Preprint2026
World models for robotic manipulation: A survey
Unknown
A survey of world models for robotic manipulation, tracing their evolution from task-specific predictors toward more general and capable systems.
0Jan 1, 2026
AI Research
AI & ML Research Papers
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
All Papers
16 papersPreprint2026
Foundation models in biomedical imaging: turning hype into reality
Unknown
This paper examines how foundation models are shifting biomedical imaging from task-specific models to unified backbones, and what it will take to turn the hype into clinical reality.
0Jan 1, 2026
Preprint2026
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
Siting Li, Zhengyang Wang, Simon Shaolei Du, et al.
A controlled autoregressive testbed shows image tokenizers act as visual languages, with task-specific losses revealing distinct scaling and downstream links.
0Sep 8, 2026MultimodalScaling Laws
arXiv
Preprint2026
Common task framework for a critical evaluation of scientific machine learning algorithms
Unknown
The paper introduces a Common Task Framework (CTF) for scientific machine learning, featuring curated datasets and task-specific metrics to enable critical evaluation of algorithms.
0Jan 1, 2026
Preprint2024
Mtlora: A low-rank adaptation approach for efficient multi-task learning
Unknown
This paper introduces Mtlora, a low-rank adaptation approach for efficient multi-task learning, with novel task-agnostic and task-specific modules applied to vision patch-merging layers.
0Jan 1, 2024Computer Vision
Preprint2026
Foundation Models for Medical Imaging: Status, Challenges, and Directions
Unknown
This paper surveys the status, challenges, and future directions of foundation models in medical imaging, contextualizing their shift from task-specific models.
0Feb 1, 2026
arXiv
ConferenceInternational Conference on Machine Learning2025
Text-to-LoRA
Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, et al.
Text-to-LoRA (T2L) is a hypernetwork that generates task-specific LoRA adapters for LLMs from a natural language description in a single forward pass, matching performance of individually trained adapters.
40Jun 6, 2025Large Language ModelsFine Tuning
arXiv
Preprint2023
Orca 2
Unknown
Orca 2 introduces Cautious Reasoning to train smaller models to select effective solution strategies via task-specific system instructions.
0Nov 1, 2023ReasoningInstruction Tuning
ConferenceInfoscience (Ecole Polytechnique Fédérale de Lausanne)2011Featured
Natural Language Processing (almost) from Scratch
Ronan Collobert, Jason Weston, Léon Bottou, et al.
A unified neural network architecture that learns internal representations from unlabelled data achieves state-of-the-art on multiple NLP tasks without task-specific feature engineering.
7.9kMar 2, 2011BenchmarksNeural Networks
arXiv
PreprintJournal of the American Medical Informatics Association2024
Improving large language models for clinical named entity recognition via prompt engineering
Yan Hu, Qingyu Chen, Jingcheng Du, et al.
This paper shows that task-specific prompt engineering, incorporating medical knowledge and few-shot examples, significantly improves GPT-3.5 and GPT-4 performance on clinical NER tasks, though still below BioClinicalBERT.
364Jan 27, 2024Large Language ModelsPrompting
PreprintarXiv.org2024
Jina Embeddings v3
Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, et al.
Jina Embeddings v3 is a 570M parameter multilingual embedding model supporting 8192-token contexts, task-specific LoRA adapters, and flexible dimension reduction via Matryoshka learning.
175Sep 1, 2024Retrieval Augmented Generation
arXiv
Preprint2019
CTRL
Unknown
A 1.63B parameter language model that uses control codes to explicitly govern style, content, and task-specific behavior during text generation.
0Sep 1, 2019