{"metadata":{"name":"Neural Compilation and Fuzzy-Function Programming","version":"1.2.0","updated_at":"2026-10-19","search_refreshed_at":"2026-10-19","core_record_count":13,"canonical_url":"https://programasweights.com/reading-list/","navigation_url":"https://programasweights.com/reading-list/data/navigation.json","citation_policy":"papers.bib and papers.csl.json contain arXiv citations. publications.bib and publications.csl.json contain conference and journal citations."},"papers":[{"id":"1511.06279","title":"Neural Programmer-Interpreters","authors":"Scott Reed, Nando de Freitas","first_public":"2015-11-19","first_public_source":"https://arxiv.org/abs/1511.06279","arxiv_first_submission":"2015-11-19","date_label":"arXiv v1","arxiv":"1511.06279","paper_url":"https://arxiv.org/abs/1511.06279","venue":"ICLR 2016","lens":["neural-programs"],"related_terms":["neural programmer-interpreter","neural programs","program memory","compositional execution"],"summary":"Learns neural programs that share a recurrent interpreter and a program memory.","contribution":"Learns from execution traces and composes subprograms for addition, sorting, and 3D-object canonicalization.","limitations":"Training requires execution traces and task-specific interfaces.","program_form":"Program embeddings stored in a key-value memory.","conditioning":"A program identifier, arguments, and observations of the environment.","execution":"A recurrent interpreter calls subprograms and takes actions in the environment.","relationship":"PAW cites this work on learned program representations and shared interpreters.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Scott Reed","Nando de Freitas"],"record_url":"https://programasweights.com/reading-list/papers/1511.06279/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-1511-06279","citation_date":"2015-11-19","json_url":"https://programasweights.com/reading-list/papers/1511.06279/record.json","markdown_url":"https://programasweights.com/reading-list/papers/1511.06279/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/1511.06279/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/1511.06279/citation.csl.json","publication":{"title":"Neural Programmer-Interpreters","author_names":["Scott Reed","Nando de Freitas"],"year":2016,"type":"paper-conference","container_title":"International Conference on Learning Representations","url":"https://arxiv.org/abs/1511.06279","source_url":"https://arxiv.org/pdf/1511.06279","verified_at":"2026-10-19","source_note":"The paper PDF identifies ICLR 2016; the conference program confirms the presentation."},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/1511.06279/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/1511.06279/publication.csl.json"},{"id":"1609.09106","title":"HyperNetworks","authors":"David Ha, Andrew Dai, Quoc V. Le","first_public":"2016-09-27","first_public_source":"https://arxiv.org/abs/1609.09106","arxiv_first_submission":"2016-09-27","date_label":"arXiv v1","arxiv":"1609.09106","paper_url":"https://arxiv.org/abs/1609.09106","venue":"ICLR 2017","lens":["generated-adapters"],"related_terms":["hypernetwork","weight generation","fast weights","conditional parameters"],"summary":"Uses one neural network to generate the weights of another.","contribution":"Applies weight generation to convolutional and recurrent networks, relaxing weight sharing across layers and generating dynamic weights for sequence models.","limitations":"The hypernetwork is trained end to end for the target architecture.","program_form":"Weights for the target network.","conditioning":"Layer embeddings or the current recurrent state.","execution":"The target network runs with the generated weights.","relationship":"Provides the weight-generation mechanism used by later description-to-adapter methods and PAW.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["David Ha","Andrew Dai","Quoc V. Le"],"record_url":"https://programasweights.com/reading-list/papers/1609.09106/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-1609-09106","citation_date":"2016-09-27","json_url":"https://programasweights.com/reading-list/papers/1609.09106/record.json","markdown_url":"https://programasweights.com/reading-list/papers/1609.09106/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/1609.09106/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/1609.09106/citation.csl.json","publication":{"title":"HyperNetworks","author_names":["David Ha","Andrew M. Dai","Quoc V. Le"],"year":2017,"type":"paper-conference","container_title":"International Conference on Learning Representations","url":"https://openreview.net/forum?id=rkpACe1lx","source_url":"https://openreview.net/pdf?id=rkpACe1lx","verified_at":"2026-10-19"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/1609.09106/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/1609.09106/publication.csl.json"},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","authors":"Xiang Lisa Li, Percy Liang","first_public":"2021-01-01","first_public_source":"https://arxiv.org/abs/2101.00190","arxiv_first_submission":"2021-01-01","date_label":"arXiv v1","arxiv":"2101.00190","paper_url":"https://arxiv.org/abs/2101.00190","venue":"ACL-IJCNLP 2021","lens":["peft"],"related_terms":["prefix-tuning","continuous prompts","virtual tokens","parameter-efficient fine-tuning"],"summary":"Adapts a frozen language model by learning a short sequence of continuous prefix vectors.","contribution":"Trains prefixes for table-to-text generation and summarization while updating far fewer parameters than full fine-tuning.","limitations":"A separate prefix is optimized for each task.","program_form":"Continuous prefix activations.","conditioning":"Training examples for the target task.","execution":"The frozen language model attends to the learned prefix.","relationship":"PAW evaluates compiler-generated prefixes alongside LoRA adapters.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Xiang Lisa Li","Percy Liang"],"record_url":"https://programasweights.com/reading-list/papers/2101.00190/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2101-00190","citation_date":"2021-01-01","json_url":"https://programasweights.com/reading-list/papers/2101.00190/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2101.00190/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2101.00190/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2101.00190/citation.csl.json","publication":{"title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","author_names":["Xiang Lisa Li","Percy Liang"],"year":2021,"type":"paper-conference","container_title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","url":"https://aclanthology.org/2021.acl-long.353/","source_url":"https://aclanthology.org/2021.acl-long.353/","verified_at":"2026-10-19","doi":"10.18653/v1/2021.acl-long.353","publisher":"Association for Computational Linguistics","pages":"4582-4597"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2101.00190/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2101.00190/publication.csl.json","method_comparisons":[{"title":"Program form and compiler","text":"LoRA represents adaptation as low-rank weight updates; prefix tuning uses continuous activations. Their original methods learn these parameters from examples. PAW generates both forms from specifications.","source_ids":["2106.09685","2101.00190","2607.02512"],"source_urls":["https://arxiv.org/abs/2106.09685","https://aclanthology.org/2021.acl-long.353/","https://arxiv.org/html/2607.02512v1#S3"],"source_labels":["LoRA paper","Prefix-tuning paper","PAW implementations"],"topic_id":"peft","topic_label":"Parameter-efficient building blocks","topic_url":"https://programasweights.com/reading-list/guides/compilation/#peft"}]},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","authors":"Qinyuan Ye, Xiang Ren","first_public":"2021-01-02","first_public_source":"https://arxiv.org/abs/2101.00420","arxiv_first_submission":"2021-01-02","date_label":"arXiv v1","arxiv":"2101.00420","paper_url":"https://arxiv.org/abs/2101.00420","venue":"ACL-IJCNLP 2021","lens":["generated-adapters"],"related_terms":["Hypter","task descriptions","generated adapters","zero-shot learning"],"summary":"Introduces Hypter, which generates adapters from natural-language task descriptions.","contribution":"Combines a description encoder and adapter generator with BART. Tests generalization to unseen tasks on ZEST and synthetic SQuAD.","limitations":"Training requires a collection of tasks with descriptions and labeled examples.","program_form":"Bottleneck adapters inserted into a text-to-text model.","conditioning":"A natural-language task description.","execution":"BART performs the task with the generated adapters.","relationship":"An early description-to-adapter method cited by PAW. PAW develops the programming interface for saving and calling the resulting neural functions.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Qinyuan Ye","Xiang Ren"],"record_url":"https://programasweights.com/reading-list/papers/2101.00420/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2101-00420","citation_date":"2021-01-02","json_url":"https://programasweights.com/reading-list/papers/2101.00420/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2101.00420/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2101.00420/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2101.00420/citation.csl.json","publication":{"title":"Learning to Generate Task-Specific Adapters from Task Description","author_names":["Qinyuan Ye","Xiang Ren"],"year":2021,"type":"paper-conference","container_title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)","url":"https://aclanthology.org/2021.acl-short.82/","source_url":"https://aclanthology.org/2021.acl-short.82/","verified_at":"2026-10-19","doi":"10.18653/v1/2021.acl-short.82","publisher":"Association for Computational Linguistics","pages":"646-653"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2101.00420/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2101.00420/publication.csl.json","method_comparisons":[{"title":"From generated adapters to reusable functions","text":"Hypter, HINT, HyperTuning, and Text-to-LoRA generate adaptations from descriptions or examples. PAW uses generated parameters as part of a program that can be saved, called from ordinary code, and reused by a fixed interpreter.","source_ids":["2101.00420","2212.10315","2211.12485","2506.06105","2607.02512"],"source_urls":["https://arxiv.org/html/2607.02512v1#S10","https://proceedings.mlr.press/v267/charakorn25a.html"],"source_labels":["PAW related work","Text-to-LoRA paper"],"topic_id":"generated-adapters","topic_label":"Generated weights and adapters","topic_url":"https://programasweights.com/reading-list/guides/compilation/#generated-adapters"}]},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","authors":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen","first_public":"2021-06-17","first_public_source":"https://arxiv.org/abs/2106.09685","arxiv_first_submission":"2021-06-17","date_label":"arXiv v1","arxiv":"2106.09685","paper_url":"https://arxiv.org/abs/2106.09685","venue":"ICLR 2022","lens":["peft"],"related_terms":["LoRA","low-rank adaptation","parameter-efficient fine-tuning","adapters"],"summary":"Adapts a pretrained model with low-rank weight updates while keeping the original weights fixed.","contribution":"Reduces the parameters trained and stored for each task. Evaluates adaptation across several language-model families.","limitations":"A separate adapter is trained for each task.","program_form":"Low-rank matrices that update selected model weights.","conditioning":"Training examples for the target task.","execution":"The language model applies the low-rank updates during inference.","relationship":"PAW uses LoRA as a program representation and generates the adapter with a trained compiler.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Edward J. Hu","Yelong Shen","Phillip Wallis","Zeyuan Allen-Zhu","Yuanzhi Li","Shean Wang","Lu Wang","Weizhu Chen"],"record_url":"https://programasweights.com/reading-list/papers/2106.09685/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2106-09685","citation_date":"2021-06-17","json_url":"https://programasweights.com/reading-list/papers/2106.09685/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2106.09685/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2106.09685/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2106.09685/citation.csl.json","publication":{"title":"LoRA: Low-Rank Adaptation of Large Language Models","author_names":["Edward Hu","Yelong Shen","Phillip Wallis","Zeyuan Allen-Zhu","Yuanzhi Li","Shean Wang","Lu Wang","Weizhu Chen"],"year":2022,"type":"paper-conference","container_title":"International Conference on Learning Representations","url":"https://openreview.net/forum?id=nZeVKeeFYf9","source_url":"https://openreview.net/pdf?id=nZeVKeeFYf9","verified_at":"2026-10-19"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2106.09685/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2106.09685/publication.csl.json","method_comparisons":[{"title":"Program form and compiler","text":"LoRA represents adaptation as low-rank weight updates; prefix tuning uses continuous activations. Their original methods learn these parameters from examples. PAW generates both forms from specifications.","source_ids":["2106.09685","2101.00190","2607.02512"],"source_urls":["https://arxiv.org/abs/2106.09685","https://aclanthology.org/2021.acl-long.353/","https://arxiv.org/html/2607.02512v1#S3"],"source_labels":["LoRA paper","Prefix-tuning paper","PAW implementations"],"topic_id":"peft","topic_label":"Parameter-efficient building blocks","topic_url":"https://programasweights.com/reading-list/guides/compilation/#peft"}]},{"id":"2211.12485","title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","authors":"Jason Phang, Yi Mao, Pengcheng He, Weizhu Chen","first_public":"2022-11-22","first_public_source":"https://arxiv.org/abs/2211.12485","arxiv_first_submission":"2022-11-22","date_label":"arXiv v1","arxiv":"2211.12485","paper_url":"https://arxiv.org/abs/2211.12485","venue":"ICML 2023","lens":["generated-adapters"],"related_terms":["HyperTuning","HyperT5","few-shot adaptation","generated LoRA"],"summary":"Produces task-specific parameters for a frozen language model from a few demonstrations.","contribution":"Introduces HyperT5 models that generate prefixes or LoRA parameters. Hyperpretraining and multitask training prepare the generator for new tasks.","limitations":"The hypermodel accepts a limited number of demonstrations. The paper also studies further task-specific tuning.","program_form":"Generated prefix or LoRA parameters.","conditioning":"A few examples of the task.","execution":"A frozen T5 model runs with the generated parameters.","relationship":"PAW cites HyperTuning as prior work on generating adaptation parameters from examples.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Jason Phang","Yi Mao","Pengcheng He","Weizhu Chen"],"record_url":"https://programasweights.com/reading-list/papers/2211.12485/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2211-12485","citation_date":"2022-11-22","json_url":"https://programasweights.com/reading-list/papers/2211.12485/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2211.12485/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2211.12485/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2211.12485/citation.csl.json","publication":{"title":"HyperTuning: Toward Adapting Large Language Models without Back-propagation","author_names":["Jason Phang","Yi Mao","Pengcheng He","Weizhu Chen"],"year":2023,"type":"paper-conference","container_title":"Proceedings of the 40th International Conference on Machine Learning","url":"https://proceedings.mlr.press/v202/phang23a.html","source_url":"https://proceedings.mlr.press/v202/phang23a.html","verified_at":"2026-10-19","volume":"202","publisher":"PMLR","pages":"27854-27875"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2211.12485/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2211.12485/publication.csl.json","method_comparisons":[{"title":"From generated adapters to reusable functions","text":"Hypter, HINT, HyperTuning, and Text-to-LoRA generate adaptations from descriptions or examples. PAW uses generated parameters as part of a program that can be saved, called from ordinary code, and reused by a fixed interpreter.","source_ids":["2101.00420","2212.10315","2211.12485","2506.06105","2607.02512"],"source_urls":["https://arxiv.org/html/2607.02512v1#S10","https://proceedings.mlr.press/v267/charakorn25a.html"],"source_labels":["PAW related work","Text-to-LoRA paper"],"topic_id":"generated-adapters","topic_label":"Generated weights and adapters","topic_url":"https://programasweights.com/reading-list/guides/compilation/#generated-adapters"}]},{"id":"2212.10315","title":"HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation","authors":"Hamish Ivison, Akshita Bhagia, Yizhong Wang, Hannaneh Hajishirzi, Matthew Peters","first_public":"2022-12-20","first_public_source":"https://arxiv.org/abs/2212.10315","arxiv_first_submission":"2022-12-20","date_label":"arXiv v1","arxiv":"2212.10315","paper_url":"https://arxiv.org/abs/2212.10315","venue":"ACL 2023","lens":["generated-adapters"],"related_terms":["HINT","instruction tuning","hypernetwork","instruction fusion"],"summary":"Turns instructions and examples into reusable prefixes, adapters, and encoded instruction representations.","contribution":"Combines a hypernetwork with instruction fusion so repeated calls can reuse the instruction computation. Evaluates zero-shot and few-shot generalization.","limitations":"The generated modules and cached instruction representations are tied to the trained encoder-decoder model.","program_form":"Prefixes, adapters, and encoded instruction representations.","conditioning":"Task instructions and optional examples.","execution":"An encoder-decoder model uses the generated modules and attends to cached instruction representations.","relationship":"HINT reuses generated modules and an encoded instruction. PAW reuses a program containing text and adaptation parameters.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Hamish Ivison","Akshita Bhagia","Yizhong Wang","Hannaneh Hajishirzi","Matthew Peters"],"record_url":"https://programasweights.com/reading-list/papers/2212.10315/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2212-10315","citation_date":"2022-12-20","json_url":"https://programasweights.com/reading-list/papers/2212.10315/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2212.10315/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2212.10315/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2212.10315/citation.csl.json","publication":{"title":"HINT: Hypernetwork Instruction Tuning for Efficient Zero- and Few-Shot Generalisation","author_names":["Hamish Ivison","Akshita Bhagia","Yizhong Wang","Hannaneh Hajishirzi","Matthew E. Peters"],"year":2023,"type":"paper-conference","container_title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","url":"https://aclanthology.org/2023.acl-long.631/","source_url":"https://aclanthology.org/2023.acl-long.631/","verified_at":"2026-10-19","doi":"10.18653/v1/2023.acl-long.631","publisher":"Association for Computational Linguistics","pages":"11272-11288"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2212.10315/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2212.10315/publication.csl.json","method_comparisons":[{"title":"From generated adapters to reusable functions","text":"Hypter, HINT, HyperTuning, and Text-to-LoRA generate adaptations from descriptions or examples. PAW uses generated parameters as part of a program that can be saved, called from ordinary code, and reused by a fixed interpreter.","source_ids":["2101.00420","2212.10315","2211.12485","2506.06105","2607.02512"],"source_urls":["https://arxiv.org/html/2607.02512v1#S10","https://proceedings.mlr.press/v267/charakorn25a.html"],"source_labels":["PAW related work","Text-to-LoRA paper"],"topic_id":"generated-adapters","topic_label":"Generated weights and adapters","topic_url":"https://programasweights.com/reading-list/guides/compilation/#generated-adapters"}]},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","authors":"Jesse Mu, Xiang Lisa Li, Noah Goodman","first_public":"2023-04-17","first_public_source":"https://arxiv.org/abs/2304.08467","arxiv_first_submission":"2023-04-17","date_label":"arXiv v1","arxiv":"2304.08467","paper_url":"https://arxiv.org/abs/2304.08467","venue":"NeurIPS 2023","lens":["context-compression"],"related_terms":["gist tokens","prompt compression","activation caching","amortized inference"],"summary":"Compresses an instruction into a few reusable token activations.","contribution":"Trains with an attention mask that forces later tokens to use gist activations in place of the original prompt.","limitations":"Compression can reduce output quality. The cached activations are tied to the trained model.","program_form":"Cached activations at a few gist-token positions.","conditioning":"The instruction or prompt.","execution":"The language model generates outputs while attending to the cached gist.","relationship":"PAW cites gisting as another way to reuse instruction computation. Gisting stores activations; PAW stores a program with text and adaptation parameters.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Jesse Mu","Xiang Lisa Li","Noah Goodman"],"record_url":"https://programasweights.com/reading-list/papers/2304.08467/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2304-08467","citation_date":"2023-04-17","json_url":"https://programasweights.com/reading-list/papers/2304.08467/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2304.08467/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2304.08467/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2304.08467/citation.csl.json","publication":{"title":"Learning to Compress Prompts with Gist Tokens","author_names":["Jesse Mu","Xiang Li","Noah Goodman"],"year":2023,"type":"paper-conference","container_title":"Advances in Neural Information Processing Systems","url":"https://proceedings.neurips.cc/paper_files/paper/2023/hash/3d77c6dcc7f143aa2154e7f4d5e22d68-Abstract-Conference.html","source_url":"https://proceedings.neurips.cc/paper_files/paper/2023/hash/3d77c6dcc7f143aa2154e7f4d5e22d68-Abstract-Conference.html","verified_at":"2026-10-19","volume":"36","doi":"10.52202/075280-0848","pages":"19327-19352"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2304.08467/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2304.08467/publication.csl.json","method_comparisons":[{"title":"What gets reused?","text":"Gisting caches a few instruction activations. Generative Adapter stores context in parameter updates. PAW saves a function as a program containing text and a neural module.","source_ids":["2304.08467","2411.05877","2607.02512"],"source_urls":["https://arxiv.org/abs/2304.08467","https://arxiv.org/abs/2411.05877","https://arxiv.org/html/2607.02512v1#S2"],"source_labels":["Gist paper","Generative Adapter paper","PAW program definition"],"topic_id":"context-compression","topic_label":"Context compression","topic_url":"https://programasweights.com/reading-list/guides/compilation/#context-compression"}]},{"id":"2407.11004","title":"The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators","authors":"Tzu-Heng Huang, Catherine Cao, Vaishnavi Bhargava, Frederic Sala","first_public":"2024-06-25","first_public_source":"https://arxiv.org/abs/2407.11004","arxiv_first_submission":"2024-06-25","date_label":"arXiv v1","arxiv":"2407.11004","paper_url":"https://arxiv.org/abs/2407.11004","venue":"NeurIPS 2024","lens":["neural-programs"],"related_terms":["ALCHEmist","program synthesis","automated labeling","reusable tools"],"summary":"Asks a language model to write labeling programs that can be saved and run locally.","contribution":"Reuses generated code across many labeling decisions and combines noisy program outputs with weak supervision.","limitations":"Label quality depends on the model’s ability to write useful programs. Complex tasks can produce code that is harder to inspect.","program_form":"Symbolic labeling programs.","conditioning":"A task description, labeling instructions, and a function signature.","execution":"Generated programs label examples locally; their outputs can be combined to train a downstream model.","relationship":"PAW evaluates an ALCHEmist-style approach. Both build reusable tools: ALCHEmist produces symbolic code, while PAW produces programs for a neural interpreter.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Tzu-Heng Huang","Catherine Cao","Vaishnavi Bhargava","Frederic Sala"],"record_url":"https://programasweights.com/reading-list/papers/2407.11004/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2407-11004","citation_date":"2024-06-25","json_url":"https://programasweights.com/reading-list/papers/2407.11004/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2407.11004/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2407.11004/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2407.11004/citation.csl.json","publication":{"title":"The ALCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators","author_names":["Tzu-Heng Huang","Catherine Cao","Vaishnavi Bhargava","Frederic Sala"],"year":2024,"type":"paper-conference","container_title":"Advances in Neural Information Processing Systems","url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html","source_url":"https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html","verified_at":"2026-10-19","volume":"37","doi":"10.52202/079017-2003","pages":"62648-62672"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2407.11004/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2407.11004/publication.csl.json","method_comparisons":[{"title":"Code and neural programs","text":"ALCHEmist generates symbolic labeling programs. PAW compiles fuzzy functions into text and learned parameters. Both build an artifact once and reuse it; one runs as code, the other on a neural interpreter.","source_ids":["2407.11004","2607.02512"],"source_urls":["https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html","https://arxiv.org/html/2607.02512v1#S6"],"source_labels":["ALCHEmist paper","PAW evaluation"],"topic_id":"neural-programs","topic_label":"Programs and reusable artifacts","topic_url":"https://programasweights.com/reading-list/guides/fuzzy-functions/"}]},{"id":"2411.05877","title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","authors":"Tong Chen, Hao Fang, Patrick Xia, Xiaodong Liu, Benjamin Van Durme, Luke Zettlemoyer, Jianfeng Gao, Hao Cheng","first_public":"2024-11-08","first_public_source":"https://arxiv.org/abs/2411.05877","arxiv_first_submission":"2024-11-08","date_label":"arXiv v1","arxiv":"2411.05877","paper_url":"https://arxiv.org/abs/2411.05877","venue":"ICLR 2025","lens":["generated-adapters","context-compression"],"related_terms":["Generative Adapter","contextualization","fast weights","streaming context"],"summary":"Converts new context into low-rank model updates in one forward pass.","contribution":"Trains an adapter generator with self-supervision. Tests learning from documents, demonstrations, and conversation history.","limitations":"The adapter generator is tied to its frozen base model.","program_form":"Additive low-rank adapters.","conditioning":"Documents, demonstrations, or conversation history, including successive chunks of context.","execution":"The adapted model answers new inputs using context stored in its parameter updates.","relationship":"PAW cites this context-to-adapter method. Generative Adapter stores information from context; PAW compiles the behavior of a function.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","first_public_note":"An AFM 2024 OpenReview version appeared before the first arXiv submission.","author_names":["Tong Chen","Hao Fang","Patrick Xia","Xiaodong Liu","Benjamin Van Durme","Luke Zettlemoyer","Jianfeng Gao","Hao Cheng"],"record_url":"https://programasweights.com/reading-list/papers/2411.05877/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2411-05877","citation_date":"2024-11-08","json_url":"https://programasweights.com/reading-list/papers/2411.05877/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2411.05877/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2411.05877/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2411.05877/citation.csl.json","publication":{"title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","author_names":["Tong Chen","Hao Fang","Patrick Xia","Xiaodong Liu","Benjamin Van Durme","Luke Zettlemoyer","Jianfeng Gao","Hao Cheng"],"year":2025,"type":"paper-conference","container_title":"International Conference on Learning Representations","url":"https://openreview.net/forum?id=bc3sUsS6ck","source_url":"https://openreview.net/pdf?id=bc3sUsS6ck","verified_at":"2026-10-19"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2411.05877/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2411.05877/publication.csl.json","method_comparisons":[{"title":"What gets reused?","text":"Gisting caches a few instruction activations. Generative Adapter stores context in parameter updates. PAW saves a function as a program containing text and a neural module.","source_ids":["2304.08467","2411.05877","2607.02512"],"source_urls":["https://arxiv.org/abs/2304.08467","https://arxiv.org/abs/2411.05877","https://arxiv.org/html/2607.02512v1#S2"],"source_labels":["Gist paper","Generative Adapter paper","PAW program definition"],"topic_id":"context-compression","topic_label":"Context compression","topic_url":"https://programasweights.com/reading-list/guides/compilation/#context-compression"}]},{"id":"2506.06105","title":"Text-to-LoRA: Instant Transformer Adaption","authors":"Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert Tjarko Lange","first_public":"2025-06-06","first_public_source":"https://arxiv.org/abs/2506.06105","arxiv_first_submission":"2025-06-06","date_label":"arXiv v1","arxiv":"2506.06105","paper_url":"https://arxiv.org/abs/2506.06105","venue":"ICML 2025","lens":["generated-adapters"],"related_terms":["Text-to-LoRA","T2L","task description","adapter generation"],"summary":"Uses a hypernetwork to generate LoRA adapters from task descriptions.","contribution":"Trains hypernetworks to reconstruct existing adapters or learn from supervised task data. Tests adapter compression and generation for unseen tasks.","limitations":"Reconstruction-trained T2L underperforms the supervised variant on unseen tasks.","program_form":"Generated LoRA matrices.","conditioning":"A natural-language task description.","execution":"A base transformer performs the task with the generated LoRA.","relationship":"PAW cites Text-to-LoRA as prior work on generating adapters. PAW develops fuzzy-function programming, FuzzyBench, and an interface for reusable neural programs.","relationship_source":"https://arxiv.org/html/2607.02512v1#S10","provenance":"arXiv record and paper.","author_names":["Rujikorn Charakorn","Edoardo Cetin","Yujin Tang","Robert Tjarko Lange"],"record_url":"https://programasweights.com/reading-list/papers/2506.06105/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2506-06105","citation_date":"2025-06-06","json_url":"https://programasweights.com/reading-list/papers/2506.06105/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2506.06105/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2506.06105/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2506.06105/citation.csl.json","publication":{"title":"Text-to-LoRA: Instant Transformer Adaption","author_names":["Rujikorn Charakorn","Edoardo Cetin","Yujin Tang","Robert Tjarko Lange"],"year":2025,"type":"paper-conference","container_title":"Proceedings of the 42nd International Conference on Machine Learning","url":"https://proceedings.mlr.press/v267/charakorn25a.html","source_url":"https://proceedings.mlr.press/v267/charakorn25a.html","verified_at":"2026-10-19","volume":"267","publisher":"PMLR","pages":"7485-7514"},"publication_bibtex_url":"https://programasweights.com/reading-list/papers/2506.06105/publication.bib","publication_csl_url":"https://programasweights.com/reading-list/papers/2506.06105/publication.csl.json","method_comparisons":[{"title":"From generated adapters to reusable functions","text":"Hypter, HINT, HyperTuning, and Text-to-LoRA generate adaptations from descriptions or examples. PAW uses generated parameters as part of a program that can be saved, called from ordinary code, and reused by a fixed interpreter.","source_ids":["2101.00420","2212.10315","2211.12485","2506.06105","2607.02512"],"source_urls":["https://arxiv.org/html/2607.02512v1#S10","https://proceedings.mlr.press/v267/charakorn25a.html"],"source_labels":["PAW related work","Text-to-LoRA paper"],"topic_id":"generated-adapters","topic_label":"Generated weights and adapters","topic_url":"https://programasweights.com/reading-list/guides/compilation/#generated-adapters"}]},{"id":"2607.02512","title":"Program-as-Weights: A Programming Paradigm for Fuzzy Functions","authors":"Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng","first_public":"2026-07-02","first_public_source":"https://arxiv.org/abs/2607.02512","arxiv_first_submission":"2026-07-02","date_label":"arXiv v1","arxiv":"2607.02512","paper_url":"https://arxiv.org/abs/2607.02512","venue":"NeurIPS 2026 (accepted)","lens":["neural-programs","generated-adapters"],"related_terms":["Program-as-Weights","ProgramAsWeights","PAW","fuzzy-function programming","neural compiler","neural interpreter","FuzzyBench"],"summary":"Proposes fuzzy-function programming: compile a natural-language function specification into a neural program, then reuse it locally.","contribution":"Develops the compiler–interpreter abstraction and programs that combine text with learned parameters. Introduces the 10M-example FuzzyBench dataset, local execution interfaces, and image-conditioned compilation. Prefix tuning and LoRA are two implementations.","limitations":"Each compiler produces programs for a specific interpreter. Compiled parameters are opaque, and FuzzyBench uses synthetic data.","program_form":"A discrete pseudo-program and a compiler-generated parameter-efficient module.","conditioning":"A function specification, optionally with examples. The image extension also accepts visual information.","execution":"A frozen lightweight interpreter loads the program and runs new inputs locally.","relationship":"Compile by Training builds on this programming abstraction. It keeps the same interface and refines the fast compiler’s prediction using synthesized examples.","relationship_source":"https://arxiv.org/html/2609.04199v1#S1","project_url":"https://programasweights.com/","code_url":"https://github.com/programasweights","equal_contribution":["Wentao Zhang","Liliana Hotsko","Woojeong Kim"],"venue_source":"https://yuntiandeng.com/","provenance":"July 2026 arXiv paper. NeurIPS 2026 acceptance is listed on Yuntian Deng’s homepage.","author_names":["Wentao Zhang","Liliana Hotsko","Woojeong Kim","Pengyu Nie","Stuart Shieber","Yuntian Deng"],"record_url":"https://programasweights.com/reading-list/papers/2607.02512/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2607-02512","citation_date":"2026-07-02","json_url":"https://programasweights.com/reading-list/papers/2607.02512/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2607.02512/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2607.02512/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2607.02512/citation.csl.json","method_comparisons":[{"title":"From generated adapters to reusable functions","text":"Hypter, HINT, HyperTuning, and Text-to-LoRA generate adaptations from descriptions or examples. PAW uses generated parameters as part of a program that can be saved, called from ordinary code, and reused by a fixed interpreter.","source_ids":["2101.00420","2212.10315","2211.12485","2506.06105","2607.02512"],"source_urls":["https://arxiv.org/html/2607.02512v1#S10","https://proceedings.mlr.press/v267/charakorn25a.html"],"source_labels":["PAW related work","Text-to-LoRA paper"],"topic_id":"generated-adapters","topic_label":"Generated weights and adapters","topic_url":"https://programasweights.com/reading-list/guides/compilation/#generated-adapters"},{"title":"Code and neural programs","text":"ALCHEmist generates symbolic labeling programs. PAW compiles fuzzy functions into text and learned parameters. Both build an artifact once and reuse it; one runs as code, the other on a neural interpreter.","source_ids":["2407.11004","2607.02512"],"source_urls":["https://proceedings.neurips.cc/paper_files/paper/2024/hash/72802bef5cf1a3449e909b20c2ae18d5-Abstract-Conference.html","https://arxiv.org/html/2607.02512v1#S6"],"source_labels":["ALCHEmist paper","PAW evaluation"],"topic_id":"neural-programs","topic_label":"Programs and reusable artifacts","topic_url":"https://programasweights.com/reading-list/guides/fuzzy-functions/"},{"title":"What gets reused?","text":"Gisting caches a few instruction activations. Generative Adapter stores context in parameter updates. PAW saves a function as a program containing text and a neural module.","source_ids":["2304.08467","2411.05877","2607.02512"],"source_urls":["https://arxiv.org/abs/2304.08467","https://arxiv.org/abs/2411.05877","https://arxiv.org/html/2607.02512v1#S2"],"source_labels":["Gist paper","Generative Adapter paper","PAW program definition"],"topic_id":"context-compression","topic_label":"Context compression","topic_url":"https://programasweights.com/reading-list/guides/compilation/#context-compression"},{"title":"Program form and compiler","text":"LoRA represents adaptation as low-rank weight updates; prefix tuning uses continuous activations. Their original methods learn these parameters from examples. PAW generates both forms from specifications.","source_ids":["2106.09685","2101.00190","2607.02512"],"source_urls":["https://arxiv.org/abs/2106.09685","https://aclanthology.org/2021.acl-long.353/","https://arxiv.org/html/2607.02512v1#S3"],"source_labels":["LoRA paper","Prefix-tuning paper","PAW implementations"],"topic_id":"peft","topic_label":"Parameter-efficient building blocks","topic_url":"https://programasweights.com/reading-list/guides/compilation/#peft"},{"title":"Fast prediction and training","text":"PAW’s fast compiler predicts a program. Compile by Training starts from that prediction, generates examples, and trains an adapter. Both use the same runtime interface; the extra training improves semantic accuracy on FuzzyBench-Hard at a higher compilation cost.","source_ids":["2607.02512","2609.04199"],"source_urls":["https://arxiv.org/html/2607.02512v1#S3","https://arxiv.org/html/2609.04199v1#S3","https://arxiv.org/html/2609.04199v1#S5"],"source_labels":["PAW compiler implementations","Compile by Training method","Compile by Training evaluation"],"topic_id":"training-compilation","topic_label":"Compilation through training","topic_url":"https://programasweights.com/reading-list/guides/compilation/#training-compilation"}]},{"id":"2609.04199","title":"Compile by Training: Turning Natural-Language Specifications into Local Neural Functions","authors":"Yuntian Deng, Pengyu Nie, Stuart Shieber","first_public":"2026-09-03","first_public_source":"https://arxiv.org/abs/2609.04199","arxiv_first_submission":"2026-09-03","date_label":"arXiv v1","arxiv":"2609.04199","paper_url":"https://arxiv.org/abs/2609.04199","original_url":"https://arxiv.org/html/2609.04199v1","venue":"EMNLP 2026 System Demonstrations","venue_source":"https://arxiv.org/abs/2609.04199","lens":["neural-programs","training-compilation"],"related_terms":["compile by training","training-based compilation","specification-specific optimization","synthetic supervision","local neural function","FuzzyBench-Hard","ProgramAsWeights"],"summary":"Compiles a function description into a reusable local program by generating training examples and optimizing an adapter.","contribution":"Makes task-specific training a software build step. Raises FuzzyBench-Hard semantic accuracy (LEM) from 22.4% to 83.6% and demonstrates composition in a website helper, avatar control, and English–Claudish translation.","limitations":"Synthetic examples can inherit teacher errors. Cold compilation takes 50.9 seconds for one specification on a B300. FuzzyBench-Hard selects fast-compiler failures under exact match; the reported accuracy uses an LLM judge.","program_form":"A LoRA adapter, runtime prompt, specification, and interpreter metadata in a PAW program.","conditioning":"The specification guides teacher synthesis. PAW’s fast compiler supplies the initial adapter and runtime prompt.","execution":"A frozen Qwen3-0.6B interpreter runs the saved function locally without further teacher calls.","relationship":"Extends PAW with training at compile time while keeping its program format and runtime interface.","relationship_source":"https://arxiv.org/html/2609.04199v1#S1","project_url":"https://programasweights.com/playground?compiler=paw-ft-bs48","demo_url":"https://programasweights.com/playground?compiler=paw-ft-bs48","code_url":"https://github.com/programasweights/compile-by-training","provenance":"September 2026 arXiv paper; its record lists EMNLP 2026 System Demonstrations.","first_public_note":"The paper reports public-service measurements from May 2026.","author_names":["Yuntian Deng","Pengyu Nie","Stuart Shieber"],"record_url":"https://programasweights.com/reading-list/papers/2609.04199/","legacy_record_url":"https://programasweights.com/reading-list/papers/#paper-2609-04199","citation_date":"2026-09-03","json_url":"https://programasweights.com/reading-list/papers/2609.04199/record.json","markdown_url":"https://programasweights.com/reading-list/papers/2609.04199/index.md","bibtex_url":"https://programasweights.com/reading-list/papers/2609.04199/citation.bib","csl_url":"https://programasweights.com/reading-list/papers/2609.04199/citation.csl.json","method_comparisons":[{"title":"Fast prediction and training","text":"PAW’s fast compiler predicts a program. Compile by Training starts from that prediction, generates examples, and trains an adapter. Both use the same runtime interface; the extra training improves semantic accuracy on FuzzyBench-Hard at a higher compilation cost.","source_ids":["2607.02512","2609.04199"],"source_urls":["https://arxiv.org/html/2607.02512v1#S3","https://arxiv.org/html/2609.04199v1#S3","https://arxiv.org/html/2609.04199v1#S5"],"source_labels":["PAW compiler implementations","Compile by Training method","Compile by Training evaluation"],"topic_id":"training-compilation","topic_label":"Compilation through training","topic_url":"https://programasweights.com/reading-list/guides/compilation/#training-compilation"}]}],"precursors":[]}