{"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/softmax/papers/166","list_of":"/method/softmax","method":"Softmax","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":166,"pages_in_order":375,"rows_per_page":100,"rows":[16501,16600],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/165","next":"/method/softmax/papers/167","papers":[{"paper":null,"slug":"ai-enhanced-data-assimilation-and-uncertainty","title":"AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage","date":"2024-02-09","arxiv_id":"2402.06110","n_code_links":0,"syntology":null},{"paper":null,"slug":"barlowtwins-cxr-enhancing-chest-x-ray","title":"BarlowTwins-CXR : Enhancing Chest X-Ray abnormality localization in heterogeneous data with cross-domain self-supervised learning","date":"2024-02-09","arxiv_id":"2402.06499","n_code_links":0,"syntology":null},{"paper":"/paper/bryndza-at-climateactivism-2024-stance-target","slug":"bryndza-at-climateactivism-2024-stance-target","title":"Bryndza at ClimateActivism 2024: Stance, Target and Hate Event Detection via Retrieval-Augmented GPT-4 and LLaMA","date":"2024-02-09","arxiv_id":"2402.06549","n_code_links":2,"syntology":null},{"paper":"/paper/culturellm-incorporating-cultural-differences","slug":"culturellm-incorporating-cultural-differences","title":"CultureLLM: Incorporating Cultural Differences into Large Language Models","date":"2024-02-09","arxiv_id":"2402.10946","n_code_links":2,"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: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["scarelette/culturellm"],"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":null,"slug":"curveformer-3d-lane-detection-by-curve-1","title":"CurveFormer++: 3D Lane Detection by Curve Propagation with Temporal Curve Queries and Attention","date":"2024-02-09","arxiv_id":"2402.06423","n_code_links":0,"syntology":null},{"paper":"/paper/entgpt-linking-generative-large-language","slug":"entgpt-linking-generative-large-language","title":"EntGPT: Linking Generative Large Language Models with Knowledge Bases","date":"2024-02-09","arxiv_id":"2402.06738","n_code_links":1,"syntology":null},{"paper":"/paper/exaranker-open-synthetic-explanation-for-ir","slug":"exaranker-open-synthetic-explanation-for-ir","title":"ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs","date":"2024-02-09","arxiv_id":"2402.06334","n_code_links":1,"syntology":null},{"paper":null,"slug":"fabert-pre-training-bert-on-persian-blogs","title":"FaBERT: Pre-training BERT on Persian Blogs","date":"2024-02-09","arxiv_id":"2402.06617","n_code_links":0,"syntology":null},{"paper":"/paper/g-sciedbert-a-contextualized-llm-for-science","slug":"g-sciedbert-a-contextualized-llm-for-science","title":"G-SciEdBERT: A Contextualized LLM for Science Assessment Tasks in German","date":"2024-02-09","arxiv_id":"2402.06584","n_code_links":1,"syntology":null},{"paper":"/paper/inducing-systematicity-in-transformers-by","slug":"inducing-systematicity-in-transformers-by","title":"Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings","date":"2024-02-09","arxiv_id":"2402.06492","n_code_links":1,"syntology":null},{"paper":null,"slug":"jointly-learning-representations-for-map","title":"Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning","date":"2024-02-09","arxiv_id":"2402.06135","n_code_links":0,"syntology":null},{"paper":null,"slug":"learn-to-be-efficient-build-structured","title":"Learn To be Efficient: Build Structured Sparsity in Large Language Models","date":"2024-02-09","arxiv_id":"2402.06126","n_code_links":0,"syntology":null},{"paper":null,"slug":"llava-docent-instruction-tuning-with","title":"LLaVA-Docent: Instruction Tuning with Multimodal Large Language Model to Support Art Appreciation Education","date":"2024-02-09","arxiv_id":"2402.06264","n_code_links":0,"syntology":null},{"paper":null,"slug":"masked-logonet-fast-and-accurate-3d-image","title":"Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain","date":"2024-02-09","arxiv_id":"2402.06190","n_code_links":0,"syntology":null},{"paper":"/paper/rarebench-can-llms-serve-as-rare-diseases","slug":"rarebench-can-llms-serve-as-rare-diseases","title":"RareBench: Can LLMs Serve as Rare Diseases Specialists?","date":"2024-02-09","arxiv_id":"2402.06341","n_code_links":1,"syntology":null},{"paper":"/paper/resumeflow-an-llm-facilitated-pipeline-for","slug":"resumeflow-an-llm-facilitated-pipeline-for","title":"ResumeFlow: An LLM-facilitated Pipeline for Personalized Resume Generation and Refinement","date":"2024-02-09","arxiv_id":"2402.06221","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Ztrimus/job-llm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-prompt-response-to-the-demand-for-automatic","slug":"a-prompt-response-to-the-demand-for-automatic","title":"A Prompt Response to the Demand for Automatic Gender-Neutral Translation","date":"2024-02-08","arxiv_id":"2402.06041","n_code_links":1,"syntology":null},{"paper":null,"slug":"ai4fapar-how-artificial-intelligence-can-help","title":"Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal","date":"2024-02-08","arxiv_id":"2402.06684","n_code_links":0,"syntology":null},{"paper":"/paper/attnlrp-attention-aware-layer-wise-relevance","slug":"attnlrp-attention-aware-layer-wise-relevance","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","date":"2024-02-08","arxiv_id":"2402.05602","n_code_links":2,"syntology":null},{"paper":"/paper/comprehensive-assessment-of-jailbreak-attacks","slug":"comprehensive-assessment-of-jailbreak-attacks","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","date":"2024-02-08","arxiv_id":"2402.05668","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["TrustAIRLab/Comprehensive_Jailbreak_Assessment"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/diffspeaker-speech-driven-3d-facial-animation","slug":"diffspeaker-speech-driven-3d-facial-animation","title":"DiffSpeaker: Speech-Driven 3D Facial Animation with Diffusion Transformer","date":"2024-02-08","arxiv_id":"2402.05712","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-models-for-the-detection-of-hate","title":"Efficient Models for the Detection of Hate, Abuse and Profanity","date":"2024-02-08","arxiv_id":"2402.05624","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-stagewise-pretraining-via","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","date":"2024-02-08","arxiv_id":"2402.05913","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-generated-narratives-of-life-events","title":"GPT-4 Generated Narratives of Life Events using a Structured Narrative Prompt: A Validation Study","date":"2024-02-08","arxiv_id":"2402.05435","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-large-language-models-with-divide-and","title":"An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models","date":"2024-02-08","arxiv_id":"2402.05359","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-transformers-perform-in-context","slug":"how-do-transformers-perform-in-context","title":"How do Transformers perform In-Context Autoregressive Learning?","date":"2024-02-08","arxiv_id":"2402.05787","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":"/paper/how-well-can-llms-negotiate-negotiationarena","slug":"how-well-can-llms-negotiate-negotiationarena","title":"How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis","date":"2024-02-08","arxiv_id":"2402.05863","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["vinid/negotiationarena"],"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":"/paper/in-context-principle-learning-from-mistakes","slug":"in-context-principle-learning-from-mistakes","title":"In-Context Principle Learning from Mistakes","date":"2024-02-08","arxiv_id":"2402.05403","n_code_links":1,"syntology":null},{"paper":"/paper/inksight-offline-to-online-handwriting","slug":"inksight-offline-to-online-handwriting","title":"InkSight: Offline-to-Online Handwriting Conversion by Learning to Read and Write","date":"2024-02-08","arxiv_id":"2402.05804","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-model-meets-graph-neural","title":"Large Language Model Meets Graph Neural Network in Knowledge Distillation","date":"2024-02-08","arxiv_id":"2402.05894","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-for-psycholinguistic","title":"Large Language Models for Psycholinguistic Plausibility Pretesting","date":"2024-02-08","arxiv_id":"2402.05455","n_code_links":0,"syntology":null},{"paper":"/paper/limits-of-transformer-language-models-on","slug":"limits-of-transformer-language-models-on","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","date":"2024-02-08","arxiv_id":"2402.05785","n_code_links":1,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["ibm/limitations-lm-algorithmic-compositional-learning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"llms-among-us-generative-ai-participating-in","title":"LLMs Among Us: Generative AI Participating in Digital Discourse","date":"2024-02-08","arxiv_id":"2402.07940","n_code_links":0,"syntology":null},{"paper":"/paper/mamba-nd-selective-state-space-modeling-for","slug":"mamba-nd-selective-state-space-modeling-for","title":"Mamba-ND: Selective State Space Modeling for Multi-Dimensional Data","date":"2024-02-08","arxiv_id":"2402.05892","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"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) · 2 unverified","official":{"repos":["jacklishufan/mamba-nd"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"memory-consolidation-enables-long-context","title":"Memory Consolidation Enables Long-Context Video Understanding","date":"2024-02-08","arxiv_id":"2402.05861","n_code_links":0,"syntology":null},{"paper":null,"slug":"named-entity-recognition-for-address","title":"Named Entity Recognition for Address Extraction in Speech-to-Text Transcriptions Using Synthetic Data","date":"2024-02-08","arxiv_id":"2402.05545","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-models-for-source-code-synthesis-and","title":"Neural Models for Source Code Synthesis and Completion","date":"2024-02-08","arxiv_id":"2402.06690","n_code_links":0,"syntology":null},{"paper":"/paper/noise-contrastive-alignment-of-language","slug":"noise-contrastive-alignment-of-language","title":"Noise Contrastive Alignment of Language Models with Explicit Rewards","date":"2024-02-08","arxiv_id":"2402.05369","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: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thu-ml/noise-contrastive-alignment"],"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":"on-calibration-and-conformal-prediction-of","title":"On Temperature Scaling and Conformal Prediction of Deep Classifiers","date":"2024-02-08","arxiv_id":"2402.05806","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-convolutional-vision-transformers-for","title":"On Convolutional Vision Transformers for Yield Prediction","date":"2024-02-08","arxiv_id":"2402.05557","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-aware-vision-transformer-for","title":"Question Aware Vision Transformer for Multimodal Reasoning","date":"2024-02-08","arxiv_id":"2402.05472","n_code_links":0,"syntology":null},{"paper":null,"slug":"repquant-towards-accurate-post-training","title":"RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization","date":"2024-02-08","arxiv_id":"2402.05628","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-alignment-of-large-language-models-via","title":"Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation","date":"2024-02-08","arxiv_id":"2402.05699","n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-vq-transformer-an-ffn-free-framework","title":"Sparse-VQ Transformer: An FFN-Free Framework with Vector Quantization for Enhanced Time Series Forecasting","date":"2024-02-08","arxiv_id":"2402.05830","n_code_links":0,"syntology":null},{"paper":null,"slug":"timearena-shaping-efficient-multitasking","title":"TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation","date":"2024-02-08","arxiv_id":"2402.05733","n_code_links":0,"syntology":null},{"paper":"/paper/uav-rain1k-a-benchmark-for-raindrop-removal","slug":"uav-rain1k-a-benchmark-for-raindrop-removal","title":"UAV-Rain1k: A Benchmark for Raindrop Removal from UAV Aerial Imagery","date":"2024-02-08","arxiv_id":"2402.05773","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: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cschenxiang/uav-rain1k"],"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":null,"slug":"unleashing-the-infinity-power-of-geometry-a","title":"Unleashing the Infinity Power of Geometry: A Novel Geometry-Aware Transformer (GOAT) for Whole Slide Histopathology Image Analysis","date":"2024-02-08","arxiv_id":"2402.05373","n_code_links":0,"syntology":null},{"paper":"/paper/you-only-need-one-color-space-an-efficient","slug":"you-only-need-one-color-space-an-efficient","title":"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement","date":"2024-02-08","arxiv_id":"2402.05809","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-chain-of-thought-reasoning-guided","title":"Zero-Shot Chain-of-Thought Reasoning Guided by Evolutionary Algorithms in Large Language Models","date":"2024-02-08","arxiv_id":"2402.05376","n_code_links":0,"syntology":null},{"paper":"/paper/a-hypothesis-driven-framework-for-the","slug":"a-hypothesis-driven-framework-for-the","title":"A Hypothesis-Driven Framework for the Analysis of Self-Rationalising Models","date":"2024-02-07","arxiv_id":"2402.04787","n_code_links":1,"syntology":null},{"paper":null,"slug":"aspect-based-sentiment-analysis-for-open","title":"Aspect-Based Sentiment Analysis for Open-Ended HR Survey Responses","date":"2024-02-07","arxiv_id":"2402.04812","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-model-agents-simulate","slug":"can-large-language-model-agents-simulate","title":"Can Large Language Model Agents Simulate Human Trust Behavior?","date":"2024-02-07","arxiv_id":"2402.04559","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":["camel-ai/agent-trust"],"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":"chatbots-in-knowledge-intensive-contexts","title":"Conversational Assistants in Knowledge-Intensive Contexts: An Evaluation of LLM- versus Intent-based Systems","date":"2024-02-07","arxiv_id":"2402.04955","n_code_links":0,"syntology":null},{"paper":"/paper/grandmaster-level-chess-without-search","slug":"grandmaster-level-chess-without-search","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","date":"2024-02-07","arxiv_id":"2402.04494","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["google-deepmind/searchless_chess"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-bert-speaks-shakespearean-english","title":"How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models","date":"2024-02-07","arxiv_id":"2402.05034","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-cross-domain-low-resource-text","title":"Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach","date":"2024-02-07","arxiv_id":"2402.04609","n_code_links":0,"syntology":null},{"paper":"/paper/latent-plan-transformer-planning-as-latent","slug":"latent-plan-transformer-planning-as-latent","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","date":"2024-02-07","arxiv_id":"2402.04647","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":4,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mingluzhao/latent-plan-transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/long-is-more-for-alignment-a-simple-but-tough","slug":"long-is-more-for-alignment-a-simple-but-tough","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning","date":"2024-02-07","arxiv_id":"2402.04833","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"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":["tml-epfl/long-is-more-for-alignment"],"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","unlocated"]}}},{"paper":null,"slug":"navigating-the-knowledge-sea-planet-scale","title":"Navigating the Knowledge Sea: Planet-scale answer retrieval using LLMs","date":"2024-02-07","arxiv_id":"2402.05318","n_code_links":0,"syntology":null},{"paper":"/paper/opening-the-ai-black-box-program-synthesis","slug":"opening-the-ai-black-box-program-synthesis","title":"Opening the AI black box: program synthesis via mechanistic interpretability","date":"2024-02-07","arxiv_id":"2402.05110","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ejmichaud/neural-verification"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"simulated-overparameterization","title":"Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training","date":"2024-02-07","arxiv_id":"2402.05033","n_code_links":0,"syntology":null},{"paper":null,"slug":"stablemask-refining-causal-masking-in-decoder","title":"StableMask: Refining Causal Masking in Decoder-only Transformer","date":"2024-02-07","arxiv_id":"2402.04779","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-accurate-camera-based-3d-object","title":"Toward Accurate Camera-based 3D Object Detection via Cascade Depth Estimation and Calibration","date":"2024-02-07","arxiv_id":"2402.04883","n_code_links":0,"syntology":null},{"paper":"/paper/transllama-llm-based-simultaneous-translation","slug":"transllama-llm-based-simultaneous-translation","title":"TransLLaMa: LLM-based Simultaneous Translation System","date":"2024-02-07","arxiv_id":"2402.04636","n_code_links":1,"syntology":null},{"paper":"/paper/triplet-interaction-improves-graph","slug":"triplet-interaction-improves-graph","title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","date":"2024-02-07","arxiv_id":"2402.04538","n_code_links":3,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"10 ran (of which 1 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) · 3 unverified","official":{"repos":["shamim-hussain/tgt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"tuning-in-analysis-of-audio-classifier","title":"Tuning In: Analysis of Audio Classifier Performance in Clinical Settings with Limited Data","date":"2024-02-07","arxiv_id":"2402.10100","n_code_links":0,"syntology":null},{"paper":"/paper/two-trades-is-not-baffled-condense-graph-via","slug":"two-trades-is-not-baffled-condense-graph-via","title":"Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching","date":"2024-02-07","arxiv_id":"2402.04924","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nus-hpc-ai-lab/ctrl"],"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":null,"slug":"advancing-legal-reasoning-the-integration-of","title":"Advancing Legal Reasoning: The Integration of AI to Navigate Complexities and Biases in Global Jurisprudence with Semi-Automated Arbitration Processes (SAAPs)","date":"2024-02-06","arxiv_id":"2402.04140","n_code_links":0,"syntology":null},{"paper":"/paper/anytool-self-reflective-hierarchical-agents","slug":"anytool-self-reflective-hierarchical-agents","title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","date":"2024-02-06","arxiv_id":"2402.04253","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["dyabel/anytool"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"attention-based-shape-and-gait","title":"Attention-based Shape and Gait Representations Learning for Video-based Cloth-Changing Person Re-Identification","date":"2024-02-06","arxiv_id":"2402.03716","n_code_links":0,"syntology":null},{"paper":null,"slug":"behind-the-screen-investigating-chatgpt-s","title":"Behind the Screen: Investigating ChatGPT's Dark Personality Traits and Conspiracy Beliefs","date":"2024-02-06","arxiv_id":"2402.04110","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-symmetry-when-training-transformers","title":"Breaking Symmetry When Training Transformers","date":"2024-02-06","arxiv_id":"2402.05969","n_code_links":0,"syntology":null},{"paper":"/paper/can-mamba-learn-how-to-learn-a-comparative","slug":"can-mamba-learn-how-to-learn-a-comparative","title":"Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks","date":"2024-02-06","arxiv_id":"2402.04248","n_code_links":2,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["krafton-ai/mambaformer-icl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cast-clustering-self-attention-using","title":"CAST: Clustering Self-Attention using Surrogate Tokens for Efficient Transformers","date":"2024-02-06","arxiv_id":"2402.04239","n_code_links":0,"syntology":null},{"paper":null,"slug":"cehr-gpt-generating-electronic-health-records","title":"CEHR-GPT: Generating Electronic Health Records with Chronological Patient Timelines","date":"2024-02-06","arxiv_id":"2402.04400","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-abstraction-in-humans-and-large","title":"Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction","date":"2024-02-06","arxiv_id":"2402.03618","n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-mode-collapse-in-language-models","title":"Detecting Mode Collapse in Language Models via Narration","date":"2024-02-06","arxiv_id":"2402.04477","n_code_links":0,"syntology":null},{"paper":null,"slug":"detection-transformer-for-teeth-detection","title":"Detection Transformer for Teeth Detection, Segmentation, and Numbering in Oral Rare Diseases: Focus on Data Augmentation and Inpainting Techniques","date":"2024-02-06","arxiv_id":"2402.04408","n_code_links":0,"syntology":null},{"paper":null,"slug":"endmember-extraction-algorithms-fusing-for","title":"Transformer based Endmember Fusion with Spatial Context for Hyperspectral Unmixing","date":"2024-02-06","arxiv_id":"2402.03835","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-retrieval-processes-for-language","title":"Enhancing Retrieval Processes for Language Generation with Augmented Queries","date":"2024-02-06","arxiv_id":"2402.16874","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-reasons-for-contraceptive","slug":"identifying-reasons-for-contraceptive","title":"Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models","date":"2024-02-06","arxiv_id":"2402.03597","n_code_links":1,"syntology":null},{"paper":null,"slug":"iterative-prompt-refinement-for-radiation","title":"Iterative Prompt Refinement for Radiation Oncology Symptom Extraction Using Teacher-Student Large Language Models","date":"2024-02-06","arxiv_id":"2402.04075","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-an-indirect-reasoner","title":"Large Language Models as an Indirect Reasoner: Contrapositive and Contradiction for Automated Reasoning","date":"2024-02-06","arxiv_id":"2402.03667","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-moocs-graders","title":"Large Language Models As MOOCs Graders","date":"2024-02-06","arxiv_id":"2402.03776","n_code_links":0,"syntology":null},{"paper":null,"slug":"leak-cheat-repeat-data-contamination-and","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","date":"2024-02-06","arxiv_id":"2402.03927","n_code_links":0,"syntology":null},{"paper":"/paper/legallens-leveraging-llms-for-legal-violation","slug":"legallens-leveraging-llms-for-legal-violation","title":"LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text","date":"2024-02-06","arxiv_id":"2402.04335","n_code_links":1,"syntology":null},{"paper":null,"slug":"lens-a-foundation-model-for-network-traffic","title":"Lens: A Foundation Model for Network Traffic","date":"2024-02-06","arxiv_id":"2402.03646","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-agents-can-autonomously-hack-websites","title":"LLM Agents can Autonomously Hack Websites","date":"2024-02-06","arxiv_id":"2402.06664","n_code_links":0,"syntology":null},{"paper":null,"slug":"minds-versus-machines-rethinking-entailment","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","date":"2024-02-06","arxiv_id":"2402.03686","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-tuning-free-data-entry-error-1","slug":"parameter-tuning-free-data-entry-error-1","title":"Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening","date":"2024-02-06","arxiv_id":"2402.10098","n_code_links":1,"syntology":null},{"paper":"/paper/pard-permutation-invariant-autoregressive","slug":"pard-permutation-invariant-autoregressive","title":"Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation","date":"2024-02-06","arxiv_id":"2402.03687","n_code_links":1,"syntology":null},{"paper":null,"slug":"partially-recentralization-softmax-loss-for","title":"Partially Recentralization Softmax Loss for Vision-Language Models Robustness","date":"2024-02-06","arxiv_id":"2402.03627","n_code_links":0,"syntology":null},{"paper":"/paper/pre-training-of-lightweight-vision","slug":"pre-training-of-lightweight-vision","title":"Pre-training of Lightweight Vision Transformers on Small Datasets with Minimally Scaled Images","date":"2024-02-06","arxiv_id":"2402.03752","n_code_links":0,"syntology":null},{"paper":null,"slug":"professional-agents-evolving-large-language","title":"Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies","date":"2024-02-06","arxiv_id":"2402.03628","n_code_links":0,"syntology":null},{"paper":null,"slug":"provably-learning-a-multi-head-attention","title":"Provably learning a multi-head attention layer","date":"2024-02-06","arxiv_id":"2402.04084","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcement-learning-from-bagged-reward-a","title":"Reinforcement Learning from Bagged Reward","date":"2024-02-06","arxiv_id":"2402.03771","n_code_links":0,"syntology":null},{"paper":null,"slug":"return-aligned-decision-transformer","title":"Return-Aligned Decision Transformer","date":"2024-02-06","arxiv_id":"2402.03923","n_code_links":0,"syntology":null},{"paper":"/paper/self-discover-large-language-models-self","slug":"self-discover-large-language-models-self","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","date":"2024-02-06","arxiv_id":"2402.03620","n_code_links":3,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":null}},{"paper":"/paper/sentiment-enhanced-graph-based-sarcasm","slug":"sentiment-enhanced-graph-based-sarcasm","title":"Sentiment-enhanced Graph-based Sarcasm Explanation in Dialogue","date":"2024-02-06","arxiv_id":"2402.03658","n_code_links":1,"syntology":null},{"paper":null,"slug":"stanceosaurus-2-0-classifying-stance-towards","title":"Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation","date":"2024-02-06","arxiv_id":"2402.03642","n_code_links":0,"syntology":null}],"record_sha256":"49ec397efc9485682be353df69c900eab0fa8d64d9c3dee60cb64157b4a2646e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}