| SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs | Feb 17, 2025 | parameter-efficient fine-tuning | CodeCode Available | 2 | 5 |
| High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net | Aug 27, 2023 | Document Shadow RemovalImage Shadow Removal | CodeCode Available | 2 | 5 |
| Color Shift Estimation-and-Correction for Image Enhancement | May 28, 2024 | Exposure CorrectionImage Enhancement | CodeCode Available | 2 | 5 |
| Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching | May 22, 2023 | AllFew-Shot Semantic Segmentation | CodeCode Available | 2 | 5 |
| Dirichlet Flow Matching with Applications to DNA Sequence Design | Feb 8, 2024 | | CodeCode Available | 2 | 5 |
| ViewFusion: Towards Multi-View Consistency via Interpolated Denoising | Feb 29, 2024 | DenoisingImage Generation | CodeCode Available | 2 | 5 |
| M3: 3D-Spatial MultiModal Memory | Mar 20, 2025 | Feature Splatting | CodeCode Available | 2 | 5 |
| Sparse Instance Activation for Real-Time Instance Segmentation | Mar 24, 2022 | Instance SegmentationObject | CodeCode Available | 2 | 5 |
| Transformers are Sample-Efficient World Models | Sep 1, 2022 | Atari Games 100kDeep Reinforcement Learning | CodeCode Available | 2 | 5 |
| Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era | May 5, 2025 | SurveyTime Series | CodeCode Available | 2 | 5 |
| A Judge-free LLM Open-ended Generation Benchmark Based on the Distributional Hypothesis | Feb 13, 2025 | Text Generation | CodeCode Available | 2 | 5 |
| AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition | May 26, 2022 | Action RecognitionVideo Recognition | CodeCode Available | 2 | 5 |
| An Egocentric Vision-Language Model based Portable Real-time Smart Assistant | Mar 6, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 2 | 5 |
| Fourier Neural Operator for Parametric Partial Differential Equations | Oct 18, 2020 | Super-Resolution | CodeCode Available | 2 | 5 |
| LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models | Mar 20, 2024 | Language ModelingLanguage Modelling | CodeCode Available | 2 | 5 |
| UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning | May 29, 2025 | | CodeCode Available | 2 | 5 |
| Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time | Mar 10, 2022 | Domain Generalization | CodeCode Available | 2 | 5 |
| GraphMAE: Self-Supervised Masked Graph Autoencoders | May 22, 2022 | Contrastive LearningGraph Classification | CodeCode Available | 2 | 5 |
| PET-MAD, a universal interatomic potential for advanced materials modeling | Mar 18, 2025 | Diversity | CodeCode Available | 2 | 5 |
| BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning | Oct 18, 2018 | Grounded language learning | CodeCode Available | 2 | 5 |
| BTS: Building Timeseries Dataset: Empowering Large-Scale Building Analytics | Jun 13, 2024 | Benchmarking | CodeCode Available | 2 | 5 |
| MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses | Oct 9, 2024 | scientific discoveryvalid | CodeCode Available | 2 | 5 |
| Source-Free Domain Adaptation with Frozen Multimodal Foundation Model | Nov 27, 2023 | Domain AdaptationPrompt Learning | CodeCode Available | 2 | 5 |
| CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers | Jan 3, 2024 | Point Cloud Completion | CodeCode Available | 2 | 5 |
| TimeLMs: Diachronic Language Models from Twitter | Feb 8, 2022 | Continual LearningLanguage Modeling | CodeCode Available | 2 | 5 |
| string2string: A Modern Python Library for String-to-String Algorithms | Apr 27, 2023 | | CodeCode Available | 2 | 5 |
| Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite | Sep 15, 2023 | Question Answering | CodeCode Available | 2 | 5 |
| Spectrally Pruned Gaussian Fields with Neural Compensation | May 1, 2024 | | CodeCode Available | 2 | 5 |
| BIG-Bench Extra Hard | Feb 26, 2025 | | CodeCode Available | 2 | 5 |
| What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective | Oct 31, 2024 | | CodeCode Available | 2 | 5 |
| Chain of Hindsight Aligns Language Models with Feedback | Feb 6, 2023 | | CodeCode Available | 2 | 5 |
| MiraGe: Editable 2D Images using Gaussian Splatting | Oct 2, 2024 | | CodeCode Available | 2 | 5 |
| Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends | Jul 31, 2024 | coreference-resolutionCoreference Resolution | CodeCode Available | 2 | 5 |
| Vision-aided UAV navigation and dynamic obstacle avoidance using gradient-based B-spline trajectory optimization | Sep 15, 2022 | Navigate | CodeCode Available | 2 | 5 |
| Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences | Apr 11, 2024 | AnatomySegmentation | CodeCode Available | 2 | 5 |
| A Novel State Space Model with Local Enhancement and State Sharing for Image Fusion | Apr 14, 2024 | MambaPansharpening | CodeCode Available | 2 | 5 |
| The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models | Jul 25, 2024 | | CodeCode Available | 2 | 5 |
| Spiking Diffusion Models | Aug 29, 2024 | Image Generation | CodeCode Available | 2 | 5 |
| Putting People in their Place: Monocular Regression of 3D People in Depth | Dec 15, 2021 | 3D Depth Estimationregression | CodeCode Available | 2 | 5 |
| MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance | May 28, 2024 | | CodeCode Available | 2 | 5 |
| PnLCalib: Sports Field Registration via Points and Lines Optimization | Apr 12, 2024 | Camera CalibrationHomography Estimation | CodeCode Available | 2 | 5 |
| XHand: Real-time Expressive Hand Avatar | Jul 30, 2024 | | CodeCode Available | 2 | 5 |
| FedGraph: A Research Library and Benchmark for Federated Graph Learning | Oct 8, 2024 | BenchmarkingFederated Learning | CodeCode Available | 2 | 5 |
| UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation | Aug 15, 2023 | 3D Object DetectionAutonomous Driving | CodeCode Available | 2 | 5 |
| ZenSVI: An Open-Source Software for the Integrated Acquisition, Processing and Analysis of Street View Imagery Towards Scalable Urban Science | Dec 24, 2024 | | CodeCode Available | 2 | 5 |
| ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design | Sep 26, 2023 | Mutational/Variant Effect Prediction | CodeCode Available | 2 | 5 |
| Editing Models with Task Arithmetic | Dec 8, 2022 | NegationTask Arithmetic | CodeCode Available | 2 | 5 |
| Learning Video Representations from Large Language Models | Dec 8, 2022 | Action ClassificationAction Recognition | CodeCode Available | 2 | 5 |
| Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives | Nov 30, 2023 | Video Understanding | CodeCode Available | 2 | 5 |
| Model-free quantification of completeness, uncertainties, and outliers in atomistic machine learning using information theory | Apr 18, 2024 | Active LearningUncertainty Quantification | CodeCode Available | 2 | 5 |