Methods › General › Optimization › ADOPT
ADaptive gradient method with the OPTimal convergence rate
ADOPT
Introduced by Shohei Taniguchi et al. in ADOPT: Modified Adam Can Converge with Any β₂ with the Optimal Rate
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The archive carries only a placeholder description for this method.
In Syntology verified reference implementation at level V3; retrieve with get_reference_implementation(name='ADOPT'). This answer is about arXiv:2411.02853, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2411.02853 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 14 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; 10 where Syntology's instrument failed) · 9 unverified (of 23 harvested samples) · 4 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 831 · with a code link: 256 · where Syntology ran a sample: 52 (46 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (52 of 831 tagged: 46 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 9: papers 1 to 100 of 831, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
RegCL: Continual Adaptation of Segment Anything Model via Model Merging 16 Jul 2025 · 0 repositories · arXiv:2507.12297
-
Efficient Discovery of Actual Causality with Uncertainty 11 Jul 2025 · 0 repositories · arXiv:2507.09000
-
Fairness Is Not Enough: Auditing Competence and Intersectional Bias in AI-powered Resume Screening 11 Jul 2025 · 1 repository · arXiv:2507.11548
-
RAPS-3D: Efficient interactive segmentation for 3D radiological imaging 10 Jul 2025 · 0 repositories · arXiv:2507.07730
-
Integrated Structural Prompt Learning for Vision-Language Models 8 Jul 2025 · 0 repositories · arXiv:2507.05677
-
Unconditional Diffusion for Generative Sequential Recommendation 8 Jul 2025 · 0 repositories · arXiv:2507.06121
-
Kalman Filter Aided Federated Koopman Learning 7 Jul 2025 · 0 repositories · arXiv:2507.04808
-
Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model 7 Jul 2025 · 0 repositories · arXiv:2507.05513
-
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting 7 Jul 2025 · 1 repository · arXiv:2507.05116Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
Advanced Financial Reasoning at Scale: A Comprehensive Evaluation of Large Language Models on CFA Level III 29 Jun 2025 · 0 repositories · arXiv:2507.02954
-
Potential Customer Lifetime Value in Financial Institutions: The Usage Of Open Banking Data to Improve CLV Estimation 28 Jun 2025 · 0 repositories · arXiv:2506.22711
-
DBConformer: Dual-Branch Convolutional Transformer for EEG Decoding 26 Jun 2025 · 1 repository · arXiv:2506.21140
-
Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments 26 Jun 2025 · 0 repositories · arXiv:2506.21497
-
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model 26 Jun 2025 · 1 repository · arXiv:2506.20923
-
Point Cloud Environment-Based Channel Knowledge Map Construction 26 Jun 2025 · 0 repositories · arXiv:2506.21112
-
YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection 26 Jun 2025 · 0 repositories · arXiv:2506.21135
-
Define-ML: An Approach to Ideate Machine Learning-Enabled Systems 25 Jun 2025 · 0 repositories · arXiv:2506.20621
-
Fusing Radiomic Features with Deep Representations for Gestational Age Estimation in Fetal Ultrasound Images 25 Jun 2025 · 0 repositories · arXiv:2506.20407
-
Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learning 25 Jun 2025 · 0 repositories · arXiv:2506.20651
-
Diffusion-based Task-oriented Semantic Communications with Model Inversion Attack 24 Jun 2025 · 0 repositories · arXiv:2506.19886
-
Finite-Horizon Strategy in Infinite-Horizon Linear-Quadratic Discrete-Time Dynamic Games 24 Jun 2025 · 0 repositories · arXiv:2506.19565
-
On the efficacy of old features for the detection of new bots 24 Jun 2025 · 0 repositories · arXiv:2506.19635
-
Open-Vocabulary Camouflaged Object Segmentation with Cascaded Vision Language Models 24 Jun 2025 · 1 repository · arXiv:2506.19300
-
A Multi-Scale Spatial Attention-Based Zero-Shot Learning Framework for Low-Light Image Enhancement 23 Jun 2025 · 0 repositories · arXiv:2506.18323
-
DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling 23 Jun 2025 · 1 repository · arXiv:2506.18680
-
Let Your Video Listen to Your Music! 23 Jun 2025 · 0 repositories · arXiv:2506.18881
-
TrajTok: Technical Report for 2025 Waymo Open Sim Agents Challenge 23 Jun 2025 · 0 repositories · arXiv:2506.21618
-
Non-Euclidean Enriched Contraction Theory for Monotone Operators and Monotone Dynamical Systems 22 Jun 2025 · 0 repositories · arXiv:2506.17990
-
Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown 21 Jun 2025 · 0 repositories · arXiv:2506.17589Syntology 4 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; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
BIDA: A Bi-level Interaction Decision-making Algorithm for Autonomous Vehicles in Dynamic Traffic Scenarios 19 Jun 2025 · 0 repositories · arXiv:2506.16546
-
CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning 19 Jun 2025 · 1 repository · arXiv:2506.17345
-
Fast Training-free Perceptual Image Compression 19 Jun 2025 · 0 repositories · arXiv:2506.16102
-
Unpacking Generative AI in Education: Computational Modeling of Teacher and Student Perspectives in Social Media Discourse 19 Jun 2025 · 0 repositories · arXiv:2506.16412
-
How does online shopping affect offline price sensitivity? 18 Jun 2025 · 0 repositories · arXiv:2506.15103
-
A multi-stage augmented multimodal interaction network for fish feeding intensity quantification 17 Jun 2025 · 0 repositories · arXiv:2506.14170
-
Balancing Caregiving and Self-Care: Exploring Mental Health Needs of Alzheimer's and Dementia Caregivers 17 Jun 2025 · 0 repositories · arXiv:2506.14196
-
KDMOS:Knowledge Distillation for Motion Segmentation 17 Jun 2025 · 1 repository · arXiv:2506.14130
-
Multi-Scale Finetuning for Encoder-based Time Series Foundation Models 17 Jun 2025 · 0 repositories · arXiv:2506.14087Syntology 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Discrete Diffusion in Large Language and Multimodal Models: A Survey 16 Jun 2025 · 1 repository · arXiv:2506.13759
-
Surprise Calibration for Better In-Context Learning 15 Jun 2025 · 0 repositories · arXiv:2506.12796
-
Transforming Chatbot Text: A Sequence-to-Sequence Approach 15 Jun 2025 · 0 repositories · arXiv:2506.12843
-
Adaptive Multi-resolution Hash-Encoding Framework for INR-based Dental CBCT Reconstruction with Truncated FOV 14 Jun 2025 · 0 repositories · arXiv:2506.12471
-
Collaborative Interest-aware Graph Learning for Group Identification 13 Jun 2025 · 0 repositories · arXiv:2506.14826
-
Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning 13 Jun 2025 · 0 repositories · arXiv:2506.11672
-
Prioritizing Alignment Paradigms over Task-Specific Model Customization in Time-Series LLMs 13 Jun 2025 · 1 repository · arXiv:2506.11512
-
Energy Aware Camera Location Search Algorithm for Increasing Precision of Observation in Automated Manufacturing 12 Jun 2025 · 0 repositories · arXiv:2506.10251
-
Structure and asymptotic preserving deep neural surrogates for uncertainty quantification in multiscale kinetic equations 12 Jun 2025 · 0 repositories · arXiv:2506.10636
-
Closer to Language than Steam: AI as the Cognitive Engine of a New Productivity Revolution 12 Jun 2025 · 0 repositories · arXiv:2506.10281
-
MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning 12 Jun 2025 · 0 repositories · arXiv:2506.10963
-
Motion-R1: Chain-of-Thought Reasoning and Reinforcement Learning for Human Motion Generation 12 Jun 2025 · 0 repositories · arXiv:2506.10353
-
MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling 12 Jun 2025 · 1 repository · arXiv:2506.10609Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Robustly Improving LLM Fairness in Realistic Settings via Interpretability 12 Jun 2025 · 1 repository · arXiv:2506.10922
-
Sampling-Based Planning Under STL Specifications: A Forward Invariance Approach 12 Jun 2025 · 0 repositories · arXiv:2506.10739
-
Eigenvalue-Based Detection in MIMO Systems for Integrated Sensing and Communication 11 Jun 2025 · 0 repositories · arXiv:2506.09439
-
ODG: Occupancy Prediction Using Dual Gaussians 11 Jun 2025 · 0 repositories · arXiv:2506.09417
-
Q2E: Query-to-Event Decomposition for Zero-Shot Multilingual Text-to-Video Retrieval 11 Jun 2025 · 0 repositories · arXiv:2506.10202
-
S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation 11 Jun 2025 · 0 repositories · arXiv:2506.11160
-
Hyperbolic Dual Feature Augmentation for Open-Environment 10 Jun 2025 · 0 repositories · arXiv:2506.08906
-
ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs 10 Jun 2025 · 0 repositories · arXiv:2506.09282
-
Computation Capacity Maximization for Pinching Antennas-Assisted Wireless Powered MEC Systems 9 Jun 2025 · 0 repositories · arXiv:2506.07598
-
Diffusion Models-Aided Uplink Channel Estimation for RIS-Assisted Systems 9 Jun 2025 · 0 repositories · arXiv:2506.07770
-
Fine-Grained Motion Compression and Selective Temporal Fusion for Neural B-Frame Video Coding 9 Jun 2025 · 0 repositories · arXiv:2506.07709
-
LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization 9 Jun 2025 · 0 repositories · arXiv:2506.07570
-
Simulating nationwide coupled disease and fear spread in an agent-based model 9 Jun 2025 · 0 repositories · arXiv:2506.07842
-
Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification 8 Jun 2025 · 1 repository · arXiv:2506.07235
-
Quantile-Optimal Policy Learning under Unmeasured Confounding 8 Jun 2025 · 0 repositories · arXiv:2506.07140
-
The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing 7 Jun 2025 · 0 repositories · arXiv:2506.06761
-
(AI peers) are people learning from the same standpoint: Perception of AI characters in a Collaborative Science Investigation 6 Jun 2025 · 0 repositories · arXiv:2506.06165
-
Generating Long Semantic IDs in Parallel for Recommendation 6 Jun 2025 · 1 repository · arXiv:2506.05781
-
Information Bargaining: Bilateral Commitment in Bayesian Persuasion 6 Jun 2025 · 1 repository · arXiv:2506.05876
-
PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time 6 Jun 2025 · 0 repositories · arXiv:2506.06254
-
Demonstrations of Integrity Attacks in Multi-Agent Systems 5 Jun 2025 · 0 repositories · arXiv:2506.04572
-
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts 5 Jun 2025 · 1 repository · arXiv:2506.05229
-
Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective 5 Jun 2025 · 0 repositories · arXiv:2506.05166
-
LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs 5 Jun 2025 · 1 repository · arXiv:2506.05260
-
MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning 5 Jun 2025 · 1 repository · arXiv:2506.05331
-
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning 5 Jun 2025 · 0 repositories · arXiv:2506.05214
-
Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights 5 Jun 2025 · 0 repositories · arXiv:2506.04851
-
On the Mechanism of Reasoning Pattern Selection in Reinforcement Learning for Language Models 5 Jun 2025 · 0 repositories · arXiv:2506.04695
-
Using In-Context Learning for Automatic Defect Labelling of Display Manufacturing Data 5 Jun 2025 · 0 repositories · arXiv:2506.04717
-
Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care 4 Jun 2025 · 0 repositories · arXiv:2506.04389
-
My Advisor, Her AI and Me: Evidence from a Field Experiment on Human-AI Collaboration and Investment Decisions 4 Jun 2025 · 0 repositories · arXiv:2506.03707
-
OSGNet @ Ego4D Episodic Memory Challenge 2025 4 Jun 2025 · 1 repository · arXiv:2506.03710
-
Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation 4 Jun 2025 · 1 repository · arXiv:2506.03857
-
VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation 4 Jun 2025 · 0 repositories · arXiv:2506.03930
-
An Empirical Study of Group Conformity in Multi-Agent Systems 2 Jun 2025 · 0 repositories · arXiv:2506.01332
-
Captivity-Escape Games as a Means for Safety in Online Motion Generation 2 Jun 2025 · 0 repositories · arXiv:2506.01399
-
WCTC-Biasing: Retraining-free Contextual Biasing ASR with Wildcard CTC-based Keyword Spotting and Inter-layer Biasing 2 Jun 2025 · 0 repositories · arXiv:2506.01263
-
dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generation 31 May 2025 · 1 repository · arXiv:2506.00322
-
Organizational Adaptation to Generative AI in Cybersecurity: A Systematic Review 31 May 2025 · 0 repositories · arXiv:2506.12060
-
A Mathematical Perspective On Contrastive Learning 30 May 2025 · 0 repositories · arXiv:2505.24134
-
Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model 30 May 2025 · 1 repository · arXiv:2505.24476
-
SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling 30 May 2025 · 1 repository · arXiv:2505.24179
-
Semi-structured LLM Reasoners Can Be Rigorously Audited 30 May 2025 · 0 repositories · arXiv:2505.24217
-
SwiftEval: Developing a Language-Specific Benchmark for LLM-generated Code Evaluation 30 May 2025 · 0 repositories · arXiv:2505.24324
-
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces 30 May 2025 · 0 repositories · arXiv:2506.00123
-
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute Recognition 29 May 2025 · 2 repositories · arXiv:2505.23313
-
Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching 29 May 2025 · 0 repositories · arXiv:2505.23346
-
Bridging Source and Target Domains via Link Prediction for Unsupervised Domain Adaptation on Graphs 29 May 2025 · 0 repositories · arXiv:2505.24055
-
Detecting Switching Attacks On Traffic Flow Regulation For Changing Driving Patterns 29 May 2025 · 0 repositories · arXiv:2505.23033
Tasks archive 2025-07-28
20 shown of 546 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections