{"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/memorization/papers/5","list_of":"/task/memorization","task":"Memorization","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":5,"pages_in_order":11,"rows_per_page":100,"rows":[401,500],"of":1088,"counts":{"archive_papers_tagged":1088,"with_a_code_link":438,"where_syntology_ran_a_sample":177,"not_listed_spam_title":0,"listed":1088,"listed_where_code_ran":177,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":148,"every_run_a_failure_of_syntologys_instrument":29,"listed_with_a_run_with_no_instrument_failure":148,"listed_every_run_a_failure_of_syntologys_instrument":29,"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/memorization","prev":"/task/memorization/papers/4","next":"/task/memorization/papers/6","papers":[{"url":"/paper/learning-from-context-or-names-an-empirical","slug":"learning-from-context-or-names-an-empirical","title":"Learning from Context or Names? An Empirical Study on Neural Relation Extraction","date":"2020-10-05","arxiv_id":"2010.01923","repositories_listed":1,"syntology":null},{"url":"/paper/extreme-memorization-via-scale-of","slug":"extreme-memorization-via-scale-of","title":"Extreme Memorization via Scale of Initialization","date":"2020-08-31","arxiv_id":"2008.13363","repositories_listed":1,"syntology":null},{"url":"/paper/what-neural-networks-memorize-and-why","slug":"what-neural-networks-memorize-and-why","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","date":"2020-08-09","arxiv_id":"2008.03703","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/what-neural-networks-memorize-and-why#ran","syntology_url":"https://syntology.ai/paper/2008.03703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.03703"}},"official":null}},{"url":"/paper/question-and-answer-test-train-overlap-in","slug":"question-and-answer-test-train-overlap-in","title":"Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets","date":"2020-08-06","arxiv_id":"2008.02637","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/question-and-answer-test-train-overlap-in#ran","syntology_url":"https://syntology.ai/paper/2008.02637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02637"}},"official":{"repos":["facebookresearch/QA-Overlap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/salvage-reusable-samples-from-noisy-data-for","slug":"salvage-reusable-samples-from-noisy-data-for","title":"Salvage Reusable Samples from Noisy Data for Robust Learning","date":"2020-08-06","arxiv_id":"2008.02427","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-memory-based-self-supervised","slug":"distributed-memory-based-self-supervised","title":"Distributed Associative Memory Network with Memory Refreshing Loss","date":"2020-07-21","arxiv_id":"2007.10637","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/distributed-memory-based-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2007.10637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10637"}},"official":{"repos":["taewonpark/DAM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/what-they-do-when-in-doubt-a-study-of","slug":"what-they-do-when-in-doubt-a-study-of","title":"What they do when in doubt: a study of inductive biases in seq2seq learners","date":"2020-06-26","arxiv_id":"2006.14953","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-language-models-as-symbolic","slug":"pre-trained-language-models-as-symbolic","title":"Are Pretrained Language Models Symbolic Reasoners Over Knowledge?","date":"2020-06-18","arxiv_id":"2006.10413","repositories_listed":1,"syntology":null},{"url":"/paper/using-wavelets-and-spectral-methods-to-study","slug":"using-wavelets-and-spectral-methods-to-study","title":"Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets","date":"2020-06-17","arxiv_id":"2006.09879","repositories_listed":1,"syntology":null},{"url":"/paper/rethink-the-connections-among-generalization","slug":"rethink-the-connections-among-generalization","title":"Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs","date":"2020-04-29","arxiv_id":"2004.13954","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":1,"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/rethink-the-connections-among-generalization#ran","syntology_url":"https://syntology.ai/paper/2004.13954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13954"}},"official":{"repos":["ZhangXiao96/RethinkSpectralBias"],"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/babyai-towards-grounded-language-learning","slug":"babyai-towards-grounded-language-learning","title":"Zero-Shot Compositional Policy Learning via Language Grounding","date":"2020-04-15","arxiv_id":"2004.07200","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-single-view-3-d-object","slug":"few-shot-single-view-3-d-object","title":"Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors","date":"2020-04-14","arxiv_id":"2004.06302","repositories_listed":1,"syntology":null},{"url":"/paper/augmented-transformer-achieves-97-and-85-for","slug":"augmented-transformer-achieves-97-and-85-for","title":"State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesis","date":"2020-03-05","arxiv_id":"2003.02804","repositories_listed":1,"syntology":null},{"url":"/paper/do-we-need-zero-training-loss-after-achieving","slug":"do-we-need-zero-training-loss-after-achieving","title":"Do We Need Zero Training Loss After Achieving Zero Training Error?","date":"2020-02-20","arxiv_id":"2002.08709","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/do-we-need-zero-training-loss-after-achieving#ran","syntology_url":"https://syntology.ai/paper/2002.08709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.08709"}},"official":{"repos":["takashiishida/flooding"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-generalization-by-controlling-label","slug":"improving-generalization-by-controlling-label","title":"Improving Generalization by Controlling Label-Noise Information in Neural Network Weights","date":"2020-02-19","arxiv_id":"2002.07933","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-generalization-by-controlling-label#ran","syntology_url":"https://syntology.ai/paper/2002.07933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.07933"}},"official":{"repos":["hrayrhar/limit-label-memorization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/self-assttentive-associative-memory","slug":"self-assttentive-associative-memory","title":"Self-Attentive Associative Memory","date":"2020-02-10","arxiv_id":"2002.03519","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-assttentive-associative-memory#ran","syntology_url":"https://syntology.ai/paper/2002.03519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.03519"}},"official":{"repos":["thaihungle/SAM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/variational-recurrent-models-for-solving-1","slug":"variational-recurrent-models-for-solving-1","title":"Variational Recurrent Models for Solving Partially Observable Control Tasks","date":"2019-12-23","arxiv_id":"1912.10703","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-learning-with-different-label","slug":"towards-robust-learning-with-different-label","title":"Towards Robust Learning with Different Label Noise Distributions","date":"2019-12-18","arxiv_id":"1912.08741","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/towards-robust-learning-with-different-label#ran","syntology_url":"https://syntology.ai/paper/1912.08741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.08741"}},"official":null}},{"url":"/paper/meta-learning-without-memorization-1","slug":"meta-learning-without-memorization-1","title":"Meta-Learning without Memorization","date":"2019-12-09","arxiv_id":"1912.03820","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-gating-mechanism-of-recurrent-1","slug":"improving-the-gating-mechanism-of-recurrent-1","title":"Improving the Gating Mechanism of Recurrent Neural Networks","date":"2019-10-22","arxiv_id":"1910.09890","repositories_listed":1,"syntology":null},{"url":"/paper/overparameterized-neural-networks-can","slug":"overparameterized-neural-networks-can","title":"Overparameterized Neural Networks Implement Associative Memory","date":"2019-09-26","arxiv_id":"1909.12362","repositories_listed":1,"syntology":null},{"url":"/paper/span-selection-pre-training-for-question","slug":"span-selection-pre-training-for-question","title":"Span Selection Pre-training for Question Answering","date":"2019-09-09","arxiv_id":"1909.04120","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/span-selection-pre-training-for-question#ran","syntology_url":"https://syntology.ai/paper/1909.04120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04120"}},"official":{"repos":["IBM/span-selection-pretraining"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lifelong-sequential-modeling-with","slug":"lifelong-sequential-modeling-with","title":"Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction","date":"2019-05-02","arxiv_id":"1905.00758","repositories_listed":1,"syntology":null},{"url":"/paper/repnet-weakly-supervised-training-of-an","slug":"repnet-weakly-supervised-training-of-an","title":"RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation","date":"2019-02-26","arxiv_id":"1902.09868","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-infer-program-sketches","slug":"learning-to-infer-program-sketches","title":"Learning to Infer Program Sketches","date":"2019-02-17","arxiv_id":"1902.06349","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-kronecker-sum-approximation-of-real","slug":"optimal-kronecker-sum-approximation-of-real","title":"Optimal Kronecker-Sum Approximation of Real Time Recurrent Learning","date":"2019-02-11","arxiv_id":"1902.03993","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-human-learning-via-spaced","slug":"enhancing-human-learning-via-spaced","title":"Enhancing human learning via spaced repetition optimization","date":"2019-01-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-overfitting-of-deep-generative","slug":"detecting-overfitting-of-deep-generative","title":"Detecting Overfitting of Deep Generative Networks via Latent Recovery","date":"2019-01-09","arxiv_id":"1901.03396","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-remember-more-with-less","slug":"learning-to-remember-more-with-less","title":"Learning to Remember More with Less Memorization","date":"2019-01-05","arxiv_id":"1901.01347","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-remember-more-with-less#ran","syntology_url":"https://syntology.ai/paper/1901.01347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01347"}},"official":null}},{"url":"/paper/pumpout-a-meta-approach-to-robust-deep","slug":"pumpout-a-meta-approach-to-robust-deep","title":"SIGUA: Forgetting May Make Learning with Noisy Labels More Robust","date":"2018-09-28","arxiv_id":"1809.11008","repositories_listed":1,"syntology":null},{"url":"/paper/split-and-rephrase-better-evaluation-and","slug":"split-and-rephrase-better-evaluation-and","title":"Split and Rephrase: Better Evaluation and Stronger Baselines","date":"2018-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/alignet-partial-shape-agnostic-alignment-via","slug":"alignet-partial-shape-agnostic-alignment-via","title":"ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning","date":"2018-04-23","arxiv_id":"1804.08497","repositories_listed":1,"syntology":null},{"url":"/paper/olive-oil-is-made-of-olives-baby-oil-is-made","slug":"olive-oil-is-made-of-olives-baby-oil-is-made","title":"Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model","date":"2018-03-21","arxiv_id":"1803.08073","repositories_listed":1,"syntology":null},{"url":"/paper/memorization-precedes-generation-learning","slug":"memorization-precedes-generation-learning","title":"Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks","date":"2018-03-05","arxiv_id":"1803.01500","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/memorization-precedes-generation-learning#ran","syntology_url":"https://syntology.ai/paper/1803.01500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01500"}},"official":{"repos":["whyjay/memoryGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/skipflow-incorporating-neural-coherence","slug":"skipflow-incorporating-neural-coherence","title":"SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring","date":"2017-11-14","arxiv_id":"1711.04981","repositories_listed":1,"syntology":null},{"url":"/paper/question-dependent-recurrent-entity-network","slug":"question-dependent-recurrent-entity-network","title":"Question Dependent Recurrent Entity Network for Question Answering","date":"2017-07-25","arxiv_id":"1707.07922","repositories_listed":1,"syntology":null},{"url":"/paper/grid-long-short-term-memory","slug":"grid-long-short-term-memory","title":"Grid Long Short-Term Memory","date":"2015-07-06","arxiv_id":"1507.01526","repositories_listed":1,"syntology":null},{"url":null,"slug":"what-should-llms-forget-quantifying-personal","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","date":"2025-07-15","arxiv_id":"2507.11128","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-memorization-law-evaluating","title":"Entropy-Memorization Law: Evaluating Memorization Difficulty of Data in LLMs","date":"2025-07-08","arxiv_id":"2507.06056","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmreason-an-open-ended-multi-modal-multi-step","title":"MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI","date":"2025-06-30","arxiv_id":"2506.23563","repositories_listed":0,"syntology":null},{"url":null,"slug":"listener-rewarded-thinking-in-vlms-for-image","title":"Listener-Rewarded Thinking in VLMs for Image Preferences","date":"2025-06-28","arxiv_id":"2506.22832","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":"counterfactual-influence-as-a-distributional","title":"Counterfactual Influence as a Distributional Quantity","date":"2025-06-25","arxiv_id":"2506.20481","repositories_listed":0,"syntology":null},{"url":null,"slug":"leaner-training-lower-leakage-revisiting","title":"Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA","date":"2025-06-25","arxiv_id":"2506.20856","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-conceptual-blindspots-in","title":"Uncovering Conceptual Blindspots in Generative Image Models Using Sparse Autoencoders","date":"2025-06-24","arxiv_id":"2506.19708","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-random-matrix-analysis-of-in-context","title":"A Random Matrix Analysis of In-context Memorization for Nonlinear Attention","date":"2025-06-23","arxiv_id":"2506.18656","repositories_listed":0,"syntology":null},{"url":null,"slug":"robots-and-children-that-learn-together","title":"Robots and Children that Learn Together : Improving Knowledge Retention by Teaching Peer-Like Interactive Robots","date":"2025-06-23","arxiv_id":"2506.18365","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-learning-strategies-emerge","title":"In-Context Learning Strategies Emerge Rationally","date":"2025-06-21","arxiv_id":"2506.17859","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-undertraining-experts-improves","title":"Less is More: Undertraining Experts Improves Model Upcycling","date":"2025-06-17","arxiv_id":"2506.14126","repositories_listed":0,"syntology":null},{"url":null,"slug":"winter-soldier-backdooring-language-models-at","title":"Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning","date":"2025-06-17","arxiv_id":"2506.14913","repositories_listed":0,"syntology":null},{"url":"/paper/sharpness-aware-machine-unlearning","slug":"sharpness-aware-machine-unlearning","title":"Sharpness-Aware Machine Unlearning","date":"2025-06-16","arxiv_id":"2506.13715","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/sharpness-aware-machine-unlearning#ran","syntology_url":"https://syntology.ai/paper/2506.13715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13715"}},"official":null}},{"url":null,"slug":"restoring-gaussian-blurred-face-images-for","title":"Restoring Gaussian Blurred Face Images for Deanonymization Attacks","date":"2025-06-14","arxiv_id":"2506.12344","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-swe-bench-illusion-when-state-of-the-art","title":"The SWE-Bench Illusion: When State-of-the-Art LLMs Remember Instead of Reason","date":"2025-06-14","arxiv_id":"2506.12286","repositories_listed":0,"syntology":null},{"url":null,"slug":"sok-data-reconstruction-attacks-against","title":"SoK: Data Reconstruction Attacks Against Machine Learning Models: Definition, Metrics, and Benchmark","date":"2025-06-09","arxiv_id":"2506.07888","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-yet-effective-extracting-private-data","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","date":"2025-06-06","arxiv_id":"2506.06060","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attacks-on-sequence","title":"Membership Inference Attacks on Sequence Models","date":"2025-06-05","arxiv_id":"2506.05126","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-cross-modality-memorization-in","title":"Quantifying Cross-Modality Memorization in Vision-Language Models","date":"2025-06-05","arxiv_id":"2506.05198","repositories_listed":0,"syntology":null},{"url":null,"slug":"trade-offs-in-data-memorization-via-strong","title":"Trade-offs in Data Memorization via Strong Data Processing Inequalities","date":"2025-06-02","arxiv_id":"2506.01855","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-much-do-language-models-memorize","title":"How much do language models memorize?","date":"2025-05-30","arxiv_id":"2505.24832","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-perspective-on-memorization-and","title":"Bayesian Perspective on Memorization and Reconstruction","date":"2025-05-29","arxiv_id":"2505.23658","repositories_listed":0,"syntology":null},{"url":null,"slug":"kernel-smoothed-scores-for-denoising","title":"Kernel-Smoothed Scores for Denoising Diffusion: A Bias-Variance Study","date":"2025-05-28","arxiv_id":"2505.22841","repositories_listed":0,"syntology":null},{"url":null,"slug":"navigating-the-latent-space-dynamics-of","title":"Navigating the Latent Space Dynamics of Neural Models","date":"2025-05-28","arxiv_id":"2505.22785","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-to-generalization-emergence-of","title":"Memorization to Generalization: Emergence of Diffusion Models from Associative Memory","date":"2025-05-27","arxiv_id":"2505.21777","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-adversarial-training-for-diffusion","title":"What is Adversarial Training for Diffusion Models?","date":"2025-05-27","arxiv_id":"2505.21742","repositories_listed":0,"syntology":null},{"url":null,"slug":"spurious-privacy-leakage-in-neural-networks","title":"Spurious Privacy Leakage in Neural Networks","date":"2025-05-26","arxiv_id":"2505.20095","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-generalization-in-diffusion","title":"Understanding Generalization in Diffusion Models via Probability Flow Distance","date":"2025-05-26","arxiv_id":"2505.20123","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-forbidden-topics-in-language","title":"Discovering Forbidden Topics in Language Models","date":"2025-05-23","arxiv_id":"2505.17441","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-diffusion-models-don-t-memorize-the-role","title":"Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training","date":"2025-05-23","arxiv_id":"2505.17638","repositories_listed":0,"syntology":null},{"url":null,"slug":"bigger-isn-t-always-memorizing-early-stopping","title":"Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models","date":"2025-05-22","arxiv_id":"2505.16959","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-or-reasoning-exploring-the-idiom","title":"Memorization or Reasoning? Exploring the Idiom Understanding of LLMs","date":"2025-05-22","arxiv_id":"2505.16216","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-fact-recall-in-language-models","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","date":"2025-05-22","arxiv_id":"2505.16178","repositories_listed":0,"syntology":null},{"url":null,"slug":"protoknowledge-shapes-behaviour-of-llms-in","title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs","date":"2025-05-21","arxiv_id":"2505.15501","repositories_listed":0,"syntology":null},{"url":null,"slug":"shared-path-unraveling-memorization-in","title":"Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities","date":"2025-05-21","arxiv_id":"2505.15722","repositories_listed":0,"syntology":null},{"url":null,"slug":"sifternet-a-generalized-and-model-agnostic","title":"SifterNet: A Generalized and Model-Agnostic Trigger Purification Approach","date":"2025-05-20","arxiv_id":"2505.14531","repositories_listed":0,"syntology":null},{"url":null,"slug":"through-a-compressed-lens-investigating-the","title":"Through a Compressed Lens: Investigating the Impact of Quantization on LLM Explainability and Interpretability","date":"2025-05-20","arxiv_id":"2505.13963","repositories_listed":0,"syntology":null},{"url":null,"slug":"positional-fragility-in-llms-how-offset","title":"Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks","date":"2025-05-19","arxiv_id":"2505.13171","repositories_listed":0,"syntology":null},{"url":null,"slug":"extracting-memorized-pieces-of-copyrighted","title":"Extracting memorized pieces of (copyrighted) books from open-weight language models","date":"2025-05-18","arxiv_id":"2505.12546","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11411","title":"Is Grokking a Computational Glass Relaxation?","date":"2025-05-16","arxiv_id":"2505.11411","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-compression-cycles-improve","title":"Memorization-Compression Cycles Improve Generalization","date":"2025-05-13","arxiv_id":"2505.08727","repositories_listed":0,"syntology":null},{"url":null,"slug":"enfoque-odychess-un-metodo-dialectico","title":"Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas","date":"2025-05-10","arxiv_id":"2505.06652","repositories_listed":0,"syntology":null},{"url":null,"slug":"obliviate-robust-and-practical-machine","title":"OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models","date":"2025-05-07","arxiv_id":"2505.04416","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-membership-inference-attack-that-spots","title":"A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)","date":"2025-05-06","arxiv_id":"2505.03490","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-or-interpolation-detecting-llm","title":"Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis","date":"2025-05-05","arxiv_id":"2505.03019","repositories_listed":0,"syntology":null},{"url":null,"slug":"resolving-memorization-in-empirical-diffusion","title":"Resolving Memorization in Empirical Diffusion Model for Manifold Data in High-Dimensional Spaces","date":"2025-05-05","arxiv_id":"2505.02508","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeking-to-collide-online-safety-critical","title":"Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Models","date":"2025-05-02","arxiv_id":"2505.00972","repositories_listed":0,"syntology":null},{"url":null,"slug":"enronqa-towards-personalized-rag-over-private","title":"EnronQA: Towards Personalized RAG over Private Documents","date":"2025-05-01","arxiv_id":"2505.00263","repositories_listed":0,"syntology":null},{"url":null,"slug":"grokking-in-the-wild-data-augmentation-for","title":"Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers","date":"2025-04-29","arxiv_id":"2504.20752","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-privacy-utility-trade-offs-to-1","title":"Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models","date":"2025-04-25","arxiv_id":"2504.18032","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-memorization-problem-can-we-trust-llms","title":"The Memorization Problem: Can We Trust LLMs' Economic Forecasts?","date":"2025-04-20","arxiv_id":"2504.14765","repositories_listed":0,"syntology":null},{"url":null,"slug":"it-s-all-connected-a-journey-through-test","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","date":"2025-04-17","arxiv_id":"2504.13173","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-a-close-look-at-books","title":"Memorization: A Close Look at Books","date":"2025-04-17","arxiv_id":"2504.12549","repositories_listed":0,"syntology":null},{"url":null,"slug":"memorization-vs-reasoning-updating-llms-with","title":"Memorization vs. Reasoning: Updating LLMs with New Knowledge","date":"2025-04-16","arxiv_id":"2504.12523","repositories_listed":0,"syntology":null},{"url":null,"slug":"replicating-relm-results-validating-large","title":"Replicating ReLM Results: Validating Large Language Models with ReLM","date":"2025-04-16","arxiv_id":"2504.12357","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-could-be-rote-learners","title":"Large Language Models Could Be Rote Learners","date":"2025-04-11","arxiv_id":"2504.08300","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-introduction-to-memory-competitions","title":"An introduction to memory competitions, records and techniques","date":"2025-04-09","arxiv_id":"2504.06747","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-method-for-storing-patterns-in-neural","title":"The Method for Storing Patterns in Neural Networks-Memorization and Recall of QR code Patterns-","date":"2025-04-09","arxiv_id":"2504.06631","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-larger-language-models-imply-better","title":"Do Larger Language Models Imply Better Reasoning? A Pretraining Scaling Law for Reasoning","date":"2025-04-04","arxiv_id":"2504.03635","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-reasoning-meets-compression-benchmarking","title":"When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks","date":"2025-04-02","arxiv_id":"2504.02010","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmo-combination-of-selective-memorization","title":"COSMO: Combination of Selective Memorization for Low-cost Vision-and-Language Navigation","date":"2025-03-31","arxiv_id":"2503.24065","repositories_listed":0,"syntology":null}],"record_sha256":"cf4d231d78c59fc4d34c60e1db9765eb8564f4d5561b7e959f7c20e83226034c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}