Showing 1–20 of 22 results
/ Date/ Name
Aug 29, 2023Uncovering the Hidden Cost of Model CompressionJul 16, 2025GitChameleon 2.0: Evaluating AI Code Generation Against Python Library Version IncompatibilitiesMar 15, 2024On the low-shot transferability of [V]-MambaJul 14, 2025(Almost) Free Modality Stitching of Foundation ModelsApr 4, 2022APP: Anytime Progressive PruningMar 19, 2024Using Shapley interactions to understand how models use structureOct 6, 2020Rotate to Attend: Convolutional Triplet Attention ModuleAug 23, 2019Mish: A Self Regularized Non-Monotonic Activation FunctionNov 5, 2024GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation ModelsDec 23, 2018Image Processing on IOPA Radiographs: A comprehensive case study on Apical PeriodontitisFeb 6, 2026Explaining Grokking in Transformers through the Lens of Inductive BiasJul 10, 2022Challenging Common Assumptions about Catastrophic ForgettingMay 30, 2024Slight Corruption in Pre-training Data Makes Better Diffusion ModelsMar 1, 2026Agents Learn Their Runtime: Interpreter Persistence as Training-Time SemanticsDec 23, 2018Advanced Image Processing for Astronomical ImagesJul 20, 2024Consent in Crisis: The Rapid Decline of the AI Data CommonsDec 19, 2024Bridging the Data Provenance Gap Across Text, Speech and VideoFeb 19, 2025MMTEB: Massive Multilingual Text Embedding BenchmarkMar 30, 2024Aurora-M: Open Source Continual Pre-training for Multilingual Language and CodeJun 9, 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models