{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/code-generation/papers/8","list_of":"/task/code-generation","task":"Code Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":17,"rows_per_page":100,"rows":[701,800],"of":1697,"counts":{"archive_papers_tagged":1697,"with_a_code_link":745,"where_syntology_ran_a_sample":280,"not_listed_spam_title":0,"listed":1697,"listed_where_code_ran":280,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":238,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":238,"listed_every_run_a_failure_of_syntologys_instrument":42,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/code-generation","prev":"/task/code-generation/papers/7","next":"/task/code-generation/papers/9","papers":[{"url":"/paper/reusing-auto-schedules-for-efficient-dnn","slug":"reusing-auto-schedules-for-efficient-dnn","title":"Transfer-Tuning: Reusing Auto-Schedules for Efficient Tensor Program Code Generation","date":"2022-01-14","arxiv_id":"2201.05587","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/reusing-auto-schedules-for-efficient-dnn#ran","syntology_url":"https://syntology.ai/paper/2201.05587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.05587"}},"official":{"repos":["giclab/transfer-tuning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/lyra-a-benchmark-for-turducken-style-code","slug":"lyra-a-benchmark-for-turducken-style-code","title":"Lyra: A Benchmark for Turducken-Style Code Generation","date":"2021-08-27","arxiv_id":"2108.12144","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-tree-structured-architectures-for","slug":"analysis-of-tree-structured-architectures-for","title":"Analysis of Tree-Structured Architectures for Code Generation","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/code-generation-from-natural-language-with","slug":"code-generation-from-natural-language-with","title":"Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tfix-learning-to-fix-coding-errors-with-a","slug":"tfix-learning-to-fix-coding-errors-with-a","title":"TFix: Learning to Fix Coding Errors with a Text-to-Text Transformer","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/akg-automatic-kernel-generation-for-neural","slug":"akg-automatic-kernel-generation-for-neural","title":"AKG: Automatic Kernel Generation for Neural Processing Units using Polyhedral Transformations","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-syntax-guided-edit-decoder-for-neural","slug":"a-syntax-guided-edit-decoder-for-neural","title":"A Syntax-Guided Edit Decoder for Neural Program Repair","date":"2021-06-15","arxiv_id":"2106.08253","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":1,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":1,"phrase":"12 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-syntax-guided-edit-decoder-for-neural#ran","syntology_url":"https://syntology.ai/paper/2106.08253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08253"}},"official":null}},{"url":"/paper/reading-stackoverflow-encourages-cheating","slug":"reading-stackoverflow-encourages-cheating","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","date":"2021-06-08","arxiv_id":"2106.04447","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-dynamic-selection-of-branch","slug":"exploring-dynamic-selection-of-branch","title":"Exploring Dynamic Selection of Branch Expansion Orders for Code Generation","date":"2021-06-01","arxiv_id":"2106.00261","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/exploring-dynamic-selection-of-branch#ran","syntology_url":"https://syntology.ai/paper/2106.00261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.00261"}},"official":{"repos":["DeepLearnXMU/CG-RL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/cotext-multi-task-learning-with-code-text","slug":"cotext-multi-task-learning-with-code-text","title":"CoTexT: Multi-task Learning with Code-Text Transformer","date":"2021-05-18","arxiv_id":"2105.08645","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-cost-analysis-for-distributed-dl","slug":"hierarchical-cost-analysis-for-distributed-dl","title":"Hierarchical Cost Analysis for Distributed DL","date":"2021-05-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/shellcode-ia32-a-dataset-for-automatic","slug":"shellcode-ia32-a-dataset-for-automatic","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","date":"2021-04-27","arxiv_id":"2104.13100","repositories_listed":1,"syntology":null},{"url":"/paper/a-sketch-based-neural-model-for-generating","slug":"a-sketch-based-neural-model-for-generating","title":"A Sketch-Based Neural Model for Generating Commit Messages from Diffs","date":"2021-04-08","arxiv_id":"2104.04087","repositories_listed":1,"syntology":null},{"url":"/paper/codetrans-towards-cracking-the-language-of","slug":"codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","repositories_listed":1,"syntology":null},{"url":"/paper/embedding-api-dependency-graph-for-neural","slug":"embedding-api-dependency-graph-for-neural","title":"Embedding API Dependency Graph for Neural Code Generation","date":"2021-03-29","arxiv_id":"2103.15361","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-code-generation-from-sketches-of","slug":"automatic-code-generation-from-sketches-of","title":"Automatic code generation from sketches of mobile applications in end-user development using Deep Learning","date":"2021-03-09","arxiv_id":"2103.05704","repositories_listed":1,"syntology":null},{"url":"/paper/iot-instance-wise-layer-reordering-for-1","slug":"iot-instance-wise-layer-reordering-for-1","title":"IOT: Instance-wise Layer Reordering for Transformer Structures","date":"2021-03-05","arxiv_id":"2103.03457","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/iot-instance-wise-layer-reordering-for-1#ran","syntology_url":"https://syntology.ai/paper/2103.03457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03457"}},"official":{"repos":["instance-wise-ordered-transformer/IOT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-code-generation-using-pre-trained","slug":"automatic-code-generation-using-pre-trained","title":"Automatic Code Generation using Pre-Trained Language Models","date":"2021-02-21","arxiv_id":"2102.10535","repositories_listed":1,"syntology":null},{"url":"/paper/cain-automatic-code-generation-for","slug":"cain-automatic-code-generation-for","title":"Cain: Automatic Code Generation for Simultaneous Convolutional Kernels on Focal-plane Sensor-processors","date":"2021-01-21","arxiv_id":"2101.08715","repositories_listed":1,"syntology":null},{"url":"/paper/teach-me-how-to-label-labeling-functions-from","slug":"teach-me-how-to-label-labeling-functions-from","title":"Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers","date":"2021-01-18","arxiv_id":"2101.07138","repositories_listed":1,"syntology":null},{"url":"/paper/fbgemm-enabling-high-performance-low","slug":"fbgemm-enabling-high-performance-low","title":"FBGEMM: Enabling High-Performance Low-Precision Deep Learning Inference","date":"2021-01-13","arxiv_id":"2101.05615","repositories_listed":1,"syntology":null},{"url":"/paper/discovering-autoregressive-orderings-with","slug":"discovering-autoregressive-orderings-with","title":"Discovering Autoregressive Orderings with Variational Inference","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/n-bref-a-high-fidelity-decompiler-exploiting","slug":"n-bref-a-high-fidelity-decompiler-exploiting","title":"N-Bref : A High-fidelity Decompiler Exploiting Programming Structures","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/semantic-parsing-with-less-prior-and-more","slug":"semantic-parsing-with-less-prior-and-more","title":"Code Generation from Natural Language with Less Prior and More Monolingual Data","date":"2021-01-01","arxiv_id":"2101.00259","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-asymmetric-deep-hashing-with","slug":"self-supervised-asymmetric-deep-hashing-with","title":"Self-supervised asymmetric deep hashing with margin-scalable constraint","date":"2020-12-07","arxiv_id":"2012.03820","repositories_listed":1,"syntology":null},{"url":"/paper/from-things-modeling-language-thingml-to","slug":"from-things-modeling-language-thingml-to","title":"From Things' Modeling Language (ThingML) to Things' Machine Learning (ThingML2)","date":"2020-09-22","arxiv_id":"2009.10632","repositories_listed":1,"syntology":null},{"url":"/paper/thingml-augmenting-model-driven-software","slug":"thingml-augmenting-model-driven-software","title":"ThingML+ Augmenting Model-Driven Software Engineering for the Internet of Things with Machine Learning","date":"2020-09-22","arxiv_id":"2009.10633","repositories_listed":1,"syntology":null},{"url":"/paper/automated-source-code-generation-and-auto","slug":"automated-source-code-generation-and-auto","title":"Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches","date":"2020-09-16","arxiv_id":"2009.07740","repositories_listed":1,"syntology":null},{"url":"/paper/fastspec-scalable-generation-and-detection-of","slug":"fastspec-scalable-generation-and-detection-of","title":"FastSpec: Scalable Generation and Detection of Spectre Gadgets Using Neural Embeddings","date":"2020-06-25","arxiv_id":"2006.14147","repositories_listed":1,"syntology":null},{"url":"/paper/multi-branch-attentive-transformer","slug":"multi-branch-attentive-transformer","title":"Multi-branch Attentive Transformer","date":"2020-06-18","arxiv_id":"2006.10270","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":2,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-branch-attentive-transformer#ran","syntology_url":"https://syntology.ai/paper/2006.10270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10270"}},"official":null}},{"url":"/paper/semantic-scaffolds-for-pseudocode-to-code","slug":"semantic-scaffolds-for-pseudocode-to-code","title":"Semantic Scaffolds for Pseudocode-to-Code Generation","date":"2020-05-12","arxiv_id":"2005.05927","repositories_listed":1,"syntology":null},{"url":"/paper/a-c-code-generator-for-fast-inference-and","slug":"a-c-code-generator-for-fast-inference-and","title":"A C Code Generator for Fast Inference and Simple Deployment of Convolutional Neural Networks on Resource Constrained Systems","date":"2020-01-14","arxiv_id":"2001.05572","repositories_listed":1,"syntology":null},{"url":"/paper/program-synthesis-and-semantic-parsing-with","slug":"program-synthesis-and-semantic-parsing-with","title":"Program Synthesis and Semantic Parsing with Learned Code Idioms","date":"2019-06-26","arxiv_id":"1906.10816","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/program-synthesis-and-semantic-parsing-with#ran","syntology_url":"https://syntology.ai/paper/1906.10816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10816"}},"official":{"repos":["rshin/seq2struct"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/interpreting-owl-complex-classes-in","slug":"interpreting-owl-complex-classes-in","title":"Interpreting OWL Complex Classes in AutomationML based on Bidirectional Translation","date":"2019-06-04","arxiv_id":"1906.04240","repositories_listed":1,"syntology":null},{"url":"/paper/reversible-jump-probabilistic-programming","slug":"reversible-jump-probabilistic-programming","title":"Reversible Jump Probabilistic Programming","date":"2019-04-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stripe-tensor-compilation-via-the-nested","slug":"stripe-tensor-compilation-via-the-nested","title":"Stripe: Tensor Compilation via the Nested Polyhedral Model","date":"2019-03-14","arxiv_id":"1903.06498","repositories_listed":1,"syntology":null},{"url":"/paper/codegru-context-aware-deep-learning-with","slug":"codegru-context-aware-deep-learning-with","title":"CodeGRU: Context-aware Deep Learning with Gated Recurrent Unit for Source Code Modeling","date":"2019-03-03","arxiv_id":"1903.00884","repositories_listed":1,"syntology":null},{"url":"/paper/eclipse-cdt-code-analysis-and-unit-testing","slug":"eclipse-cdt-code-analysis-and-unit-testing","title":"Eclipse CDT code analysis and unit testing","date":"2018-11-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-grammar-based-structural-cnn-decoder-for","slug":"a-grammar-based-structural-cnn-decoder-for","title":"A Grammar-Based Structural CNN Decoder for Code Generation","date":"2018-11-14","arxiv_id":"1811.06837","repositories_listed":1,"syntology":null},{"url":"/paper/retrieval-based-neural-code-generation","slug":"retrieval-based-neural-code-generation","title":"Retrieval-Based Neural Code Generation","date":"2018-08-29","arxiv_id":"1808.10025","repositories_listed":1,"syntology":null},{"url":"/paper/neural-machine-translation-for-query","slug":"neural-machine-translation-for-query","title":"Neural Machine Translation for Query Construction and Composition","date":"2018-06-27","arxiv_id":"1806.10478","repositories_listed":1,"syntology":null},{"url":"/paper/deep-hashing-with-category-mask-for-fast","slug":"deep-hashing-with-category-mask-for-fast","title":"Deep Hashing with Category Mask for Fast Video Retrieval","date":"2017-12-22","arxiv_id":"1712.08315","repositories_listed":1,"syntology":null},{"url":"/paper/dlvm-a-modern-compiler-infrastructure-for","slug":"dlvm-a-modern-compiler-infrastructure-for","title":"DLVM: A modern compiler infrastructure for deep learning systems","date":"2017-11-08","arxiv_id":"1711.03016","repositories_listed":1,"syntology":null},{"url":"/paper/abstract-syntax-networks-for-code-generation","slug":"abstract-syntax-networks-for-code-generation","title":"Abstract Syntax Networks for Code Generation and Semantic Parsing","date":"2017-04-25","arxiv_id":"1704.07535","repositories_listed":1,"syntology":null},{"url":"/paper/boda-rtc-productive-generation-of-portable","slug":"boda-rtc-productive-generation-of-portable","title":"Boda-RTC: Productive Generation of Portable, Efficient Code for Convolutional Neural Networks on Mobile Computing Platforms","date":"2016-06-01","arxiv_id":"1606.00094","repositories_listed":1,"syntology":null},{"url":null,"slug":"cuda-l1-improving-cuda-optimization-via","title":"CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning","date":"2025-07-18","arxiv_id":"2507.14111","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-formal-verification-of-llm-generated","title":"Towards Formal Verification of LLM-Generated Code from Natural Language Prompts","date":"2025-07-17","arxiv_id":"2507.13290","repositories_listed":0,"syntology":null},{"url":null,"slug":"mera-code-a-unified-framework-for-evaluating","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","date":"2025-07-16","arxiv_id":"2507.12284","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-up-rl-unlocking-diverse-reasoning-in","title":"Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training","date":"2025-07-16","arxiv_id":"2507.12507","repositories_listed":0,"syntology":null},{"url":"/paper/codeassistbench-cab-dataset-benchmarking-for","slug":"codeassistbench-cab-dataset-benchmarking-for","title":"CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance","date":"2025-07-14","arxiv_id":"2507.10646","repositories_listed":0,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/codeassistbench-cab-dataset-benchmarking-for#ran","syntology_url":"https://syntology.ai/paper/2507.10646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.10646"}},"official":null}},{"url":null,"slug":"codejudgebench-benchmarking-llm-as-a-judge","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","date":"2025-07-14","arxiv_id":"2507.10535","repositories_listed":0,"syntology":null},{"url":null,"slug":"turning-the-tide-repository-based-code","title":"Turning the Tide: Repository-based Code Reflection","date":"2025-07-14","arxiv_id":"2507.09866","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-multimodal-software-developer","title":"Multilingual Multimodal Software Developer for Code Generation","date":"2025-07-11","arxiv_id":"2507.08719","repositories_listed":0,"syntology":null},{"url":null,"slug":"opencodereasoning-ii-a-simple-test-time","title":"OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique","date":"2025-07-11","arxiv_id":"2507.09075","repositories_listed":0,"syntology":null},{"url":null,"slug":"automating-md-simulations-for-proteins-using","title":"Automating MD simulations for Proteins using Large language Models: NAMD-Agent","date":"2025-07-10","arxiv_id":"2507.07887","repositories_listed":0,"syntology":null},{"url":null,"slug":"artifactsbench-bridging-the-visual","title":"ArtifactsBench: Bridging the Visual-Interactive Gap in LLM Code Generation Evaluation","date":"2025-07-07","arxiv_id":"2507.04952","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-globally-speak-locally-bridging-the","title":"Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning","date":"2025-07-07","arxiv_id":"2507.05418","repositories_listed":0,"syntology":null},{"url":null,"slug":"core-benchmarking-llms-code-reasoning","title":"CORE: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks","date":"2025-07-03","arxiv_id":"2507.05269","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-realistic-safety-critical-driving","title":"LLM-based Realistic Safety-Critical Driving Video Generation","date":"2025-07-02","arxiv_id":"2507.01264","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-empowered-agent-for","title":"A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis","date":"2025-06-27","arxiv_id":"2507.02938","repositories_listed":0,"syntology":null},{"url":null,"slug":"where-to-find-grokking-in-llm-pretraining","title":"Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test","date":"2025-06-26","arxiv_id":"2506.21551","repositories_listed":0,"syntology":null},{"url":null,"slug":"sacl-understanding-and-combating-textual-bias","title":"SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization","date":"2025-06-25","arxiv_id":"2506.20081","repositories_listed":0,"syntology":null},{"url":null,"slug":"sv-llm-an-agentic-approach-for-soc-security","title":"SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models","date":"2025-06-25","arxiv_id":"2506.20415","repositories_listed":0,"syntology":null},{"url":null,"slug":"qhackbench-benchmarking-large-language-models","title":"QHackBench: Benchmarking Large Language Models for Quantum Code Generation Using PennyLane Hackathon Challenges","date":"2025-06-24","arxiv_id":"2506.20008","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-do-open-source-llms-struggle-with-data","title":"Why Do Open-Source LLMs Struggle with Data Analysis? A Systematic Empirical Study","date":"2025-06-24","arxiv_id":"2506.19794","repositories_listed":0,"syntology":null},{"url":null,"slug":"steering-conceptual-bias-via-transformer","title":"Steering Conceptual Bias via Transformer Latent-Subspace Activation","date":"2025-06-23","arxiv_id":"2506.18887","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-debugging-decay-index-rethinking","title":"The Debugging Decay Index: Rethinking Debugging Strategies for Code LLMs","date":"2025-06-23","arxiv_id":"2506.18403","repositories_listed":0,"syntology":null},{"url":null,"slug":"use-property-based-testing-to-bridge-llm-code","title":"Use Property-Based Testing to Bridge LLM Code Generation and Validation","date":"2025-06-23","arxiv_id":"2506.18315","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotwin-2-0-a-scalable-data-generator-and","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","date":"2025-06-22","arxiv_id":"2506.18088","repositories_listed":0,"syntology":null},{"url":null,"slug":"massive-supervised-fine-tuning-experiments","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","date":"2025-06-17","arxiv_id":"2506.14681","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-technical-study-into-small-reasoning","title":"A Technical Study into Small Reasoning Language Models","date":"2025-06-16","arxiv_id":"2506.13404","repositories_listed":0,"syntology":null},{"url":null,"slug":"frontendbench-a-benchmark-for-evaluating-llms","title":"FrontendBench: A Benchmark for Evaluating LLMs on Front-End Development via Automatic Evaluation","date":"2025-06-16","arxiv_id":"2506.13832","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-llm-reasoning-work-for-code-a-survey","title":"How Does LLM Reasoning Work for Code? A Survey and a Call to Action","date":"2025-06-16","arxiv_id":"2506.13932","repositories_listed":0,"syntology":null},{"url":null,"slug":"structured-program-synthesis-using-llms","title":"Structured Program Synthesis using LLMs: Results and Insights from the IPARC Challenge","date":"2025-06-15","arxiv_id":"2506.13820","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-safety-reminder-a-soft-prompt-to","title":"The Safety Reminder: A Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models","date":"2025-06-15","arxiv_id":"2506.15734","repositories_listed":0,"syntology":null},{"url":null,"slug":"code-transformed-the-influence-of-large","title":"code_transformed: The Influence of Large Language Models on Code","date":"2025-06-13","arxiv_id":"2506.12014","repositories_listed":0,"syntology":null},{"url":null,"slug":"reveal-self-evolving-code-agents-via","title":"ReVeal: Self-Evolving Code Agents via Iterative Generation-Verification","date":"2025-06-13","arxiv_id":"2506.11442","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-as-a-judge-for-reference-less-automatic","title":"LLM-as-a-Judge for Reference-less Automatic Code Validation and Refinement for Natural Language to Bash in IT Automation","date":"2025-06-12","arxiv_id":"2506.11237","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-10204","title":"Prompt Variability Effects On LLM Code Generation","date":"2025-06-11","arxiv_id":"2506.10204","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-as-a-resource-optimizing-fast-and","title":"Reasoning as a Resource: Optimizing Fast and Slow Thinking in Code Generation Models","date":"2025-06-11","arxiv_id":"2506.09396","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08311","title":"Understanding Software Engineering Agents Through the Lens of Traceability: An Empirical Study","date":"2025-06-10","arxiv_id":"2506.08311","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-flows-flow-matching-with-edit-operations","title":"Edit Flows: Flow Matching with Edit Operations","date":"2025-06-10","arxiv_id":"2506.09018","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-capabilities-of-the-frontier","title":"Exploring the Capabilities of the Frontier Large Language Models for Nuclear Energy Research","date":"2025-06-10","arxiv_id":"2506.19863","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-for-argoverse2-scenario","title":"Technical Report for Argoverse2 Scenario Mining Challenges on Iterative Error Correction and Spatially-Aware Prompting","date":"2025-06-10","arxiv_id":"2506.11124","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08171","title":"Worst-Case Symbolic Constraints Analysis and Generalisation with Large Language Models","date":"2025-06-09","arxiv_id":"2506.08171","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08173","title":"Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles","date":"2025-06-09","arxiv_id":"2506.08173","repositories_listed":0,"syntology":null},{"url":null,"slug":"protocolllm-rtl-benchmark-for-systemverilog","title":"ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols","date":"2025-06-09","arxiv_id":"2506.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"veriloc-line-of-code-level-prediction-of","title":"VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code","date":"2025-06-08","arxiv_id":"2506.07239","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-generate-reliable-test-case","title":"Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems","date":"2025-06-07","arxiv_id":"2506.06821","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-theoretical-physics-research-benefit-from","title":"Can Theoretical Physics Research Benefit from Language Agents?","date":"2025-06-06","arxiv_id":"2506.06214","repositories_listed":0,"syntology":null},{"url":null,"slug":"cp-bench-evaluating-large-language-models-for","title":"CP-Bench: Evaluating Large Language Models for Constraint Modelling","date":"2025-06-06","arxiv_id":"2506.06052","repositories_listed":0,"syntology":null},{"url":null,"slug":"safegenbench-a-benchmark-framework-for","title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","date":"2025-06-06","arxiv_id":"2506.05692","repositories_listed":0,"syntology":null},{"url":null,"slug":"demonstrations-of-integrity-attacks-in-multi","title":"Demonstrations of Integrity Attacks in Multi-Agent Systems","date":"2025-06-05","arxiv_id":"2506.04572","repositories_listed":0,"syntology":null},{"url":null,"slug":"hdl2v-a-code-translation-dataset-for-enhanced","title":"hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation","date":"2025-06-05","arxiv_id":"2506.04544","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalertl-scaling-llms-with-reasoning-data-and","title":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","date":"2025-06-05","arxiv_id":"2506.05566","repositories_listed":0,"syntology":null},{"url":null,"slug":"cetbench-a-novel-dataset-constructed-via","title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking","date":"2025-06-04","arxiv_id":"2506.04019","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-virtual-agents-to-robot-teams-a-multi","title":"From Virtual Agents to Robot Teams: A Multi-Robot Framework Evaluation in High-Stakes Healthcare Context","date":"2025-06-04","arxiv_id":"2506.03546","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-automotive-code-large-language","title":"Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems","date":"2025-06-04","arxiv_id":"2506.04038","repositories_listed":0,"syntology":null},{"url":null,"slug":"viscoder-fine-tuning-llms-for-executable","title":"VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation","date":"2025-06-04","arxiv_id":"2506.03930","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-do-pre-trained-models-support-software","title":"How do Pre-Trained Models Support Software Engineering? An Empirical Study in Hugging Face","date":"2025-06-03","arxiv_id":"2506.03013","repositories_listed":0,"syntology":null}],"record_sha256":"382b6c58cd55b49380e32c153b7051624d188a2b65bfb82d90bfa4ebe35f827c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}