{"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":"/method/opt","slug":"opt","name":"OPT","full_name":"OPT","full_name_withheld":false,"description_markdown":"**OPT** is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear learning rate schedule, warming up from 0 to the maximum learning rate over the first 2000 steps in OPT-175B, or over 375M tokens in the smaller models, and decaying down to 10% of the maximum LR over 300B tokens. The batch sizes range from 0.5M to 4M depending on the model size and is kept constant throughout the course of training.","description_state":"present","introduced_year":null,"introduced_by":{"title":"OPT: Open Pre-trained Transformer Language Models","paper":"/paper/opt-open-pre-trained-transformer-language","first_author":"Susan Zhang","n_authors":19,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/opt-open-pre-trained-transformer-language"},"source":{"url":"https://arxiv.org/abs/2205.01068v4","title":"OPT: Open Pre-trained Transformer Language Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":285,"archive_num_papers":285,"papers_newest_first":[{"paper":null,"slug":"incentivizing-high-quality-participation-from","title":"Incentivizing High-quality Participation From Federated Learning Agents","date":"2025-06-20","arxiv_id":"2506.16731","n_code_links":0,"syntology":null},{"paper":"/paper/attribution-guided-pruning-for-compression","slug":"attribution-guided-pruning-for-compression","title":"Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs","date":"2025-06-16","arxiv_id":"2506.13727","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixture-of-weight-shared-heterogeneous-group","title":"Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization","date":"2025-06-16","arxiv_id":"2506.13541","n_code_links":0,"syntology":null},{"paper":null,"slug":"tensorslm-energy-efficient-embedding","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","date":"2025-06-16","arxiv_id":"2506.13514","n_code_links":0,"syntology":null},{"paper":null,"slug":"fzoo-fast-zeroth-order-optimizer-for-fine","title":"FZOO: Fast Zeroth-Order Optimizer for Fine-Tuning Large Language Models towards Adam-Scale Speed","date":"2025-06-10","arxiv_id":"2506.09034","n_code_links":0,"syntology":null},{"paper":null,"slug":"conservative-bias-in-large-language-models","title":"Conservative Bias in Large Language Models: Measuring Relation Predictions","date":"2025-06-09","arxiv_id":"2506.08120","n_code_links":0,"syntology":null},{"paper":null,"slug":"nqkv-a-kv-cache-quantization-scheme-based-on","title":"NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics","date":"2025-05-22","arxiv_id":"2505.16210","n_code_links":0,"syntology":null},{"paper":"/paper/polar-sparsity-high-throughput-batched-llm","slug":"polar-sparsity-high-throughput-batched-llm","title":"Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity","date":"2025-05-20","arxiv_id":"2505.14884","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"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","official":{"repos":["susavlsh10/polar-sparsity"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"optimizing-energy-consumption-in-stochastic","title":"Optimizing Energy Consumption in Stochastic Production Systems: Using a Simulation-Based Approach for Stopping Policy","date":"2025-05-14","arxiv_id":"2505.11536","n_code_links":0,"syntology":null},{"paper":null,"slug":"anticipating-gaming-to-incentivize","title":"Anticipating Gaming to Incentivize Improvement: Guiding Agents in (Fair) Strategic Classification","date":"2025-05-08","arxiv_id":"2505.05594","n_code_links":0,"syntology":null},{"paper":null,"slug":"spap-structured-pruning-via-alternating","title":"SPAP: Structured Pruning via Alternating Optimization and Penalty Methods","date":"2025-05-06","arxiv_id":"2505.03373","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-shapley-value-based-non-uniform","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","date":"2025-05-03","arxiv_id":"2505.01731","n_code_links":0,"syntology":null},{"paper":"/paper/unidetox-universal-detoxification-of-large","slug":"unidetox-universal-detoxification-of-large","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","date":"2025-04-29","arxiv_id":"2504.20500","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["EminLU/UniDetox"],"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"]}}},{"paper":null,"slug":"pin-wm-learning-physics-informed-world-models","title":"PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation","date":"2025-04-23","arxiv_id":"2504.16693","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferable-text-data-distillation-by","title":"Transferable text data distillation by trajectory matching","date":"2025-04-14","arxiv_id":"2504.09818","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximum-redundancy-pruning-a-principle-driven","title":"Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs","date":"2025-03-24","arxiv_id":"2503.18377","n_code_links":0,"syntology":null},{"paper":null,"slug":"muma-3d-pbr-texturing-via-multi-channel-multi","title":"MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing","date":"2025-03-24","arxiv_id":"2503.18461","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-bike-absence-influence-mode-shifts","title":"How does Bike Absence Influence Mode Shifts Among Dockless Bike-Sharing Users? Evidence From Nanjing, China","date":"2025-03-18","arxiv_id":"2503.14265","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-finance-estimating","title":"Large language models in finance : what is financial sentiment?","date":"2025-03-05","arxiv_id":"2503.03612","n_code_links":0,"syntology":null},{"paper":"/paper/probe-pruning-accelerating-llms-through","slug":"probe-pruning-accelerating-llms-through","title":"Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing","date":"2025-02-21","arxiv_id":"2502.15618","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"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) · 1 unverified","official":{"repos":["qi-le1/probe_pruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/enhancing-cross-tokenizer-knowledge","slug":"enhancing-cross-tokenizer-knowledge","title":"Enhancing Cross-Tokenizer Knowledge Distillation with Contextual Dynamical Mapping","date":"2025-02-16","arxiv_id":"2502.11104","n_code_links":1,"syntology":null},{"paper":"/paper/the-odyssey-of-the-fittest-can-agents-survive","slug":"the-odyssey-of-the-fittest-can-agents-survive","title":"The Odyssey of the Fittest: Can Agents Survive and Still Be Good?","date":"2025-02-08","arxiv_id":"2502.05442","n_code_links":1,"syntology":null},{"paper":"/paper/green-code-optimizing-energy-efficiency-in","slug":"green-code-optimizing-energy-efficiency-in","title":"GREEN-CODE: Learning to Optimize Energy Efficiency in LLM-based Code Generation","date":"2025-01-19","arxiv_id":"2501.11006","n_code_links":1,"syntology":null},{"paper":null,"slug":"fasp-fast-and-accurate-structured-pruning-of","title":"FASP: Fast and Accurate Structured Pruning of Large Language Models","date":"2025-01-16","arxiv_id":"2501.09412","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-llms-struggle-to-link","slug":"multilingual-llms-struggle-to-link","title":"Multilingual LLMs Struggle to Link Orthography and Semantics in Bilingual Word Processing","date":"2025-01-15","arxiv_id":"2501.09127","n_code_links":1,"syntology":null},{"paper":null,"slug":"has-an-ai-model-been-trained-on-your-images","title":"Has an AI model been trained on your images?","date":"2025-01-11","arxiv_id":"2501.06399","n_code_links":0,"syntology":null},{"paper":"/paper/explore-activation-sparsity-in-recurrent-llms","slug":"explore-activation-sparsity-in-recurrent-llms","title":"Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing","date":"2025-01-09","arxiv_id":"2501.16337","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-sparse-signal-to-smooth-motion-real-time","title":"From Sparse Signal to Smooth Motion: Real-Time Motion Generation with Rolling Prediction Models","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sentiment-trading-with-large-language-models","title":"Sentiment trading with large language models","date":"2024-12-26","arxiv_id":"2412.19245","n_code_links":0,"syntology":null},{"paper":null,"slug":"ragonite-iterative-retrieval-on-induced","title":"RAGONITE: Iterative Retrieval on Induced Databases and Verbalized RDF for Conversational QA over KGs with RAG","date":"2024-12-23","arxiv_id":"2412.17690","n_code_links":0,"syntology":null},{"paper":null,"slug":"sharp-results-for-hypothesis-testing-with","title":"Sharp Results for Hypothesis Testing with Risk-Sensitive Agents","date":"2024-12-21","arxiv_id":"2412.16452","n_code_links":0,"syntology":null},{"paper":"/paper/variability-need-not-imply-error-the-case-of","slug":"variability-need-not-imply-error-the-case-of","title":"Variability Need Not Imply Error: The Case of Adequate but Semantically Distinct Responses","date":"2024-12-20","arxiv_id":"2412.15683","n_code_links":1,"syntology":null},{"paper":null,"slug":"sequence-level-analysis-of-leakage-risk-of","title":"Sequence-Level Leakage Risk of Training Data in Large Language Models","date":"2024-12-15","arxiv_id":"2412.11302","n_code_links":0,"syntology":null},{"paper":"/paper/razor-sharpening-knowledge-by-cutting-bias","slug":"razor-sharpening-knowledge-by-cutting-bias","title":"RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting","date":"2024-12-10","arxiv_id":"2412.07675","n_code_links":1,"syntology":null},{"paper":"/paper/augmenting-the-action-space-with-conventions","slug":"augmenting-the-action-space-with-conventions","title":"Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi","date":"2024-12-09","arxiv_id":"2412.06333","n_code_links":1,"syntology":null},{"paper":null,"slug":"taming-sensitive-weights-noise-perturbation","title":"Taming Sensitive Weights : Noise Perturbation Fine-tuning for Robust LLM Quantization","date":"2024-12-08","arxiv_id":"2412.06858","n_code_links":0,"syntology":null},{"paper":null,"slug":"iternorm-fast-iterative-normalization","title":"IterL2Norm: Fast Iterative L2-Normalization","date":"2024-12-06","arxiv_id":"2412.04778","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-generative-ai-on-student-churn","title":"The Impact of Generative AI on Student Churn and the Future of Formal Education","date":"2024-11-30","arxiv_id":"2412.00605","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-extensive-evaluation-of-factual","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-performance-of-the-lstm-based-code","title":"The Performance of the LSTM-based Code Generated by Large Language Models (LLMs) in Forecasting Time Series Data","date":"2024-11-27","arxiv_id":"2411.18731","n_code_links":0,"syntology":null},{"paper":null,"slug":"strategic-prompting-for-conversational-tasks","title":"Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks","date":"2024-11-26","arxiv_id":"2411.17204","n_code_links":0,"syntology":null},{"paper":null,"slug":"anda-unlocking-efficient-llm-inference-with-a","title":"Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format","date":"2024-11-24","arxiv_id":"2411.15982","n_code_links":0,"syntology":null},{"paper":"/paper/robust-detection-of-watermarks-for-large","slug":"robust-detection-of-watermarks-for-large","title":"Robust Detection of Watermarks for Large Language Models Under Human Edits","date":"2024-11-21","arxiv_id":"2411.13868","n_code_links":1,"syntology":null},{"paper":null,"slug":"real-time-adapting-routing-rar-improving","title":"Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models","date":"2024-11-14","arxiv_id":"2411.09837","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-the-effects-of-human-written","slug":"understanding-the-effects-of-human-written","title":"Understanding the Effects of Human-written Paraphrases in LLM-generated Text Detection","date":"2024-11-06","arxiv_id":"2411.03806","n_code_links":1,"syntology":null},{"paper":"/paper/explaining-and-improving-contrastive-decoding","slug":"explaining-and-improving-contrastive-decoding","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","date":"2024-11-03","arxiv_id":"2411.01610","n_code_links":1,"syntology":null},{"paper":null,"slug":"reconstruction-of-differentially-private-text","title":"Reconstruction of Differentially Private Text Sanitization via Large Language Models","date":"2024-10-16","arxiv_id":"2410.12443","n_code_links":0,"syntology":null},{"paper":"/paper/disp-llm-dimension-independent-structural","slug":"disp-llm-dimension-independent-structural","title":"DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11988","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":3,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhengaoLi/DISP-LLM-Dimension-Independent-Structural-Pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"simultaneous-computation-and-memory-efficient","title":"Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models","date":"2024-10-13","arxiv_id":"2410.09823","n_code_links":0,"syntology":null},{"paper":null,"slug":"crossquant-a-post-training-quantization","title":"CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression","date":"2024-10-10","arxiv_id":"2410.07505","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-model-for-less-resourced-language","title":"Generative Model for Less-Resourced Language with 1 billion parameters","date":"2024-10-09","arxiv_id":"2410.06898","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-information-acquisition-strategies","title":"Optimal Information Acquisition Strategies: The Case of Online Lending","date":"2024-10-07","arxiv_id":"2410.05539","n_code_links":0,"syntology":null},{"paper":"/paper/timer-xl-long-context-transformers-for","slug":"timer-xl-long-context-transformers-for","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","date":"2024-10-07","arxiv_id":"2410.04803","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-using-reinforcement-learning-for","title":"Towards using Reinforcement Learning for Scaling and Data Replication in Cloud Systems","date":"2024-10-07","arxiv_id":"2410.11862","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-event-streams-with-deep","title":"Leveraging Event Streams with Deep Reinforcement Learning for End-to-End UAV Tracking","date":"2024-10-03","arxiv_id":"2410.14685","n_code_links":0,"syntology":null},{"paper":null,"slug":"harnessing-diversity-for-important-data","title":"Harnessing Diversity for Important Data Selection in Pretraining Large Language Models","date":"2024-09-25","arxiv_id":"2409.16986","n_code_links":0,"syntology":null},{"paper":null,"slug":"analog-beamforming-aided-by-full-dimension","title":"Analog Beamforming Aided by Full-Dimension One-Bit Chains","date":"2024-09-10","arxiv_id":"2409.06819","n_code_links":0,"syntology":null},{"paper":"/paper/a-coin-has-two-sides-a-novel-detector","slug":"a-coin-has-two-sides-a-novel-detector","title":"A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction","date":"2024-09-06","arxiv_id":"2409.04150","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-llm-context-distillation","title":"Efficient LLM Context Distillation","date":"2024-09-03","arxiv_id":"2409.01930","n_code_links":0,"syntology":null},{"paper":null,"slug":"imagining-from-images-with-an-ai-storytelling","title":"Imagining from Images with an AI Storytelling Tool","date":"2024-08-21","arxiv_id":"2408.11517","n_code_links":0,"syntology":null},{"paper":"/paper/llm-barber-block-aware-rebuilder-for-sparsity","slug":"llm-barber-block-aware-rebuilder-for-sparsity","title":"LLM-Barber: Block-Aware Rebuilder for Sparsity Mask in One-Shot for Large Language Models","date":"2024-08-20","arxiv_id":"2408.10631","n_code_links":1,"syntology":null},{"paper":null,"slug":"modegpt-modular-decomposition-for-large","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","date":"2024-08-19","arxiv_id":"2408.09632","n_code_links":0,"syntology":null},{"paper":null,"slug":"wpn-an-unlearning-method-based-on-n-pair","title":"WPN: An Unlearning Method Based on N-pair Contrastive Learning in Language Models","date":"2024-08-18","arxiv_id":"2408.09459","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-nah-bandit-modeling-user-non-compliance","title":"The Nah Bandit: Modeling User Non-compliance in Recommendation Systems","date":"2024-08-15","arxiv_id":"2408.07897","n_code_links":0,"syntology":null},{"paper":null,"slug":"decentralized-intelligence-health-network","title":"Decentralized Health Intelligence Network (DHIN)","date":"2024-08-12","arxiv_id":"2408.06240","n_code_links":0,"syntology":null},{"paper":"/paper/eigen-attention-attention-in-low-rank-space","slug":"eigen-attention-attention-in-low-rank-space","title":"Eigen Attention: Attention in Low-Rank Space for KV Cache Compression","date":"2024-08-10","arxiv_id":"2408.05646","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":5,"n_instrument":4,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["utkarshsaxena1/eigenattn"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-convex-optimization-based-layer-wise-post","title":"A Convex-optimization-based Layer-wise Post-training Pruner for Large Language Models","date":"2024-08-07","arxiv_id":"2408.03728","n_code_links":0,"syntology":null},{"paper":"/paper/2408-03247","slug":"2408-03247","title":"Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons","date":"2024-08-06","arxiv_id":"2408.03247","n_code_links":1,"syntology":null},{"paper":null,"slug":"2408-01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","date":"2024-08-03","arxiv_id":"2408.01803","n_code_links":0,"syntology":null},{"paper":null,"slug":"a2sf-accumulative-attention-scoring-with","title":"A2SF: Accumulative Attention Scoring with Forgetting Factor for Token Pruning in Transformer Decoder","date":"2024-07-30","arxiv_id":"2407.20485","n_code_links":0,"syntology":null},{"paper":null,"slug":"nudging-consent-and-the-new-opt-out-system-to","title":"Nudging Consent and the New Opt Out System to the Processing of Health Data in England","date":"2024-07-28","arxiv_id":"2407.19447","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-model-size-on-fine-tuned-llm","title":"Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation","date":"2024-07-19","arxiv_id":"2407.14088","n_code_links":0,"syntology":null},{"paper":null,"slug":"mini-llm-memory-efficient-structured-pruning","title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","date":"2024-07-16","arxiv_id":"2407.11681","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-llms-for-optimization-modeling","slug":"benchmarking-llms-for-optimization-modeling","title":"OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling","date":"2024-07-13","arxiv_id":"2407.09887","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["yangzhch6/ReSocratic"],"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"]}}},{"paper":null,"slug":"multi-token-joint-speculative-decoding-for","title":"Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference","date":"2024-07-12","arxiv_id":"2407.09722","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-learning-rate-scheduler-with","title":"Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice","date":"2024-07-10","arxiv_id":"2407.07613","n_code_links":0,"syntology":null},{"paper":null,"slug":"sinkhorn-algorithms-and-linear-programming","title":"Sinkhorn algorithms and linear programming solvers for optimal partial transport problems","date":"2024-07-09","arxiv_id":"2407.06481","n_code_links":0,"syntology":null},{"paper":null,"slug":"lateralization-lora-interleaved-instruction","title":"Lateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations","date":"2024-07-04","arxiv_id":"2407.03604","n_code_links":0,"syntology":null},{"paper":"/paper/freetraj-tuning-free-trajectory-control-in","slug":"freetraj-tuning-free-trajectory-control-in","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","date":"2024-06-24","arxiv_id":"2406.16863","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":7,"n_instrument":5,"unverified":3,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["arthur-qiu/freetraj"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/shadowllm-predictor-based-contextual-sparsity","slug":"shadowllm-predictor-based-contextual-sparsity","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","date":"2024-06-24","arxiv_id":"2406.16635","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"phrase":"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) · 1 unverified","official":{"repos":["abdelfattah-lab/shadow_llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mitigating-social-biases-in-language-models","title":"Mitigating Social Biases in Language Models through Unlearning","date":"2024-06-19","arxiv_id":"2406.13551","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-large-model-training-through","title":"Optimizing Large Model Training through Overlapped Activation Recomputation","date":"2024-06-13","arxiv_id":"2406.08756","n_code_links":0,"syntology":null},{"paper":"/paper/cattleface-rgbt-rgb-t-cattle-facial-landmark","slug":"cattleface-rgbt-rgb-t-cattle-facial-landmark","title":"CattleFace-RGBT: RGB-T Cattle Facial Landmark Benchmark","date":"2024-06-05","arxiv_id":"2406.03431","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveil-the-duality-of-retrieval-augmented","title":"A Theory for Token-Level Harmonization in Retrieval-Augmented Generation","date":"2024-06-03","arxiv_id":"2406.00944","n_code_links":0,"syntology":null},{"paper":"/paper/decoop-robust-prompt-tuning-with-out-of","slug":"decoop-robust-prompt-tuning-with-out-of","title":"DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection","date":"2024-06-01","arxiv_id":"2406.00345","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":2,"n_instrument":4,"unverified":3,"pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["WNJXYK/DeCoOp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"effective-interplay-between-sparsity-and","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","date":"2024-05-31","arxiv_id":"2405.20935","n_code_links":0,"syntology":null},{"paper":null,"slug":"outliers-and-calibration-sets-have","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","date":"2024-05-31","arxiv_id":"2405.20835","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-watermark-stealing-with","title":"Large Language Model Watermark Stealing With Mixed Integer Programming","date":"2024-05-30","arxiv_id":"2405.19677","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-domain-adaptation-by-transformers","title":"Automatic Domain Adaptation by Transformers in In-Context Learning","date":"2024-05-27","arxiv_id":"2405.16819","n_code_links":0,"syntology":null},{"paper":"/paper/looking-backward-streaming-video-to-video","slug":"looking-backward-streaming-video-to-video","title":"Looking Backward: Streaming Video-to-Video Translation with Feature Banks","date":"2024-05-24","arxiv_id":"2405.15757","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":5,"n_instrument":5,"unverified":2,"pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Jeff-LiangF/streamv2v"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/your-transformer-is-secretly-linear","slug":"your-transformer-is-secretly-linear","title":"Your Transformer is Secretly Linear","date":"2024-05-19","arxiv_id":"2405.12250","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AIRI-Institute/LLM-Microscope"],"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"]}}},{"paper":"/paper/scalarisation-based-risk-concepts-for-robust","slug":"scalarisation-based-risk-concepts-for-robust","title":"Scalarisation-based risk concepts for robust multi-objective optimisation","date":"2024-05-16","arxiv_id":"2405.10221","n_code_links":1,"syntology":null},{"paper":null,"slug":"combining-multiple-post-training-techniques","title":"Post Training Quantization of Large Language Models with Microscaling Formats","date":"2024-05-12","arxiv_id":"2405.07135","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-and-explainable-fine-grained-visual","title":"Robust and Explainable Fine-Grained Visual Classification with Transfer Learning: A Dual-Carriageway Framework","date":"2024-05-09","arxiv_id":"2405.05853","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-order-reasoning-for-time-critical","title":"High Order Reasoning for Time Critical Recommendation in Evidence-based Medicine","date":"2024-05-05","arxiv_id":"2405.03010","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-adversarial-robustness-of-large","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","date":"2024-05-04","arxiv_id":"2405.02764","n_code_links":0,"syntology":null},{"paper":null,"slug":"parameter-efficient-tuning-large-language","title":"Parameter-Efficient Tuning Large Language Models for Graph Representation Learning","date":"2024-04-28","arxiv_id":"2404.18271","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-beat-byterl-exploitability-of","title":"Learning to Beat ByteRL: Exploitability of Collectible Card Game Agents","date":"2024-04-25","arxiv_id":"2404.16689","n_code_links":0,"syntology":null},{"paper":"/paper/does-your-neural-code-completion-model-use-my","slug":"does-your-neural-code-completion-model-use-my","title":"Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach","date":"2024-04-22","arxiv_id":"2404.14296","n_code_links":1,"syntology":null},{"paper":"/paper/towards-reliable-latent-knowledge-estimation","slug":"towards-reliable-latent-knowledge-estimation","title":"Towards Reliable Latent Knowledge Estimation in LLMs: Zero-Prompt Many-Shot Based Factual Knowledge Extraction","date":"2024-04-19","arxiv_id":"2404.12957","n_code_links":1,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":285,"with_a_code_link":123,"where_syntology_ran_a_sample":55,"not_listed_spam_title":0,"listed":285,"listed_where_code_ran":55,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":39,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":39,"listed_every_run_a_failure_of_syntologys_instrument":16,"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"},"papers_where_code_ran":55,"papers_where_code_ran_first_page":"/method/opt/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":3,"url":"/method/opt/papers/2","json":"/method/opt/papers/2.json","rows":100},{"order":"archive","page":3,"of":3,"url":"/method/opt/papers/3","json":"/method/opt/papers/3.json","rows":85},{"order":"ran","page":1,"of":1,"url":"/method/opt/papers/ran/1","json":"/method/opt/papers/ran/1.json","rows":55}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":41},{"task":"/task/language-modeling","name":"Language Modeling","papers":28},{"task":"/task/quantization","name":"Quantization","papers":24},{"task":null,"name":"GPU","papers":22},{"task":"/task/large-language-model","name":"Large Language Model","papers":17},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":14},{"task":"/task/question-answering","name":"Question Answering","papers":14},{"task":"/task/text-generation","name":"Text Generation","papers":12},{"task":"/task/model-compression","name":"Model Compression","papers":8},{"task":"/task/retrieval","name":"Retrieval","papers":8},{"task":"/task/fairness","name":"Fairness","papers":7},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":7},{"task":"/task/translation","name":"Translation","papers":7},{"task":"/task/attribute","name":"Attribute","papers":6},{"task":"/task/benchmarking","name":"Benchmarking","papers":6},{"task":"/task/object-detection","name":"Object Detection","papers":6},{"task":"/task/scheduling","name":"Scheduling","papers":6},{"task":"/task/sentence","name":"Sentence","papers":6},{"task":"/task/object-detection-1","name":"object-detection","papers":6},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":5}],"tasks_shown":20,"n_tasks":247,"usage_by_year":[{"year":"2022","papers":49},{"year":"2023","papers":104},{"year":"2024","papers":104},{"year":"2025","papers":28}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/opt"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=OPT","read_at":"2026-10-05T00:59:54+00:00","query":"OPT","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"OPT","origin_arxiv_id":"2205.01068"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2205.01068","repositories":{"listed":5,"in_graph":11,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":4,"served":{"arxiv_id":"2205.01068","citations":4924},"leading_other_bearer":{"arxiv_id":"2107.00249","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","citations":41,"named_by":["title_prefix"],"bearer_name":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","ask_with":"have('2107.00249')"},"n_other_bearers_listed":3,"note":"3 other thing(s) here are also called 'OPT', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2205.01068","page":"/paper/opt-open-pre-trained-transformer-language","syntology_url":"https://syntology.ai/paper/2205.01068","in_graph_layer":true,"samples":24,"ran":14,"n_ran_checked":13,"n_instrument":1,"unverified":10,"phrase":"14 ran (of which 2 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: official). This answer is about arXiv:2205.01068, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"787a63d139e681a327baf7e208435f39f4e3255a4d14a17da99c5fe36581bea9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}