Transform Concepts

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 17

All topics

On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D
Sep 30, 2026Fabio J. Fehr, Philip TorrHypernetwork Model Weights
University of Oxford
Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
Sep 30, 2026Yue YU, Bowen Zuo, David Crandall +2Diffusion Language Models Large Language Model Reinforcement Learning
Indiana University · University of California, Riverside
Simultaneous Neural Optimal Transport
Sep 29, 2026Milena Gazdieva, Kirill Sokolov, Jiawei Chen +2Optimal Transport Approach Image Restoration
Applied AI Institute AXXX Moscow, Russia · Lomonosov Moscow State University Moscow, Russia · MIRIAI Moscow, Russia
MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies
Sep 22, 2026Elie Abboud, Oren GalMulti-Agent Reinforcement Learning Multi-Agent Communication
department of Marine Technologies, University of Haifa, Israel · Department of Marine Technologies, University of Haifa, Israel
Transformation Laws in Neural Representations: Structure, Realisability, and Construction
Sep 16, 2026Yuan SunNeural Representations Transform Concepts
School of Mathematical Sciences, Beijing Normal University, Beijing 100875, China
Can Deep Learning Achieve Cross-Physics Mapping?
Sep 15, 2026Pengfei Zhu, Julien Lecompagnon, Mathias ZieglerScalar Field Deep Learning
Bundesanstalt für Materialforschung and -prüfung (BAM), 12205 Berlin, Germany
LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances
Sep 7, 2026Vamsi Krishna Kodavali, Rituraj SinghCharacter Error Rate Multiple-Choice Questions
Samsung
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Aug 10, 2026Björn Engdahl, Adrian Kosowski, Jan Chorowski +6Efficient Latent Reasoning Large Reasoning Models
New York University
How Far Do Simple Transformations Translate Across Text Embedding Models?
Aug 6, 2026Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin +1Text Embeddings Transform Concepts
Orange Research · Orange
Language Models Represent and Transform Concepts with Shared Geometry
Jul 5, 2026Zhimin Hu, Lanhao Niu, Sashank VarmaLanguage Modeling Transform Concepts
1Georgia Institute of Technology · University of Edinburgh
Transformation Behavior of Images in Latent Space
Jun 23, 2026Christian Zöllner, Mozzam Motiwala, Aysel Ahadova +4Digital Pathology Transform Concepts
Department of Applied Tumor Biology Institute of Pathology Heidelberg University Hospital · Department of Applied Tumor Biology, Institute of Pathology, Heidelberg University Hospital, Im Neuenheimer Feld 224, 69120, Heidelberg, Germany · National Center for Hereditary Tumor Syndromes, University Hospital Bonn, Venusberg-Campus 1, 53127, Bonn, Germany +5
Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models
Jun 22, 2026Junrong Huang, Zhiyuan Zhang, Rui Tang +2Diffusion Transformers Texture
City University of Hong Kong, China · Manycore Tech Inc., China · Hong Kong University of Science and Technology, China
Does Text Actually Help? Uncovering and Resolving Text Collapse in Multimodal Time Series Forecasting
Jun 17, 2026Huu Hiep Nguyen, Minh Hoang Nguyen, Dung Nguyen +1Time Series Forecasting Representation Collapse
Applied Artificial Intelligence Initiative Deakin University Geelong, Australia
ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization
Jun 11, 2026Aitor Sánchez-Ferrera, Elisabeth Wetzer, Kristoffer Wickstrøm +2Time-Series Anomaly Detection Transform Concepts
aDepartment of Computer Science and Artificial Intelligence, University of the Basque Country UPV/EHU, Donostia, Spain · bDepartment of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway
Harness In-Context Operator Learning with Chain of Operators
Jun 10, 2026Minghui Yang, Ling Guo, Liu YangLogical Connectives In-Context Learning
Department of Mathematics, Shanghai Normal University, Shanghai, China · Department of Mathematics, National University of Singapore, Singapore
From I/O to Code with Discovery Agent
May 14, 2026Yihong Dong, Jiaru Qian, Haoran Zhang +7Llm-Driven Code Synthesis Transform Concepts
School of Computer Science, Peking University · Tongyi Lab, Alibaba Group · Wuhan University +3
Multi-Narrow Transformation as a Single-Model Ensemble: Boundary Conditions, Mechanisms, and Failure Modes
May 12, 2026Tatsuhito Hasegawa, Taisei TanakaCnn-Transformer Tradeoff Ensemble
Graduate School of Engineering, University of Fukui, Bunkyo, Fukui, 9108507, Fukui, Japan

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

On-the-fly Weight Generation: A Hypernetwork Proof of Concept on ARC-1D

Fabio J. Fehr, Philip Torr

University of Oxford

Hypernetwork Model Weights Few-Shot Learning Generative Architectures Improved Generalization Compositional Generalization+1

Open paper AskPDF arXiv

General-purpose models can adapt to many tasks from context, while specialised models can execute individual functions with less capacity. Yet obtaining such specialists requires task-specific training or adaptation. We ask whether they can instead be generated directly from a few demonstrations. Using ARC-1D as a controlled testbed, we show that individual transformations can be represented by tiny specialist models, and that a hypernetwork can generate their parameters from context. The generated parameters form a structured weight space, while the resulting specialists show partial compositional generalisation and generalisation to transformations not seen during training. In both settings, removing explicit task identifiers improves generalisation beyond the training transformations. Together, these results provide a proof of concept that few-shot task context can be compiled on-the-fly into compact executable model parameters, and that the resulting weight space can support reuse and generalisation beyond known functions.

Momentum

Related topics

Latest papers 17