1 | Andrea Santillihttps://www.santilli.xyz/publication-type/1/1Wowchemy (https://wowchemy.com)en-usSat, 01 Nov 2025 00:00:00 +0000https://www.santilli.xyz/media/icon_hu2de582bf2cbe6aeaf3734397f2d741cf_526_512x512_fill_lanczos_center_3.png1https://www.santilli.xyz/publication-type/1/Language Models are Injective and Hence Invertiblehttps://www.santilli.xyz/publication/pringle/Sat, 01 Nov 2025 00:00:00 +0000https://www.santilli.xyz/publication/pringle/Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Resultshttps://www.santilli.xyz/publication/spurious_acl2025/Tue, 01 Jul 2025 00:00:00 +0000https://www.santilli.xyz/publication/spurious_acl2025/Mergenetic: a Simple Evolutionary Model Merging Libraryhttps://www.santilli.xyz/publication/mergenetic_acl2025/Sun, 01 Jun 2025 00:00:00 +0000https://www.santilli.xyz/publication/mergenetic_acl2025/MERGE3: Efficient Evolutionary Merging on Consumer-grade GPUshttps://www.santilli.xyz/publication/merge3/Thu, 01 May 2025 00:00:00 +0000https://www.santilli.xyz/publication/merge3/Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaceshttps://www.santilli.xyz/publication/plato/Sat, 01 Feb 2025 00:00:00 +0000https://www.santilli.xyz/publication/plato/Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutionshttps://www.santilli.xyz/publication/privacy/Wed, 01 Jan 2025 00:00:00 +0000https://www.santilli.xyz/publication/privacy/Camoscio: An italian instruction-tuned llamahttps://www.santilli.xyz/publication/camoscio/Tue, 01 Aug 2023 00:00:00 +0000https://www.santilli.xyz/publication/camoscio/Accelerating Transformer Inference for Translation via Parallel Decodinghttps://www.santilli.xyz/publication/ipi/Mon, 08 May 2023 00:00:00 +0000https://www.santilli.xyz/publication/ipi/Multimodal Neural Databaseshttps://www.santilli.xyz/publication/mmndb/Sun, 07 May 2023 00:00:00 +0000https://www.santilli.xyz/publication/mmndb/Latent Autoregressive Source Separationhttps://www.santilli.xyz/publication/postolache-2023-latent/Sun, 01 Jan 2023 00:00:00 +0000https://www.santilli.xyz/publication/postolache-2023-latent/Multitask Prompted Training Enables Zero-Shot Task Generalizationhttps://www.santilli.xyz/publication/multitask-prompted-training-enables-zero-shot-task-generalization/Wed, 29 Sep 2021 00:00:00 +0000https://www.santilli.xyz/publication/multitask-prompted-training-enables-zero-shot-task-generalization/KERMIT: Complementing Transformer Architectures with Encoders of Explicit Syntactic Interpretationshttps://www.santilli.xyz/publication/kermit-complementing-transformer-architectures-with-encoders-of-explicit-syntactic-interpretations/Wed, 10 Jun 2020 00:00:00 +0000https://www.santilli.xyz/publication/kermit-complementing-transformer-architectures-with-encoders-of-explicit-syntactic-interpretations/A Kernel-based Approach for Irony and Sarcasm Detection in Italianhttps://www.santilli.xyz/publication/a-kernel-based-approach-for-irony-and-sarcasm-detection-in-italian/Wed, 10 Oct 2018 00:00:00 +0000https://www.santilli.xyz/publication/a-kernel-based-approach-for-irony-and-sarcasm-detection-in-italian/SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptronshttps://www.santilli.xyz/publication/syntnn-at-semeval-2018-task-2-is-syntax-useful-for-emoji-prediction-embedding-syntactic-trees-in-multi-layer-perceptrons/Mon, 25 Jun 2018 00:00:00 +0000https://www.santilli.xyz/publication/syntnn-at-semeval-2018-task-2-is-syntax-useful-for-emoji-prediction-embedding-syntactic-trees-in-multi-layer-perceptrons/