Showing 1–20 of 20 results
/ Date/ Name
Mar 28, 2026Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and CompressionDec 23, 2025CHAMMI-75: Pre-training multi-channel models with heterogeneous microscopy imagesDec 11, 2025Mull-Tokens: Modality-Agnostic Latent ThinkingMar 17, 2025Web Artifact Attacks Disrupt Vision Language ModelsDec 10, 2024SAT: Dynamic Spatial Aptitude Training for Multimodal Language ModelsDec 22, 2023UniHuman: A Unified Model for Editing Human Images in the WildDec 3, 2023Learning to Compose SuperWeights for Neural Parameter Allocation SearchNov 30, 2023A Unified Framework for Connecting Noise Modeling to Boost Noise DetectionNov 7, 2023MixtureGrowth: Growing Neural Networks by Recombining Learned ParametersOct 30, 2023CHAMMI: A benchmark for channel-adaptive models in microscopy imagingAug 8, 2023From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image RecognitionMar 28, 2023Language-Guided Audio-Visual Source Separation via Trimodal ConsistencyJul 26, 2022NewsStories: Illustrating articles with visual summariesMar 24, 2022Complex Scene Image Editing by Scene Graph ComprehensionApr 17, 2021Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual EnvironmentsSep 8, 2019MULE: Multimodal Universal Language EmbeddingAug 17, 2019Language Features Matter: Effective Language Representations for Vision-Language TasksMay 26, 2019Why do These Match? Explaining the Behavior of Image Similarity ModelsNov 17, 2018Revisiting Image-Language Networks for Open-ended Phrase DetectionSep 24, 2018Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback