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.
Open Data Synthesis For Deep ResearcharXiv 2025Unsupervised Contrast-Consistent Ranking with Language ModelsarXiv 2023Large Language Models in Computer Science Education: A Systematic Literature ReviewarXiv 2024Diversity-Enhanced Reasoning for Subjective QuestionsarXiv 2025Injecting Image Guidance into Text-Conditioned Diffusion Models at InferencearXiv 2026PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMsarXiv 2023GPTs Are Multilingual Annotators for Sequence Generation TasksarXiv 2024AdaptEval: Evaluating Large Language Models on Domain Adaptation for Text SummarizationarXiv 2024LVLM-Interpret: An Interpretability Tool for Large Vision-Language ModelsarXiv 2024What do we know about Hugging Face? A systematic literature review and quantitative validation of qualitative claimsarXiv 2024Robust Perception through EquivariancearXiv 2022How to Detect Network Dependence in Latent Factor Models? A Bias-Corrected CD TestarXiv 2021Multimodal Foundation Models Exploit Text to Make Medical Image PredictionsarXiv 2023ReIn: Conversational Error Recovery with Reasoning InceptionarXiv 2026Teaching Probabilistic Logical Reasoning to TransformersarXiv 2023What Can Be Learnt With Wide Convolutional Neural Networks?arXiv 2022TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge DevicesarXiv 2024Learning semantic sentence representations from visually grounded language without lexical knowledgearXiv 2019Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-ExpertsarXiv 2023EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene ReconstructionarXiv 2024How to Train BERT with an Academic BudgetEMNLP 2021 11Global Crop-Specific Fertilization Dataset from 1961-2019arXiv 2024Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot TechniquesarXiv 2024Soft Tokens, Hard TruthsarXiv 2025Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample ComplexityarXiv 2023Translating Across Cultures: LLMs for Intralingual Cultural AdaptationarXiv 2024Empathy Detection from Text, Audiovisual, Audio or Physiological Signals: A Systematic Review of Task Formulations and Machine Learning MethodsarXiv 2023Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent KernelsarXiv 2023UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine TranslationarXiv 2022Conservative State Value Estimation for Offline Reinforcement Learningconservative-state-value-estimation-forHow Vocabulary Sharing Facilitates Multilingualism in LLaMA?arXiv 2023Deep Linear Networks can Benignly Overfit when Shallow Ones DoarXiv 2022Breaking the Curse of Multilinguality with Cross-lingual Expert Language ModelsarXiv 2024When Do Curricula Work in Federated Learning?ICCV 2023 1A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial DiversityarXiv 2023Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow PoliciesarXiv 2026Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model InternalsarXiv 2026Human Expertise in Algorithmic PredictionarXiv 2024Neural Network Distiller: A Python Package For DNN Compression ResearcharXiv 2019Challenges and Practices of Deep Learning Model Reengineering: A Case Study on Computer VisionarXiv 2023The Computational Limits of Deep LearningarXiv 2020CLNeRF: Continual Learning Meets NeRFICCV 2023 1Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive BiasarXiv 2023Soda-Eval: Open-Domain Dialogue Evaluation in the age of LLMsarXiv 2024Cross-lingual transfer of multilingual models on low resource African LanguagesarXiv 2024Mitigating Transformer Overconfidence via Lipschitz RegularizationarXiv 2023LOOPer: A Learned Automatic Code Optimizer For Polyhedral CompilersarXiv 2024FSD50K: An Open Dataset of Human-Labeled Sound EventsarXiv 2020Two 100 TeV neutrinos coincident with the Seyfert galaxy NGC 7469arXiv 2024MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density PredictionarXiv 2025Automated Quantum Circuit Design with Nested Monte Carlo Tree SearcharXiv 2022BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimizationbq-nco-bisimulation-quotienting-for-efficientMultiSubs: A Large-scale Multimodal and Multilingual DatasetLREC 2022 6Dynamic Evaluation of Large Language Models by Meta Probing AgentsarXiv 2024CoLRIO: LiDAR-Ranging-Inertial Centralized State Estimation for Robotic
SwarmsarXiv 2024DeAL: Decoding-time Alignment for Large Language ModelsarXiv 2024Quadratic models for understanding catapult dynamics of neural networksarXiv 2022APIGen: Generative API Method RecommendationarXiv 2024AI auditing: The Broken Bus on the Road to AI AccountabilityarXiv 2024Health Text Simplification: An Annotated Corpus for Digestive Cancer Education and Novel Strategies for Reinforcement LearningarXiv 2024Emotion Classification In Software Engineering Texts: A Comparative
Analysis of Pre-trained Transformers Language ModelsarXiv 2024Performative Recommendation: Diversifying Content via Strategic IncentivesarXiv 2023Rethinking Round-Trip Translation for Machine Translation EvaluationarXiv 2022Graph Mamba: Towards Learning on Graphs with State Space ModelsarXiv 2024Scaling Mesh Generation via Compressive TokenizationCVPR 2025 1Capability Instruction Tuning: A New Paradigm for Dynamic LLM RoutingarXiv 2025ScanBank: A Benchmark Dataset for Figure Extraction from Scanned Electronic Theses and DissertationsarXiv 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesistowards-faster-and-stabilized-gan-trainingLook Again, Think Slowly: Enhancing Visual Reflection in Vision-Language ModelsarXiv 2025Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified ModelarXiv 2024Multi-head Spatial-Spectral Mamba for Hyperspectral Image ClassificationarXiv 2024Consecutive Batch Model Editing with HooK LayersarXiv 2024ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion RecognitionarXiv 2024Evaluating Neural Language Models as Cognitive Models of Language AcquisitionarXiv 2023Delving into the Utilisation of ChatGPT in Scientific Publications in AstronomyarXiv 2024Unveiling Global Narratives: A Multilingual Twitter Dataset of News Media on the Russo-Ukrainian ConflictarXiv 2023Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention SteeringarXiv 2024HaloScope: Harnessing Unlabeled LLM Generations for Hallucination DetectionarXiv 2024Evaluating Dialect Robustness of Language Models via Conversation UnderstandingarXiv 2024From Babble to Words: Pre-Training Language Models on Continuous Streams of PhonemesarXiv 2024Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and BenchmarksarXiv 2024DynaSaur: Large Language Agents Beyond Predefined ActionsarXiv 2024Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading ScenariosarXiv 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge CollaborationarXiv 2024Deep Learning Model Reuse in the HuggingFace Community: Challenges, Benefit and TrendsarXiv 2024Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix ItarXiv 2024Deploying Large Language Models With Retrieval Augmented GenerationarXiv 2024Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal ModelsarXiv 2024Assessing Demographic Bias in Named Entity RecognitionarXiv 2020Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation MetricarXiv 2024BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem SolvingarXiv 2024Fine-Tuning Large Language Models for Scientific Text Classification: A Comparative StudyarXiv 2024COLD: Causal reasOning in cLosed Daily activitiesarXiv 2024Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled RepresentationsarXiv 2024The Virtues of Laziness in Model-based RL: A Unified Objective and AlgorithmsarXiv 2023T-REG: Preference Optimization with Token-Level Reward RegularizationarXiv 2024Online Matching: A Real-time Bandit System for Large-scale
RecommendationsarXiv 2023Provably Learning Diverse Features in Multi-View Data with Midpoint MixuparXiv 2022Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong ConvexityarXiv 2023Randomized Quantization is All You Need for Differential Privacy in Federated LearningarXiv 2023Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsarXiv 2024LDC: Learning to Generate Research Idea with Dynamic ControlarXiv 2024The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data OnlyarXiv 2023Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence SimilarityarXiv 2023Understanding the Impact of Confidence in Retrieval Augmented Generation: A Case Study in the Medical DomainarXiv 2024UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual PretrainingarXiv 2023Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning FrameworkarXiv 2025Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning InterfacearXiv 2025How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven FeedbackarXiv 2025Scaling Inference-Efficient Language ModelsarXiv 2025Optimizing Neural Network Hyperparameters with Gaussian Processes for Dialog Act ClassificationarXiv 2016Inverse Bridge Matching DistillationarXiv 2025Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language ModelsarXiv 2023Generalized-Smooth Nonconvex Optimization is As Efficient As Smooth
Nonconvex OptimizationarXiv 2023Token Assorted: Mixing Latent and Text Tokens for Improved Language Model ReasoningarXiv 2025What the Harm? Quantifying the Tangible Impact of Gender Bias in Machine Translation with a Human-centered StudyarXiv 2024X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment
Vision-Language-Action ModelarXiv 2025Quantum Policy Gradient Algorithm with Optimized Action DecodingarXiv 2022Inverse Scaling in Test-Time ComputearXiv 2025QFFT, Question-Free Fine-Tuning for Adaptive ReasoningarXiv 2025Should We Still Pretrain Encoders with Masked Language Modeling?arXiv 2025HLFormer: Enhancing Partially Relevant Video Retrieval with Hyperbolic LearningICCV 2025S$^2$-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion ModelsarXiv 2025What Makes a Good Natural Language Prompt?arXiv 2025Mathesis: Towards Formal Theorem Proving from Natural LanguagesarXiv 2025LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-TuningarXiv 2025Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought RewardarXiv 2025RSRefSeg 2: Decoupling Referring Remote Sensing Image Segmentation with Foundation ModelsarXiv 2025UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding LearningarXiv 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference
LearningarXiv 2025DBConformer: Dual-Branch Convolutional Transformer for EEG DecodingarXiv 2025Flow-Anchored Consistency ModelsarXiv 2025RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy OptimizationarXiv 2025DiffuCoder: Understanding and Improving Masked Diffusion Models for Code GenerationarXiv 2025ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarksarXiv 2025The Denario project: Deep knowledge AI agents for scientific discoveryarXiv 2025OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic WorkflowsarXiv 2025Skywork-R1V3 Technical ReportarXiv 2025Scaling Instruction-Based Video Editing with a High-Quality Synthetic
DatasetarXiv 2025Being-H0: Vision-Language-Action Pretraining from Large-Scale Human VideosarXiv 2025FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion TransformersarXiv 2025CharaConsist: Fine-Grained Consistent Character GenerationICCV 2025LongCodeZip: Compress Long Context for Code Language ModelsarXiv 2025Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level ComputationarXiv 2025GEM: A Gym for Agentic LLMsarXiv 2025Valori: A Deterministic Memory Substrate for AI SystemsarXiv 2025ComboStoc: Combinatorial Stochasticity for Diffusion Generative ModelsarXiv 2026How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public CompetitionarXiv 2026Distribution Matching Distillation Meets Reinforcement LearningarXiv 2025Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPOarXiv 2025SARAH: Spatially Aware Real-time Agentic HumansarXiv 2026Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual GenerationarXiv 2025PointWorld: Scaling 3D World Models for In-The-Wild Robotic ManipulationarXiv 2026Beyond Fixed Frames: Dynamic Character-Aligned Speech TokenizationarXiv 2026Pillar-0: A New Frontier for Radiology Foundation ModelsarXiv 2025JustRL: Scaling a 1.5B LLM with a Simple RL RecipearXiv 2025QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory ManagementarXiv 2025STEP3-VL-10B Technical ReportarXiv 2026SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement LearningarXiv 2025An Empirical Recipe for Universal Phone RecognitionarXiv 2026AgentOCR: Reimagining Agent History via Optical Self-CompressionarXiv 2026Small Vision-Language Models are Smart Compressors for Long Video UnderstandingarXiv 2026SciEvalKit: An Open-source Evaluation Toolkit for Scientific General IntelligencearXiv 2025Latent Collaboration in Multi-Agent SystemsarXiv 2025Uni-Edit: Intelligent Editing Is A General Task For Unified Model TuningarXiv 2026Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?arXiv 2026Probing Scientific General Intelligence of LLMs with Scientist-Aligned WorkflowsarXiv 2025Track4World: Feedforward World-centric Dense 3D Tracking of All PixelsarXiv 2026AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep ResearcharXiv 2026Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and EditingarXiv 2026When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal ReasoningarXiv 2026PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context InferencearXiv 2026Your Agent, Their Asset: A Real-World Safety Analysis of OpenClawarXiv 2026WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPGarXiv 2026PyVision-RL: Forging Open Agentic Vision Models via RLarXiv 2026KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge GuidancearXiv 2026Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary EnvironmentsarXiv 2026Free Geometry: Refining 3D Reconstruction from Longer Versions of ItselfarXiv 2026Next-Embedding Prediction Makes Strong Vision LearnersarXiv 2025NitroGen: An Open Foundation Model for Generalist Gaming AgentsarXiv 2026Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World ModelsarXiv 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent SystemsarXiv 2026DreamWorld: Unified World Modeling in Video GenerationarXiv 2026Toward Autonomous Long-Horizon Engineering for ML ResearcharXiv 2026SWE-Pruner: Self-Adaptive Context Pruning for Coding AgentsarXiv 2026TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-trainingarXiv 2026NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding AgentsarXiv 2025DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and EditingarXiv 2026WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric MemoriesarXiv 2026Any4D: Unified Feed-Forward Metric 4D ReconstructionarXiv 2025Let ViT Speak: Generative Language-Image Pre-trainingarXiv 2026Dr. Zero: Self-Evolving Search Agents without Training DataarXiv 2026ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics AlignmentarXiv 2026Echo-Forcing: A Scene Memory Framework for Interactive Long Video GenerationarXiv 2026Step-GUI Technical ReportarXiv 2025RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator FrameworkarXiv 2026tttLRM: Test-Time Training for Long Context and Autoregressive 3D ReconstructionarXiv 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval InterfacesarXiv 2026Interpreting CLIP with Hierarchical Sparse AutoencodersarXiv 2025Efficient Test-Time Scaling via Self-CalibrationarXiv 2025