{"url":"/task/inference-optimization","name":"Inference Optimization","slug":"inference-optimization","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":56,"papers_with_code":21,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/online-beat-tracking","name":"Online Beat Tracking"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":21,"of":21,"tagged_in_all":56,"items":[{"url":"/paper/enhanced-graph-learning-schemes-driven-by","title":"Enhanced graph-learning schemes driven by similar distributions of motifs","date":"2022-07-11","arxiv_id":"2207.04747","repositories_listed":3,"syntology":null},{"url":"/paper/input-convex-neural-networks","title":"Input Convex Neural Networks","date":"2016-09-22","arxiv_id":"1609.07152","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/cyclebnn-cyclic-precision-training-in-binary-1","title":"CycleBNN: Cyclic Precision Training in Binary Neural Networks","date":"2024-09-28","arxiv_id":"2410.00050","repositories_listed":2,"syntology":null},{"url":"/paper/patched-moa-optimizing-inference-for-diverse","title":"Patched MOA: optimizing inference for diverse software development tasks","date":"2024-07-26","arxiv_id":"2407.18521","repositories_listed":2,"syntology":null},{"url":"/paper/representing-edge-flows-on-graphs-via-sparse","title":"Representing Edge Flows on Graphs via Sparse Cell Complexes","date":"2023-09-04","arxiv_id":"2309.01632","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/2506-08686","title":"Brevity is the soul of sustainability: Characterizing LLM response lengths","date":"2025-06-10","arxiv_id":"2506.08686","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-llm-inference-fluid-guided-online","title":"Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints","date":"2025-04-15","arxiv_id":"2504.11320","repositories_listed":1,"syntology":null},{"url":"/paper/simplear-pushing-the-frontier-of","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","date":"2025-04-15","arxiv_id":"2504.11455","repositories_listed":1,"syntology":{"n":11,"n_ran":2,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/the-1st-solution-for-4th-pvuw-mevis-challenge","title":"The 1st Solution for 4th PVUW MeViS Challenge: Unleashing the Potential of Large Multimodal Models for Referring Video Segmentation","date":"2025-04-07","arxiv_id":"2504.05178","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-inference-optimization-techniques","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","date":"2024-12-18","arxiv_id":"2412.14219","repositories_listed":1,"syntology":null},{"url":"/paper/a-temporal-linear-network-for-time-series","title":"A Temporal Linear Network for Time Series Forecasting","date":"2024-10-28","arxiv_id":"2410.21448","repositories_listed":1,"syntology":null},{"url":"/paper/llm-rank-a-graph-theoretical-approach-to","title":"LLM-Rank: A Graph Theoretical Approach to Pruning Large Language Models","date":"2024-10-17","arxiv_id":"2410.13299","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02006","title":"LLaSA: Large Language and E-Commerce Shopping Assistant","date":"2024-08-04","arxiv_id":"2408.02006","repositories_listed":1,"syntology":null},{"url":"/paper/inference-performance-optimization-for-large","title":"Inference Performance Optimization for Large Language Models on CPUs","date":"2024-07-10","arxiv_id":"2407.07304","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/painterly-image-harmonization-using-diffusion","title":"Painterly Image Harmonization using Diffusion Model","date":"2023-08-04","arxiv_id":"2308.02228","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/eenet-learning-to-early-exit-for-adaptive","title":"Adaptive Deep Neural Network Inference Optimization with EENet","date":"2023-01-15","arxiv_id":"2301.07099","repositories_listed":1,"syntology":null},{"url":"/paper/adjust-a-dictionary-based-joint","title":"ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral Tomography","date":"2021-12-21","arxiv_id":"2112.11406","repositories_listed":1,"syntology":null},{"url":"/paper/a-novel-1d-state-space-for-efficient-music","title":"A Novel 1D State Space for Efficient Music Rhythmic Analysis","date":"2021-11-01","arxiv_id":"2111.00704","repositories_listed":1,"syntology":null},{"url":"/paper/easy-and-efficient-transformer-scalable","title":"Easy and Efficient Transformer : Scalable Inference Solution For large NLP model","date":"2021-04-26","arxiv_id":"2104.12470","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-method-for-amortizing-variational","title":"A General Method for Amortizing Variational Filtering","date":"2018-11-13","arxiv_id":"1811.05090","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/iterative-amortized-inference","title":"Iterative Amortized Inference","date":"2018-07-24","arxiv_id":"1807.09356","repositories_listed":1,"syntology":null}],"syntology_records":6,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}