{"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/inductive-bias/papers/13","list_of":"/task/inductive-bias","task":"Inductive Bias","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":13,"pages_in_order":16,"rows_per_page":100,"rows":[1201,1300],"of":1529,"counts":{"archive_papers_tagged":1529,"with_a_code_link":716,"where_syntology_ran_a_sample":284,"not_listed_spam_title":0,"listed":1529,"listed_where_code_ran":284,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":244,"every_run_a_failure_of_syntologys_instrument":40,"listed_with_a_run_with_no_instrument_failure":244,"listed_every_run_a_failure_of_syntologys_instrument":40,"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/inductive-bias","prev":"/task/inductive-bias/papers/12","next":"/task/inductive-bias/papers/14","papers":[{"url":null,"slug":"dynamic-recognition-of-speakers-for-consent","title":"Dynamic Recognition of Speakers for Consent Management by Contrastive Embedding Replay","date":"2022-05-17","arxiv_id":"2205.08459","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-attention-via-convex-duality","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","date":"2022-05-17","arxiv_id":"2205.08078","repositories_listed":0,"syntology":null},{"url":null,"slug":"volatility-inspired-s-lstm-cell","title":"Volatility-inspired $σ$-LSTM cell","date":"2022-05-14","arxiv_id":"2205.07022","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-symmetry-in-variational-quantum","title":"Exploiting symmetry in variational quantum machine learning","date":"2022-05-12","arxiv_id":"2205.06217","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-a-single-mr-modality","title":"Disentangling A Single MR Modality","date":"2022-05-10","arxiv_id":"2205.04982","repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-content-synergistic-learning-for","title":"Invariant Content Synergistic Learning for Domain Generalization of Medical Image Segmentation","date":"2022-05-05","arxiv_id":"2205.02845","repositories_listed":0,"syntology":null},{"url":null,"slug":"remus-gnn-a-rotation-equivariant-model-for","title":"REMuS-GNN: A Rotation-Equivariant Model for Simulating Continuum Dynamics","date":"2022-05-05","arxiv_id":"2205.07852","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-wug-two-wug-s-transformer-inflection","title":"One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theory-of-natural-intelligence","title":"A Theory of Natural Intelligence","date":"2022-04-22","arxiv_id":"2205.00002","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-theory-of-mind-via-dynamic-traits","title":"Learning Theory of Mind via Dynamic Traits Attribution","date":"2022-04-17","arxiv_id":"2204.09047","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-shuffle-mixer-an-efficient-context-aware","title":"3D Shuffle-Mixer: An Efficient Context-Aware Vision Learner of Transformer-MLP Paradigm for Dense Prediction in Medical Volume","date":"2022-04-14","arxiv_id":"2204.06779","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-active-learning-strategies-for","title":"Benchmarking Active Learning Strategies for Materials Optimization and Discovery","date":"2022-04-12","arxiv_id":"2204.05838","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-transformer-equipped-with-neural","title":"Vision Transformer Equipped with Neural Resizer on Facial Expression Recognition Task","date":"2022-04-05","arxiv_id":"2204.02181","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-blind-image-denoising-via-implicit","title":"Zero-shot Blind Image Denoising via Implicit Neural Representations","date":"2022-04-05","arxiv_id":"2204.02405","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-information-estimation-for-graph","title":"Mutual information estimation for graph convolutional neural networks","date":"2022-03-31","arxiv_id":"2203.16887","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-single-long-short-term-memory-network-for","title":"A single Long Short-Term Memory network for enhancing the prediction of path-dependent plasticity with material heterogeneity and anisotropy","date":"2022-03-29","arxiv_id":"2204.01466","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-localness-transformer-for-smart","title":"Efficient Localness Transformer for Smart Sensor-Based Energy Disaggregation","date":"2022-03-29","arxiv_id":"2203.16537","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-mix-example-interpolation","title":"Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translation","date":"2022-03-15","arxiv_id":"2203.07627","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-networks-for-relational","title":"Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control","date":"2022-03-11","arxiv_id":"2203.05985","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-deep-signed-distance-fields-for","title":"Regularized Deep Signed Distance Fields for Reactive Motion Generation","date":"2022-03-09","arxiv_id":"2203.04739","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-transitive-information-theory-and-its","title":"The Transitive Information Theory and its Application to Deep Generative Models","date":"2022-03-09","arxiv_id":"2203.05074","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-networks-for-image","title":"Graph Neural Networks for Image Classification and Reinforcement Learning using Graph representations","date":"2022-03-07","arxiv_id":"2203.03457","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-multi-scale-learning-for-outcome","title":"Multi-Task Multi-Scale Learning For Outcome Prediction in 3D PET Images","date":"2022-03-01","arxiv_id":"2203.00641","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-grammars-augmenting-transformer","title":"Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale","date":"2022-03-01","arxiv_id":"2203.00633","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multi-task-gaussian-process-over","title":"Learning Multi-Task Gaussian Process Over Heterogeneous Input Domains","date":"2022-02-25","arxiv_id":"2202.12636","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-dynamics-and-structure-of-complex","title":"Learning Dynamics and Structure of Complex Systems Using Graph Neural Networks","date":"2022-02-22","arxiv_id":"2202.10996","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometrically-equivariant-graph-neural","title":"Geometrically Equivariant Graph Neural Networks: A Survey","date":"2022-02-15","arxiv_id":"2202.07230","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuously-generalized-ordinal-regression","title":"Continuously Generalized Ordinal Regression for Linear and Deep Models","date":"2022-02-14","arxiv_id":"2202.07005","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-no-free-lunch-theorems-of-supervised","title":"The no-free-lunch theorems of supervised learning","date":"2022-02-09","arxiv_id":"2202.04513","repositories_listed":0,"syntology":null},{"url":null,"slug":"rigidity-preserving-image-transformations-and","title":"Rigidity Preserving Image Transformations and Equivariance in Perspective","date":"2022-01-31","arxiv_id":"2201.13065","repositories_listed":0,"syntology":null},{"url":null,"slug":"autodistil-few-shot-task-agnostic-neural","title":"AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models","date":"2022-01-29","arxiv_id":"2201.12507","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-coordinate-with-humans-using","title":"Learning Intuitive Policies Using Action Features","date":"2022-01-29","arxiv_id":"2201.12658","repositories_listed":0,"syntology":null},{"url":null,"slug":"invariant-representation-driven-neural","title":"Invariant Representation Driven Neural Classifier for Anti-QCD Jet Tagging","date":"2022-01-18","arxiv_id":"2201.07199","repositories_listed":0,"syntology":null},{"url":null,"slug":"destr-object-detection-with-split-transformer","title":"DESTR: Object Detection With Split Transformer","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knn-local-attention-for-image-restoration","title":"KNN Local Attention for Image Restoration","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"data-efficient-learning-for-3d-mirror","title":"NeRD++: Improved 3D-mirror symmetry learning from a single image","date":"2021-12-23","arxiv_id":"2112.12579","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-proximal-learning-for-high-resolution","title":"Deep Proximal Learning for High-Resolution Plane Wave Compounding","date":"2021-12-23","arxiv_id":"2112.12410","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-transformation-invariant-geometric","title":"Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?","date":"2021-12-23","arxiv_id":"2112.12345","repositories_listed":0,"syntology":null},{"url":null,"slug":"locformer-enabling-transformers-to-perform","title":"LocFormer: Enabling Transformers to Perform Temporal Moment Localization on Long Untrimmed Videos With a Feature Sampling Approach","date":"2021-12-19","arxiv_id":"2112.10066","repositories_listed":0,"syntology":null},{"url":null,"slug":"gopher-categorical-probabilistic-forecasting-1","title":"GOPHER: Categorical probabilistic forecasting with graph structure via local continuous-time dynamics","date":"2021-12-18","arxiv_id":"2112.09964","repositories_listed":0,"syntology":null},{"url":null,"slug":"ace-bert-adversarial-cross-modal-enhanced","title":"ACE-BERT: Adversarial Cross-modal Enhanced BERT for E-commerce Retrieval","date":"2021-12-14","arxiv_id":"2112.07209","repositories_listed":0,"syntology":null},{"url":null,"slug":"equivariant-quantum-graph-circuits","title":"Equivariant Quantum Graph Circuits","date":"2021-12-10","arxiv_id":"2112.05261","repositories_listed":0,"syntology":null},{"url":null,"slug":"lctr-on-awakening-the-local-continuity-of","title":"LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization","date":"2021-12-10","arxiv_id":"2112.05291","repositories_listed":0,"syntology":null},{"url":null,"slug":"skeletal-graph-self-attention-embedding-a","title":"Skeletal Graph Self-Attention: Embedding a Skeleton Inductive Bias into Sign Language Production","date":"2021-12-06","arxiv_id":"2112.05277","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-carotid-artery-vessel","title":"Deep Learning-Based Carotid Artery Vessel Wall Segmentation in Black-Blood MRI Using Anatomical Priors","date":"2021-12-02","arxiv_id":"2112.01137","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-gaussian-process-bayesian-bernoulli-mixture","title":"A Gaussian Process-Bayesian Bernoulli Mixture Model for Multi-Label Active Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-learn-dense-gaussian-processes","title":"Learning to Learn Dense Gaussian Processes for Few-Shot Learning","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-instantiated-recurrent-units-with","title":"Self-Instantiated Recurrent Units with Dynamic Soft Recursion","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-flatland-pre-training-with-a-strong-3d","title":"Beyond Flatland: Pre-training with a Strong 3D Inductive Bias","date":"2021-11-30","arxiv_id":"2112.00113","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuron-with-steady-response-leads-to-better","title":"Neuron with Steady Response Leads to Better Generalization","date":"2021-11-30","arxiv_id":"2111.15414","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-fields-as-learnable-kernels-for-3d","title":"Neural Fields as Learnable Kernels for 3D Reconstruction","date":"2021-11-26","arxiv_id":"2111.13674","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-without-the-magic-inductive-bias-of-1","title":"Depth Without the Magic: Inductive Bias of Natural Gradient Descent","date":"2021-11-22","arxiv_id":"2111.11542","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-query-key-and-value-embedding-in","title":"Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints","date":"2021-11-19","arxiv_id":"2111.10017","repositories_listed":0,"syntology":null},{"url":null,"slug":"sdcup-schema-dependency-enhanced-curriculum","title":"Linking-Enhanced Pre-Training for Table Semantic Parsing","date":"2021-11-18","arxiv_id":"2111.09486","repositories_listed":0,"syntology":null},{"url":null,"slug":"co-training-an-unsupervised-constituency-1","title":"Co-training an Unsupervised Constituency Parser with Weak Supervision","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coloring-the-blank-slate-pre-training-imparts","title":"Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-learning-via-language-model-in-context-1","title":"Meta-learning via Language Model In-context Tuning","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nenet-monocular-depth-estimation-via-neural","title":"Towards Comprehensive Monocular Depth Estimation: Multiple Heads Are Better Than One","date":"2021-11-16","arxiv_id":"2111.08313","repositories_listed":0,"syntology":null},{"url":null,"slug":"trig-transformer-based-text-recognizer-with","title":"TRIG: Transformer-Based Text Recognizer with Initial Embedding Guidance","date":"2021-11-16","arxiv_id":"2111.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-in-the-machine-integrating-physical","title":"Physics in the Machine: Integrating Physical Knowledge in Autonomous Phase-Mapping","date":"2021-11-15","arxiv_id":"2111.07478","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-neural-processes-1","title":"Multi-Task Neural Processes","date":"2021-11-10","arxiv_id":"2111.05820","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-relational-model-for-one-shot","title":"A Relational Model for One-Shot Classification","date":"2021-11-08","arxiv_id":"2111.04313","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmentations-in-graph-contrastive-learning","title":"Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices","date":"2021-11-05","arxiv_id":"2111.03220","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-waveform-based-acoustic-models","title":"Towards Robust Waveform-Based Acoustic Models","date":"2021-10-16","arxiv_id":"2110.08634","repositories_listed":0,"syntology":null},{"url":null,"slug":"editvae-unsupervised-part-aware-controllable","title":"EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation","date":"2021-10-13","arxiv_id":"2110.06679","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-inductive-bias-of-in-context-learning-1","title":"The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design","date":"2021-10-09","arxiv_id":"2110.04541","repositories_listed":0,"syntology":null},{"url":null,"slug":"lagrangian-neural-network-with-differential","title":"Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias","date":"2021-10-07","arxiv_id":"2110.03266","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-the-inductive-bias-of-large","title":"Leveraging the Inductive Bias of Large Language Models for Abstract Textual Reasoning","date":"2021-10-05","arxiv_id":"2110.02370","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstruction-for-powerful-graph","title":"Reconstruction for Powerful Graph Representations","date":"2021-10-01","arxiv_id":"2110.00577","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-principled-permutation-invariant-approach","title":"A Principled Permutation Invariant Approach to Mean-Field Multi-Agent Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"brain-insights-improve-rnns-accuracy-and","title":"Brain insights improve RNNs' accuracy and robustness for hierarchical control of continually learned autonomous motor motifs","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"crossformer-transformer-with-alternated-cross","title":"Crossformer: Transformer with Alternated Cross-Layer Guidance","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eqr-equivariant-representations-for-data","title":"EqR: Equivariant Representations for Data-Efficient Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"equivariant-neural-network-for-factor-graphs","title":"Equivariant Neural Network for Factor Graphs","date":"2021-09-29","arxiv_id":"2109.14218","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-deal-with-missing-data-in-supervised","title":"How to deal with missing data in supervised deep learning?","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"icy-a-benchmark-for-measuring-compositional","title":"Icy: A benchmark for measuring compositional inductive bias of emergent communication models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"inductive-relation-prediction-using-analogy","title":"Inductive Relation Prediction Using Analogy Subgraph Embeddings","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"is-heterophily-a-real-nightmare-for-graph-1","title":"Is Heterophily A Real Nightmare For Graph Neural Networks on Performing Node Classification?","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-symmetric-representations-for","title":"Learning Symmetric Representations for Equivariant World Models","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-label-correlations-implicitly","title":"Modeling label correlations implicitly through latent label encodings for multi-label text classification","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"momentum-conserving-lagrangian-neural","title":"Momentum Conserving Lagrangian Neural Networks","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-tangent-kernel-eigenvalues-accurately-1","title":"Neural tangent kernel eigenvalues accurately predict generalization","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"neurosed-learning-subgraph-similarity-via","title":"NeuroSED: Learning Subgraph Similarity via Graph Neural Networks","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-disentanglement-network","title":"Recursive Disentanglement Network","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"shaped-rewards-bias-emergent-language","title":"Shaped Rewards Bias Emergent Language","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"trivial-or-impossible-dichotomous-data","title":"Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-learning-of-disentangled","title":"Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-coordination-via-semantic","title":"Zero-Shot Coordination via Semantic Relationships Between Actions and Observations","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imagenet-suffers-from-dichotomous-data","title":"ImageNet suffers from dichotomous data difficulty","date":"2021-09-28","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"daren-a-collaborative-approach-towards","title":"DAReN: A Collaborative Approach Towards Reasoning And Disentangling","date":"2021-09-27","arxiv_id":"2109.13156","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-motif-interactions-from","title":"Uncovering motif interactions from convolutional-attention networks for genomics","date":"2021-09-24","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gopher-categorical-probabilistic-forecasting","title":"GOPHER: Categorical probabilistic forecasting withgraph structure via local continuous-time dynamics","date":"2021-09-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"remixers-a-mixer-transformer-architecture","title":"Remixers: A Mixer-Transformer Architecture with Compositional Operators for Natural Language Understanding","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-vs-model-architectures-how-does","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling? An Extensive Empirical Study on Language Tasks","date":"2021-09-17","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"good-enough-example-extrapolation","title":"Good-Enough Example Extrapolation","date":"2021-09-12","arxiv_id":"2109.05602","repositories_listed":0,"syntology":null},{"url":"/paper/is-heterophily-a-real-nightmare-for-graph","slug":"is-heterophily-a-real-nightmare-for-graph","title":"Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?","date":"2021-09-12","arxiv_id":"2109.05641","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-positional-encodings-on","title":"The Impact of Positional Encodings on Multilingual Compression","date":"2021-09-11","arxiv_id":"2109.05388","repositories_listed":0,"syntology":null},{"url":null,"slug":"power-to-the-relational-inductive-bias-graph","title":"Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids","date":"2021-09-08","arxiv_id":"2109.03604","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-learning-via-dependency-maximization","title":"Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis","date":"2021-09-07","arxiv_id":"2109.02820","repositories_listed":0,"syntology":null},{"url":null,"slug":"convnets-vs-transformers-whose-visual","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","date":"2021-08-11","arxiv_id":"2108.05305","repositories_listed":0,"syntology":null}],"record_sha256":"bdabe61663b97571db942635cded54d850b81dca3c8ce8434b52ca1172865385","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}