image Editing via Video GenerationCVPR 2025 1Learning Better Masking for Better Language Model Pre-trainingarXiv 2022ACLSum: A New Dataset for Aspect-based Summarization of Scientific PublicationsarXiv 2024Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-AttentionarXiv 2023A density estimation perspective on learning from pairwise human preferencesarXiv 2023Adversarial Bayesian Augmentation for Single-Source Domain GeneralizationICCV 2023 1Varifocal Question Generation for Fact-checkingarXiv 2022Formalizing and Estimating Distribution Inference RisksarXiv 2021D2PO: Discriminator-Guided DPO with Response Evaluation ModelsarXiv 2024SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian LanguagesarXiv 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level PerturbationsarXiv 2024SemiPFL: Personalized Semi-Supervised Federated Learning Framework for Edge IntelligencearXiv 2022Sparse Autoencoder Features for Classifications and TransferabilityarXiv 2025Right this way: Can VLMs Guide Us to See More to Answer Questions?arXiv 2024Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over TimearXiv 2023CollabStory: Multi-LLM Collaborative Story Generation and Authorship AnalysisarXiv 2024Evaluating Factual Consistency of Summaries with Large Language ModelsarXiv 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal FusionCVPR 2023 1Exploration into Translation-Equivariant Image QuantizationarXiv 2021Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective DistillationFindings (ACL) 2022 5ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression LearningarXiv 2023BeLLM: Backward Dependency Enhanced Large Language Model for Sentence EmbeddingsarXiv 2023SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NASarXiv 2024LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question AnsweringarXiv 2021Inverse problem regularization with hierarchical variational autoencodersICCV 2023 1Multi-annotator Deep Learning: A Probabilistic Framework for ClassificationarXiv 2023Hierarchies of Reward MachinesarXiv 2022Temporal Reasoning Transfer from Text to VideoarXiv 2024MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of ShardsarXiv 2024Spatial-temporal Concept based Explanation of 3D ConvNetsCVPR 2023 1Concept-based Explanations for Out-Of-Distribution DetectorsarXiv 2022User Satisfaction Estimation with Sequential Dialogue Act Modeling in Goal-oriented Conversational SystemsarXiv 2022Semantic Ranking for Automated Adversarial Technique Annotation in
Security TextarXiv 2024Bi-directional Attention with Agreement for Dependency Parsingbi-directional-attention-with-agreement-for-1Contracting Skeletal Kinematics for Human-Related Video Anomaly DetectionarXiv 2023Dataset Distillation by Automatic Training TrajectoriesarXiv 2024Train Long, Think Short: Curriculum Learning for Efficient ReasoningarXiv 2025Distilling Rule-based Knowledge into Large Language ModelsarXiv 2023NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local CommunitiesarXiv 2025LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and BenchmarkICCV 2023 1FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust ClusteringarXiv 2023Spy-Watermark: Robust Invisible Watermarking for Backdoor AttackarXiv 2024ExpLLM: Towards Chain of Thought for Facial Expression RecognitionarXiv 2024Cooperative Retriever and Ranker in Deep RecommendersarXiv 2022Can LLM-Augmented autonomous agents cooperate?, An evaluation of their cooperative capabilities through Melting PotarXiv 2024Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual ReasoningarXiv 2026MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMsarXiv 2024Information-Theoretic Segmentation by Inpainting Error MaximizationCVPR 2021 1Think-J: Learning to Think for Generative LLM-as-a-JudgearXiv 2025People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language DetectionarXiv 2023Predictive, scalable and interpretable knowledge tracing on structured domainsarXiv 2024KazSAnDRA: Kazakh Sentiment Analysis Dataset of Reviews and AttitudesarXiv 2024DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary DomainarXiv 2026A New Benchmark and Reverse Validation Method for Passage-level Hallucination DetectionarXiv 2023Retrieval Augmented Zero-Shot Text ClassificationarXiv 2024xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation MetricsarXiv 2024Long-Term Ad Memorability: Understanding & Generating Memorable AdsarXiv 2023Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectorsarXiv 2024Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication ChannelarXiv 2023Tracking the Feature Dynamics in LLM Training: A Mechanistic StudyarXiv 2024Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly DetectionarXiv 2020Zero and Few-shot Semantic Parsing with Ambiguous InputsarXiv 2023Aligning Large Language Models by On-Policy Self-JudgmentarXiv 2024Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain GeneralizationarXiv 2024Demo2Code: From Summarizing Demonstrations to Synthesizing Code via
Extended Chain-of-ThoughtarXiv 2023Crystal: Introspective Reasoners Reinforced with Self-FeedbackarXiv 2023Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMsarXiv 2024Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-LevelsarXiv 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized SmoothingarXiv 2024PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuningarXiv 2024Order-preserving Consistency Regularization for Domain Adaptation and GeneralizationICCV 2023 1Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt WordingarXiv 2023Test Time Adaptation for Blind Image Quality AssessmentICCV 2023 1Z-LaVI: Zero-Shot Language Solver Fueled by Visual ImaginationarXiv 2022Distract Large Language Models for Automatic Jailbreak AttackarXiv 2024HC3 Plus: A Semantic-Invariant Human ChatGPT Comparison CorpusarXiv 2023Automated Educational Question Generation at Different Bloom's Skill Levels using Large Language Models: Strategies and EvaluationarXiv 2024Out-of-distribution generalization via composition: a lens through induction heads in TransformersarXiv 2024Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video RecognitionICCV 2023 1SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its TeacherarXiv 2024Live in the Moment: Learning Dynamics Model Adapted to Evolving PolicyarXiv 2022Effective Use of Transformer Networks for Entity Trackingeffective-use-of-transformer-networks-for-1Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?arXiv 2024FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion ModelsarXiv 2024Where to put the Image in an Image Caption GeneratorarXiv 2017IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language ModelsarXiv 2024On the Structural Memory of LLM AgentsarXiv 2024Deep Bayesian Active Learning for Preference Modeling in Large Language ModelsarXiv 2024Acceptability Judgements via Examining the Topology of Attention MapsarXiv 2022ProtoTEx: Explaining Model Decisions with Prototype TensorsACL 2022 5KoBE: Knowledge-Based Machine Translation EvaluationFindings of the Association for Computational Linguistics 2020Continual Semi-Supervised Learning through Contrastive Interpolation ConsistencyarXiv 2021Cascaded Span Extraction and Response Generation for Document-Grounded DialogACL (dialdoc) 2021 8VURF: A General-purpose Reasoning and Self-refinement Framework for Video UnderstandingarXiv 2024Multi-Level Compositional Reasoning for Interactive Instruction FollowingarXiv 2023Model Editing as a Robust and Denoised variant of DPO: A Case Study on ToxicityarXiv 2024CompoundPiece: Evaluating and Improving Decompounding Performance of Language ModelsarXiv 2023indicnlp@kgp at DravidianLangTech-EACL2021: Offensive Language Identification in Dravidian LanguagesEACL (DravidianLangTech) 2021 4Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation RegularizationarXiv 2024Rethinking the Role of Pre-Trained Networks in Source-Free Domain AdaptationICCV 2023 1Calibrating Reasoning in Language Models with Internal ConsistencyarXiv 2024BN-HTRd: A Benchmark Dataset for Document Level Offline Bangla Handwritten Text Recognition (HTR) and Line SegmentationarXiv 2022Will Large-scale Generative Models Corrupt Future Datasets?ICCV 2023 1Neural Amortized Inference for Nested Multi-agent ReasoningarXiv 2023To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DROarXiv 2024Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy CompetitionarXiv 2024Distribution Free Prediction Sets for Node ClassificationarXiv 2022Understanding Oversquashing in GNNs through the Lens of Effective ResistancearXiv 2023A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain GaparXiv 2024MetaHate: A Dataset for Unifying Efforts on Hate Speech DetectionarXiv 2024Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy DistillationarXiv 2024Clustering Word Embeddings with Self-Organizing Maps. Application on LaRoSeDa -- A Large Romanian Sentiment Data SetarXiv 2021PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuningarXiv 2023Kolmogorov-Arnold Network AutoencodersarXiv 2024When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and LimitationsarXiv 2023A Brief Review of Hypernetworks in Deep LearningarXiv 2023Coin Sampling: Gradient-Based Bayesian Inference without Learning RatesarXiv 2023Probing LLMs for Joint Encoding of Linguistic CategoriesarXiv 2023Temporal Label Smoothing for Early Event PredictionarXiv 2022Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep LearningarXiv 2021MemeTector: Enforcing deep focus for meme detectionarXiv 2022Style Outweighs Substance: Failure Modes of LLM Judges in Alignment BenchmarkingarXiv 2024Latent State Models of Training DynamicsarXiv 2023Parametric Information Maximization for Generalized Category DiscoveryICCV 2023 1CLUTR: Curriculum Learning via Unsupervised Task Representation LearningarXiv 2022ToNER: Type-oriented Named Entity Recognition with Generative Language ModelarXiv 2024CODE-ACCORD: A Corpus of Building Regulatory Data for Rule Generation towards Automatic Compliance CheckingarXiv 2024Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term RetentionarXiv 2024Evaluating Large Language Models on Controlled Generation TasksarXiv 2023Collaborative Tracking Learning for Frame-Rate-Insensitive Multi-Object TrackingICCV 2023 1V-LoL: A Diagnostic Dataset for Visual Logical LearningarXiv 2023Twitter conversations predict the daily confirmed COVID-19 casesarXiv 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?arXiv 2022StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style ElementsarXiv 2024Towards Infinite-Long Prefix in TransformerarXiv 2024From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in TransformersarXiv 2024Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance LearningarXiv 2022Ensembling Diffusion Models via Adaptive Feature AggregationarXiv 2024ASGuard: Activation-Scaling Guard to Mitigate Targeted Jailbreaking AttackarXiv 2026DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned ModelsarXiv 2024Transformer as Linear Expansion of LearngenearXiv 2023InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction TuningarXiv 2023