{"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/papers/2","list_of":"/method/opt","method":"OPT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":285,"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":41,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":41,"listed_every_run_a_failure_of_syntologys_instrument":14,"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":"/method/opt","prev":"/method/opt","next":"/method/opt/papers/3","papers":[{"paper":null,"slug":"optigrad-a-fair-and-more-efficient-price","title":"OptiGrad: A Fair and more Efficient Price Elasticity Optimization via a Gradient Based Learning","date":"2024-04-16","arxiv_id":"2404.10275","n_code_links":0,"syntology":null},{"paper":null,"slug":"competitive-retrieval-going-beyond-the-single","title":"Competitive Retrieval: Going Beyond the Single Query","date":"2024-04-14","arxiv_id":"2404.09253","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-known-clusters-probe-new-prototypes","slug":"beyond-known-clusters-probe-new-prototypes","title":"Beyond Known Clusters: Probe New Prototypes for Efficient Generalized Class Discovery","date":"2024-04-13","arxiv_id":"2404.08995","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xjtuyw/pnp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"challenges-faced-by-large-language-models-in","title":"Challenges Faced by Large Language Models in Solving Multi-Agent Flocking","date":"2024-04-06","arxiv_id":"2404.04752","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-efficient-hopfield-layers-for-large","slug":"outlier-efficient-hopfield-layers-for-large","title":"Outlier-Efficient Hopfield Layers for Large Transformer-Based Models","date":"2024-04-04","arxiv_id":"2404.03828","n_code_links":1,"syntology":{"ran":10,"of":13,"n_ran_checked":5,"n_instrument":5,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","official":{"repos":["magics-lab/outeffhop"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/flexidreamer-single-image-to-3d-generation","slug":"flexidreamer-single-image-to-3d-generation","title":"FlexiDreamer: Single Image-to-3D Generation with FlexiCubes","date":"2024-04-01","arxiv_id":"2404.00987","n_code_links":1,"syntology":null},{"paper":"/paper/nerf-mae-masked-autoencoders-for-self","slug":"nerf-mae-masked-autoencoders-for-self","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","date":"2024-04-01","arxiv_id":"2404.01300","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zubair-irshad/NeRF-MAE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/interpreting-key-mechanisms-of-factual-recall","slug":"interpreting-key-mechanisms-of-factual-recall","title":"Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models","date":"2024-03-28","arxiv_id":"2403.19521","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":12,"n_instrument":0,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["trestad/factual-recall-mechanism"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mitigating-misleading-chain-of-thought","slug":"mitigating-misleading-chain-of-thought","title":"Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering","date":"2024-03-28","arxiv_id":"2403.19167","n_code_links":1,"syntology":null},{"paper":null,"slug":"alisa-accelerating-large-language-model","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","date":"2024-03-26","arxiv_id":"2403.17312","n_code_links":0,"syntology":null},{"paper":null,"slug":"clean-image-backdoor-attacks","title":"Clean-image Backdoor Attacks","date":"2024-03-22","arxiv_id":"2403.15010","n_code_links":0,"syntology":null},{"paper":null,"slug":"wscloc-weakly-supervised-sparse-view-camera","title":"WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization","date":"2024-03-22","arxiv_id":"2403.15272","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-bayesian-future-fusion-for-self","title":"Deep Bayesian Future Fusion for Self-Supervised, High-Resolution, Off-Road Mapping","date":"2024-03-18","arxiv_id":"2403.11876","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-language-models-represent-some","title":"Pre-Trained Language Models Represent Some Geographic Populations Better Than Others","date":"2024-03-16","arxiv_id":"2403.11025","n_code_links":0,"syntology":null},{"paper":null,"slug":"exegpt-constraint-aware-resource-scheduling","title":"ExeGPT: Constraint-Aware Resource Scheduling for LLM Inference","date":"2024-03-15","arxiv_id":"2404.07947","n_code_links":0,"syntology":null},{"paper":null,"slug":"quanttune-optimizing-model-quantization-with","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","date":"2024-03-11","arxiv_id":"2403.06497","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-all-layers-of-llms-are-necessary-during","title":"Not All Layers of LLMs Are Necessary During Inference","date":"2024-03-04","arxiv_id":"2403.02181","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-quantized-large-language-models","slug":"evaluating-quantized-large-language-models","title":"Evaluating Quantized Large Language Models","date":"2024-02-28","arxiv_id":"2402.18158","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":10,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["thu-nics/qllm-eval"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"merino-entropy-driven-design-for-generative","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","date":"2024-02-28","arxiv_id":"2403.07921","n_code_links":0,"syntology":null},{"paper":"/paper/emmark-robust-watermarks-for-ip-protection-of","slug":"emmark-robust-watermarks-for-ip-protection-of","title":"EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models","date":"2024-02-27","arxiv_id":"2402.17938","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-posterior-proximal-sampling-for","slug":"diffusion-posterior-proximal-sampling-for","title":"Diffusion Posterior Proximal Sampling for Image Restoration","date":"2024-02-25","arxiv_id":"2402.16907","n_code_links":1,"syntology":{"ran":15,"of":26,"n_ran_checked":9,"n_instrument":6,"unverified":11,"pointer_only":26,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified","official":{"repos":["74587887/dpps_code"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deepset-simclr-self-supervised-deep-sets-for","title":"DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning","date":"2024-02-23","arxiv_id":"2402.15598","n_code_links":0,"syntology":null},{"paper":null,"slug":"recursive-speculative-decoding-accelerating","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","date":"2024-02-21","arxiv_id":"2402.14160","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-zeroth-order-optimization-for","slug":"revisiting-zeroth-order-optimization-for","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","date":"2024-02-18","arxiv_id":"2402.11592","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":3,"n_instrument":6,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zo-bench/zo-llm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/smaller-language-models-are-capable-of","slug":"smaller-language-models-are-capable-of","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models","date":"2024-02-16","arxiv_id":"2402.10430","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dheeraj7596/small2large"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"eliciting-big-five-personality-traits-in","title":"Eliciting Personality Traits in Large Language Models","date":"2024-02-13","arxiv_id":"2402.08341","n_code_links":0,"syntology":null},{"paper":"/paper/connecting-the-dots-collaborative-fine-tuning","slug":"connecting-the-dots-collaborative-fine-tuning","title":"Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models","date":"2024-02-06","arxiv_id":"2402.04050","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["mrflogs/craft"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/transfer-learning-in-ecg-diagnosis-is-it","slug":"transfer-learning-in-ecg-diagnosis-is-it","title":"Transfer Learning in ECG Diagnosis: Is It Effective?","date":"2024-02-03","arxiv_id":"2402.02021","n_code_links":1,"syntology":null},{"paper":null,"slug":"paramanu-a-family-of-novel-efficient-indic","title":"Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages","date":"2024-01-31","arxiv_id":"2401.18034","n_code_links":0,"syntology":null},{"paper":"/paper/slicegpt-compress-large-language-models-by","slug":"slicegpt-compress-large-language-models-by","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","date":"2024-01-26","arxiv_id":"2401.15024","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":["microsoft/transformercompression"],"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":"generative-human-motion-stylization-in-latent","title":"Generative Human Motion Stylization in Latent Space","date":"2024-01-24","arxiv_id":"2401.13505","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-vulnerabilities-in-large-language","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","date":"2024-01-11","arxiv_id":"2401.05949","n_code_links":0,"syntology":null},{"paper":"/paper/the-llm-surgeon","slug":"the-llm-surgeon","title":"The LLM Surgeon","date":"2023-12-28","arxiv_id":"2312.17244","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":4,"n_instrument":0,"unverified":6,"pointer_only":10,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["qualcomm-ai-research/llm-surgeon"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"diagnosis-of-takotsubo-syndrome-by-robust","title":"Diagnosis Of Takotsubo Syndrome By Robust Feature Selection From The Complex Latent Space Of DL-based Segmentation Network","date":"2023-12-19","arxiv_id":"2312.12653","n_code_links":0,"syntology":null},{"paper":"/paper/venn-resource-management-across-federated","slug":"venn-resource-management-across-federated","title":"Venn: Resource Management for Collaborative Learning Jobs","date":"2023-12-13","arxiv_id":"2312.08298","n_code_links":1,"syntology":null},{"paper":"/paper/dyad-a-descriptive-yet-abjuring-density","slug":"dyad-a-descriptive-yet-abjuring-density","title":"DYAD: A Descriptive Yet Abjuring Density efficient approximation to linear neural network layers","date":"2023-12-11","arxiv_id":"2312.06881","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["asappresearch/dyad"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/agile-quant-activation-guided-quantization","slug":"agile-quant-activation-guided-quantization","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","date":"2023-12-09","arxiv_id":"2312.05693","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shawnricecake/agile-quant"],"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"]}}},{"paper":null,"slug":"holmes-towards-distributed-training-across","title":"Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment","date":"2023-12-06","arxiv_id":"2312.03549","n_code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-detection-of-hallucinations","slug":"weakly-supervised-detection-of-hallucinations","title":"Weakly Supervised Detection of Hallucinations in LLM Activations","date":"2023-12-05","arxiv_id":"2312.02798","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Trusted-AI/adversarial-robustness-toolbox"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fast-view-synthesis-of-casual-videos","title":"Fast View Synthesis of Casual Videos with Soup-of-Planes","date":"2023-12-04","arxiv_id":"2312.02135","n_code_links":0,"syntology":null},{"paper":null,"slug":"bit-cipher-a-simple-yet-powerful-word","title":"Bit Cipher -- A Simple yet Powerful Word Representation System that Integrates Efficiently with Language Models","date":"2023-11-18","arxiv_id":"2311.11012","n_code_links":0,"syntology":null},{"paper":"/paper/3d-paintbrush-local-stylization-of-3d-shapes","slug":"3d-paintbrush-local-stylization-of-3d-shapes","title":"3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation","date":"2023-11-16","arxiv_id":"2311.09571","n_code_links":1,"syntology":null},{"paper":"/paper/back-to-basics-a-simple-recipe-for-improving","slug":"back-to-basics-a-simple-recipe-for-improving","title":"Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders","date":"2023-11-16","arxiv_id":"2311.09765","n_code_links":1,"syntology":null},{"paper":"/paper/cd-coco-a-versatile-complex-distorted-coco","slug":"cd-coco-a-versatile-complex-distorted-coco","title":"CD-COCO: A Versatile Complex Distorted COCO Database for Scene-Context-Aware Computer Vision","date":"2023-11-12","arxiv_id":"2311.06976","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-computation-efficiency-in-large","title":"Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization","date":"2023-11-09","arxiv_id":"2311.05161","n_code_links":0,"syntology":null},{"paper":null,"slug":"aweq-post-training-quantization-with","title":"AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models","date":"2023-11-02","arxiv_id":"2311.01305","n_code_links":0,"syntology":null},{"paper":"/paper/network-contention-aware-cluster-scheduling","slug":"network-contention-aware-cluster-scheduling","title":"Network Contention-Aware Cluster Scheduling with Reinforcement Learning","date":"2023-10-31","arxiv_id":"2310.20209","n_code_links":1,"syntology":null},{"paper":null,"slug":"constituency-parsing-using-llms","title":"Constituency Parsing using LLMs","date":"2023-10-30","arxiv_id":"2310.19462","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacherlm-teaching-to-fish-rather-than-giving","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","date":"2023-10-29","arxiv_id":"2310.19019","n_code_links":0,"syntology":null},{"paper":null,"slug":"transfer-learning-in-transformer-based-demand","title":"Transfer Learning in Transformer-Based Demand Forecasting For Home Energy Management System","date":"2023-10-29","arxiv_id":"2310.19159","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-well-can-machine-generated-texts-be","title":"How well can machine-generated texts be identified and can language models be trained to avoid identification?","date":"2023-10-25","arxiv_id":"2310.16992","n_code_links":0,"syntology":null},{"paper":"/paper/redco-a-lightweight-tool-to-automate","slug":"redco-a-lightweight-tool-to-automate","title":"RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs","date":"2023-10-25","arxiv_id":"2310.16355","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":12,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["tanyuqian/redco"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"e-sparse-boosting-the-large-language-model","title":"E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity","date":"2023-10-24","arxiv_id":"2310.15929","n_code_links":0,"syntology":null},{"paper":null,"slug":"design-inclusive-language-models-for","title":"She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models","date":"2023-10-20","arxiv_id":"2310.18333","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-dataset-distillation-through","slug":"efficient-dataset-distillation-through","title":"AST: Effective Dataset Distillation through Alignment with Smooth and High-Quality Expert Trajectories","date":"2023-10-16","arxiv_id":"2310.10541","n_code_links":1,"syntology":null},{"paper":"/paper/dpzero-dimension-independent-and","slug":"dpzero-dimension-independent-and","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","date":"2023-10-14","arxiv_id":"2310.09639","n_code_links":1,"syntology":{"ran":8,"of":17,"n_ran_checked":6,"n_instrument":2,"unverified":9,"pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["liang137/dpzero"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"community-membership-hiding-as-counterfactual","title":"Evading Community Detection via Counterfactual Neighborhood Search","date":"2023-10-13","arxiv_id":"2310.08909","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-sparse-no-training-training-free-fine","slug":"dynamic-sparse-no-training-training-free-fine","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","date":"2023-10-13","arxiv_id":"2310.08915","n_code_links":1,"syntology":{"ran":8,"of":15,"n_ran_checked":6,"n_instrument":2,"unverified":7,"pointer_only":15,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","official":{"repos":["zyxxmu/dsnot"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-end-to-end-4-bit-inference-on","slug":"towards-end-to-end-4-bit-inference-on","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","date":"2023-10-13","arxiv_id":"2310.09259","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ist-daslab/quik"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/outlier-weighed-layerwise-sparsity-owl-a","slug":"outlier-weighed-layerwise-sparsity-owl-a","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","date":"2023-10-08","arxiv_id":"2310.05175","n_code_links":1,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["luuyin/owl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/beyond-one-preference-for-all-multi-objective","slug":"beyond-one-preference-for-all-multi-objective","title":"Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization","date":"2023-10-05","arxiv_id":"2310.03708","n_code_links":2,"syntology":null},{"paper":null,"slug":"salsa-semantically-aware-latent-space","title":"SALSA: Semantically-Aware Latent Space Autoencoder","date":"2023-10-04","arxiv_id":"2310.02744","n_code_links":0,"syntology":null},{"paper":null,"slug":"coralvos-dataset-and-benchmark-for-coral","title":"CoralVOS: Dataset and Benchmark for Coral Video Segmentation","date":"2023-10-03","arxiv_id":"2310.01946","n_code_links":0,"syntology":null},{"paper":null,"slug":"decorait-decentralized-opt-in-out-registry","title":"DECORAIT -- DECentralized Opt-in/out Registry for AI Training","date":"2023-09-25","arxiv_id":"2309.14400","n_code_links":0,"syntology":null},{"paper":"/paper/egocentric-rgb-depth-action-recognition-in","slug":"egocentric-rgb-depth-action-recognition-in","title":"Egocentric RGB+Depth Action Recognition in Industry-Like Settings","date":"2023-09-25","arxiv_id":"2309.13962","n_code_links":1,"syntology":null},{"paper":"/paper/h2o-heavy-hitter-oracle-for-efficient","slug":"h2o-heavy-hitter-oracle-for-efficient","title":"H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/statistical-knowledge-assessment-for-large","slug":"statistical-knowledge-assessment-for-large","title":"Statistical Knowledge Assessment for Large Language Models","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"neurons-in-large-language-models-dead-n-gram","title":"Neurons in Large Language Models: Dead, N-gram, Positional","date":"2023-09-09","arxiv_id":"2309.04827","n_code_links":0,"syntology":null},{"paper":null,"slug":"softmax-bias-correction-for-quantized","title":"Softmax Bias Correction for Quantized Generative Models","date":"2023-09-04","arxiv_id":"2309.01729","n_code_links":0,"syntology":null},{"paper":null,"slug":"expanding-frozen-vision-language-models","title":"Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception","date":"2023-08-31","arxiv_id":"2308.16493","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-compression-via-subspace","slug":"transformer-compression-via-subspace","title":"$\\rm SP^3$: Enhancing Structured Pruning via PCA Projection","date":"2023-08-31","arxiv_id":"2308.16475","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hyx1999/sp3"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"acnpu-a-4-75tops-w-1080p-30fps-super","title":"ACNPU: A 4.75TOPS/W 1080P@30FPS Super Resolution Accelerator with Decoupled Asymmetric Convolution","date":"2023-08-30","arxiv_id":"2308.15807","n_code_links":0,"syntology":null},{"paper":"/paper/calm-a-multi-task-benchmark-for-comprehensive","slug":"calm-a-multi-task-benchmark-for-comprehensive","title":"CALM : A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias","date":"2023-08-24","arxiv_id":"2308.12539","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vipulgupta1011/calm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ipa-inference-pipeline-adaptation-to-achieve","slug":"ipa-inference-pipeline-adaptation-to-achieve","title":"IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency","date":"2023-08-24","arxiv_id":"2308.12871","n_code_links":1,"syntology":null},{"paper":"/paper/activation-addition-steering-language-models","slug":"activation-addition-steering-language-models","title":"Steering Language Models With Activation Engineering","date":"2023-08-20","arxiv_id":"2308.10248","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["montemac/activation_additions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"balancing-transparency-and-risk-the-security","title":"Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models","date":"2023-08-18","arxiv_id":"2308.09490","n_code_links":0,"syntology":null},{"paper":"/paper/ternary-singular-value-decomposition-as-a","slug":"ternary-singular-value-decomposition-as-a","title":"Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping","date":"2023-08-15","arxiv_id":"2308.07641","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ozzzp/ternary_decompose"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ensemble-modeling-for-multimodal-visual","slug":"ensemble-modeling-for-multimodal-visual","title":"Ensemble Modeling for Multimodal Visual Action Recognition","date":"2023-08-10","arxiv_id":"2308.05430","n_code_links":1,"syntology":null},{"paper":"/paper/silo-language-models-isolating-legal-risk-in","slug":"silo-language-models-isolating-legal-risk-in","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","date":"2023-08-08","arxiv_id":"2308.04430","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-sentence-embeddings-with-large","slug":"scaling-sentence-embeddings-with-large","title":"Scaling Sentence Embeddings with Large Language Models","date":"2023-07-31","arxiv_id":"2307.16645","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kongds/scaling_sentemb"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/overcoming-distribution-mismatch-in","slug":"overcoming-distribution-mismatch-in","title":"Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks","date":"2023-07-25","arxiv_id":"2307.13337","n_code_links":1,"syntology":null},{"paper":null,"slug":"mechanical-artifacts-in-optical-projection-1","title":"Mechanical Artifacts in Optical Projection Tomography: Classification and Automatic Calibration","date":"2023-07-19","arxiv_id":"2309.16677","n_code_links":0,"syntology":null},{"paper":null,"slug":"raymvsnet-learning-ray-based-1d-implicit-1","title":"RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo","date":"2023-07-16","arxiv_id":"2307.10233","n_code_links":0,"syntology":null},{"paper":"/paper/qigen-generating-efficient-kernels-for","slug":"qigen-generating-efficient-kernels-for","title":"QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models","date":"2023-07-07","arxiv_id":"2307.03738","n_code_links":1,"syntology":null},{"paper":null,"slug":"skipdecode-autoregressive-skip-decoding-with","title":"SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference","date":"2023-07-05","arxiv_id":"2307.02628","n_code_links":0,"syntology":null},{"paper":"/paper/shifting-attention-to-relevance-towards-the","slug":"shifting-attention-to-relevance-towards-the","title":"Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models","date":"2023-07-03","arxiv_id":"2307.01379","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jinhaoduan/sar","jinhaoduan/shifting-attention-to-relevance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"kite-keypoint-conditioned-policies-for","title":"KITE: Keypoint-Conditioned Policies for Semantic Manipulation","date":"2023-06-29","arxiv_id":"2306.16605","n_code_links":0,"syntology":null},{"paper":"/paper/h-2-o-heavy-hitter-oracle-for-efficient","slug":"h-2-o-heavy-hitter-oracle-for-efficient","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","date":"2023-06-24","arxiv_id":"2306.14048","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fminference/h2o"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"solving-dialogue-grounding-embodied-task-in-a","title":"Solving Dialogue Grounding Embodied Task in a Simulated Environment using Further Masked Language Modeling","date":"2023-06-21","arxiv_id":"2306.12387","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-search-for-nonlinear-balanced-boolean","title":"A Search for Nonlinear Balanced Boolean Functions by Leveraging Phenotypic Properties","date":"2023-06-15","arxiv_id":"2306.09190","n_code_links":0,"syntology":null},{"paper":null,"slug":"inroads-into-autonomous-network-defence-using","title":"Inroads into Autonomous Network Defence using Explained Reinforcement Learning","date":"2023-06-15","arxiv_id":"2306.09318","n_code_links":0,"syntology":null},{"paper":"/paper/easyguide-esg-issue-identification-framework","slug":"easyguide-esg-issue-identification-framework","title":"EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models","date":"2023-06-11","arxiv_id":"2306.06662","n_code_links":1,"syntology":null},{"paper":"/paper/make-pre-trained-model-reversible-from-1","slug":"make-pre-trained-model-reversible-from-1","title":"Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning","date":"2023-06-01","arxiv_id":"2306.00477","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["baohaoliao/mefts"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"paper":"/paper/gpt4tools-teaching-large-language-model-to","slug":"gpt4tools-teaching-large-language-model-to","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","date":"2023-05-30","arxiv_id":"2305.18752","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-relentless-benchmark-for-modelling-graded","title":"A RelEntLess Benchmark for Modelling Graded Relations between Named Entities","date":"2023-05-24","arxiv_id":"2305.15002","n_code_links":0,"syntology":null},{"paper":"/paper/adapting-language-models-to-compress-contexts","slug":"adapting-language-models-to-compress-contexts","title":"Adapting Language Models to Compress Contexts","date":"2023-05-24","arxiv_id":"2305.14788","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["princeton-nlp/autocompressors"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/llmdet-a-large-language-models-detection-tool","slug":"llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","arxiv_id":"2305.15004","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["trustedllm/llmdet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/tricking-llms-into-disobedience-understanding","slug":"tricking-llms-into-disobedience-understanding","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","date":"2023-05-24","arxiv_id":"2305.14965","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AetherPrior/TrickLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/trusting-your-evidence-hallucinate-less-with","slug":"trusting-your-evidence-hallucinate-less-with","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","date":"2023-05-24","arxiv_id":"2305.14739","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":null}},{"paper":null,"slug":"a-trip-towards-fairness-bias-and-de-biasing","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","date":"2023-05-23","arxiv_id":"2305.13862","n_code_links":0,"syntology":null}],"record_sha256":"e59fcb4ff36242504ca56299d1a867d2ae41ed585f7309a72535ee8017aa6c1b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}