{"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/linear-layer/papers/41","list_of":"/method/linear-layer","method":"Linear Layer","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":41,"pages_in_order":255,"rows_per_page":100,"rows":[4001,4100],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"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/linear-layer","prev":"/method/linear-layer/papers/40","next":"/method/linear-layer/papers/42","papers":[{"paper":"/paper/measuring-and-modifying-the-readability-of","slug":"measuring-and-modifying-the-readability-of","title":"Measuring and Modifying the Readability of English Texts with GPT-4","date":"2024-10-17","arxiv_id":"2410.14028","n_code_links":1,"syntology":null},{"paper":null,"slug":"metacognitive-monitoring-a-human-ability","title":"Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence","date":"2024-10-17","arxiv_id":"2410.13392","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-bench-automatic-multilingual-benchmark","slug":"mirage-bench-automatic-multilingual-benchmark","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","date":"2024-10-17","arxiv_id":"2410.13716","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-partial-prototype-collapse-in-the-dino","title":"On Partial Prototype Collapse in the DINO Family of Self-Supervised Methods","date":"2024-10-17","arxiv_id":"2410.14060","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-learn-to-optimize-capabilities-of","title":"On the Learn-to-Optimize Capabilities of Transformers in In-Context Sparse Recovery","date":"2024-10-17","arxiv_id":"2410.13981","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-role-of-attention-heads-in-large","slug":"on-the-role-of-attention-heads-in-large","title":"On the Role of Attention Heads in Large Language Model Safety","date":"2024-10-17","arxiv_id":"2410.13708","n_code_links":1,"syntology":{"ran":16,"of":24,"n_ran_checked":8,"n_instrument":8,"unverified":8,"pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 8 unverified","official":{"repos":["ydyjya/safetyheadattribution"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-use-of-audio-to-improve-dialogue","slug":"on-the-use-of-audio-to-improve-dialogue","title":"On the Use of Audio to Improve Dialogue Policies","date":"2024-10-17","arxiv_id":"2410.13385","n_code_links":1,"syntology":null},{"paper":null,"slug":"personalized-adaptation-via-in-context","title":"Personalized Adaptation via In-Context Preference Learning","date":"2024-10-17","arxiv_id":"2410.14001","n_code_links":0,"syntology":null},{"paper":null,"slug":"precipitation-nowcasting-using-diffusion","title":"Precipitation Nowcasting Using Diffusion Transformer with Causal Attention","date":"2024-10-17","arxiv_id":"2410.13314","n_code_links":0,"syntology":null},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["openmatch/rag-ddr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"rgb-to-hyperspectral-spectral-reconstruction","title":"RGB to Hyperspectral: Spectral Reconstruction for Enhanced Surgical Imaging","date":"2024-10-17","arxiv_id":"2410.13570","n_code_links":0,"syntology":null},{"paper":"/paper/sbi-rag-enhancing-math-word-problem-solving","slug":"sbi-rag-enhancing-math-word-problem-solving","title":"SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation","date":"2024-10-17","arxiv_id":"2410.13293","n_code_links":1,"syntology":null},{"paper":null,"slug":"soullmate-an-application-enhancing-diverse","title":"SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques","date":"2024-10-17","arxiv_id":"2410.16322","n_code_links":0,"syntology":null},{"paper":"/paper/tabseq-a-framework-for-deep-learning-on","slug":"tabseq-a-framework-for-deep-learning-on","title":"TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering","date":"2024-10-17","arxiv_id":"2410.13203","n_code_links":1,"syntology":null},{"paper":null,"slug":"temporal-enhanced-multimodal-transformer-for","title":"Temporal-Enhanced Multimodal Transformer for Referring Multi-Object Tracking and Segmentation","date":"2024-10-17","arxiv_id":"2410.13437","n_code_links":0,"syntology":null},{"paper":"/paper/towards-cross-cultural-machine-translation","slug":"towards-cross-cultural-machine-translation","title":"Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs","date":"2024-10-17","arxiv_id":"2410.14057","n_code_links":0,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"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) · 0 unverified","official":null}},{"paper":null,"slug":"training-compute-optimal-vision-transformers","title":"Training Compute-Optimal Vision Transformers for Brain Encoding","date":"2024-10-17","arxiv_id":"2410.19810","n_code_links":0,"syntology":null},{"paper":"/paper/unig-modelling-unitary-3d-gaussians-for-view","slug":"unig-modelling-unitary-3d-gaussians-for-view","title":"UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images","date":"2024-10-17","arxiv_id":"2410.13195","n_code_links":2,"syntology":null},{"paper":null,"slug":"unlocking-legal-knowledge-a-multilingual","title":"Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland","date":"2024-10-17","arxiv_id":"2410.13456","n_code_links":0,"syntology":null},{"paper":null,"slug":"advancing-fairness-in-natural-language","title":"Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability","date":"2024-10-16","arxiv_id":"2410.12511","n_code_links":0,"syntology":null},{"paper":"/paper/agent-skill-acquisition-for-large-language","slug":"agent-skill-acquisition-for-large-language","title":"Agent Skill Acquisition for Large Language Models via CycleQD","date":"2024-10-16","arxiv_id":"2410.14735","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["SakanaAI/CycleQD"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/at-rag-an-adaptive-rag-model-enhancing-query","slug":"at-rag-an-adaptive-rag-model-enhancing-query","title":"AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoning","date":"2024-10-16","arxiv_id":"2410.12886","n_code_links":1,"syntology":null},{"paper":null,"slug":"ccsbench-evaluating-compositional","title":"CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization","date":"2024-10-16","arxiv_id":"2410.12601","n_code_links":0,"syntology":null},{"paper":"/paper/cofe-rag-a-comprehensive-full-chain","slug":"cofe-rag-a-comprehensive-full-chain","title":"CoFE-RAG: A Comprehensive Full-chain Evaluation Framework for Retrieval-Augmented Generation with Enhanced Data Diversity","date":"2024-10-16","arxiv_id":"2410.12248","n_code_links":1,"syntology":null},{"paper":null,"slug":"communication-efficient-and-tensorized","title":"Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models","date":"2024-10-16","arxiv_id":"2410.13097","n_code_links":0,"syntology":null},{"paper":null,"slug":"context-scaling-versus-task-scaling-in-in","title":"Context-Scaling versus Task-Scaling in In-Context Learning","date":"2024-10-16","arxiv_id":"2410.12783","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-morphological-compositional","slug":"evaluating-morphological-compositional","title":"Evaluating Morphological Compositional Generalization in Large Language Models","date":"2024-10-16","arxiv_id":"2410.12656","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":["selimfirat/bilkent-turkish-writings-dataset"],"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":"evaluation-of-attribution-bias-in-retrieval","title":"Evaluation of Attribution Bias in Retrieval-Augmented Large Language Models","date":"2024-10-16","arxiv_id":"2410.12380","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-large-language-models-for-hate","title":"Exploring Large Language Models for Hate Speech Detection in Rioplatense Spanish","date":"2024-10-16","arxiv_id":"2410.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusionllm-a-decentralized-llm-training-system","title":"FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression","date":"2024-10-16","arxiv_id":"2410.12707","n_code_links":0,"syntology":null},{"paper":"/paper/hypothesis-testing-the-circuit-hypothesis-in","slug":"hypothesis-testing-the-circuit-hypothesis-in","title":"Hypothesis Testing the Circuit Hypothesis in LLMs","date":"2024-10-16","arxiv_id":"2410.13032","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["blei-lab/circuitry"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"identifying-task-groupings-for-multi-task","title":"Identifying Task Groupings for Multi-Task Learning Using Pointwise V-Usable Information","date":"2024-10-16","arxiv_id":"2410.12774","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-semantic-chunking-worth-the-computational","title":"Is Semantic Chunking Worth the Computational Cost?","date":"2024-10-16","arxiv_id":"2410.13070","n_code_links":0,"syntology":null},{"paper":null,"slug":"kallini-et-al-2024-do-not-compare-impossible","title":"Kallini et al. (2024) do not compare impossible languages with constituency-based ones","date":"2024-10-16","arxiv_id":"2410.12271","n_code_links":0,"syntology":null},{"paper":null,"slug":"mambabev-an-efficient-3d-detection-model-with","title":"MambaBEV: An efficient 3D detection model with Mamba2","date":"2024-10-16","arxiv_id":"2410.12673","n_code_links":0,"syntology":null},{"paper":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"5 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mirror-a-novel-approach-for-the-automated","title":"MIRROR: A Novel Approach for the Automated Evaluation of Open-Ended Question Generation","date":"2024-10-16","arxiv_id":"2410.12893","n_code_links":0,"syntology":null},{"paper":"/paper/mmed-rag-versatile-multimodal-rag-system-for","slug":"mmed-rag-versatile-multimodal-rag-system-for","title":"MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models","date":"2024-10-16","arxiv_id":"2410.13085","n_code_links":1,"syntology":{"ran":7,"of":10,"n_ran_checked":3,"n_instrument":4,"unverified":3,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["richard-peng-xia/mmed-rag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/msc-sql-multi-sample-critiquing-small","slug":"msc-sql-multi-sample-critiquing-small","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","date":"2024-10-16","arxiv_id":"2410.12916","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["layer6ai-labs/msc-sql"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-a-scale-from-1-to-5-quantifying","title":"On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation","date":"2024-10-16","arxiv_id":"2410.12222","n_code_links":0,"syntology":null},{"paper":null,"slug":"risk-assessment-for-autonomous-landing-in","title":"Risk Assessment for Autonomous Landing in Urban Environments using Semantic Segmentation","date":"2024-10-16","arxiv_id":"2410.12988","n_code_links":0,"syntology":null},{"paper":null,"slug":"shapefilegpt-a-multi-agent-large-language","title":"ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing","date":"2024-10-16","arxiv_id":"2410.12376","n_code_links":0,"syntology":null},{"paper":"/paper/stabilize-the-latent-space-for-image","slug":"stabilize-the-latent-space-for-image","title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","date":"2024-10-16","arxiv_id":"2410.12490","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["DAMO-NLP-SG/DiGIT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"swim-an-attention-only-model-for-speech","title":"AttentiveMOS: A Lightweight Attention-Only Model for Speech Quality Prediction","date":"2024-10-16","arxiv_id":"2410.12675","n_code_links":0,"syntology":null},{"paper":null,"slug":"table-llm-specialist-language-model","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","date":"2024-10-16","arxiv_id":"2410.12164","n_code_links":0,"syntology":null},{"paper":null,"slug":"tracking-universal-features-through-fine","title":"Tracking Universal Features Through Fine-Tuning and Model Merging","date":"2024-10-16","arxiv_id":"2410.12391","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-super-resolution","title":"Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approaches","date":"2024-10-16","arxiv_id":"2410.12728","n_code_links":0,"syntology":null},{"paper":null,"slug":"unifying-economic-and-language-models-for","title":"Unifying Economic and Language Models for Enhanced Sentiment Analysis of the Oil Market","date":"2024-10-16","arxiv_id":"2410.12473","n_code_links":0,"syntology":null},{"paper":"/paper/unitary-multi-margin-bert-for-robust-natural","slug":"unitary-multi-margin-bert-for-robust-natural","title":"Unitary Multi-Margin BERT for Robust Natural Language Processing","date":"2024-10-16","arxiv_id":"2410.12759","n_code_links":1,"syntology":null},{"paper":null,"slug":"when-not-to-answer-evaluating-prompts-on-gpt","title":"When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems","date":"2024-10-16","arxiv_id":"2410.13029","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-survey-on-deep-tabular-learning","title":"A Survey on Deep Tabular Learning","date":"2024-10-15","arxiv_id":"2410.12034","n_code_links":0,"syntology":null},{"paper":null,"slug":"athena-retrieval-augmented-legal-judgment","title":"Athena: Retrieval-augmented Legal Judgment Prediction with Large Language Models","date":"2024-10-15","arxiv_id":"2410.11195","n_code_links":0,"syntology":null},{"paper":null,"slug":"bypassing-the-exponential-dependency-looped","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","date":"2024-10-15","arxiv_id":"2410.11268","n_code_links":0,"syntology":null},{"paper":"/paper/cognitive-overload-attack-prompt-injection","slug":"cognitive-overload-attack-prompt-injection","title":"Cognitive Overload Attack:Prompt Injection for Long Context","date":"2024-10-15","arxiv_id":"2410.11272","n_code_links":1,"syntology":null},{"paper":"/paper/de-jargonizing-science-for-journalists-with","slug":"de-jargonizing-science-for-journalists-with","title":"De-jargonizing Science for Journalists with GPT-4: A Pilot Study","date":"2024-10-15","arxiv_id":"2410.12069","n_code_links":1,"syntology":null},{"paper":"/paper/deciphering-the-chaos-enhancing-jailbreak","slug":"deciphering-the-chaos-enhancing-jailbreak","title":"Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation","date":"2024-10-15","arxiv_id":"2410.11317","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":["qizhangli/adversarial-prompt-translator"],"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":"dodt-enhanced-online-decision-transformer","title":"DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting","date":"2024-10-15","arxiv_id":"2410.11359","n_code_links":0,"syntology":null},{"paper":"/paper/dynamicer-resolving-emerging-mentions-to","slug":"dynamicer-resolving-emerging-mentions-to","title":"DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG","date":"2024-10-15","arxiv_id":"2410.11494","n_code_links":1,"syntology":null},{"paper":null,"slug":"ed-vit-splitting-vision-transformer-for","title":"Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference","date":"2024-10-15","arxiv_id":"2410.11650","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidence-of-cognitive-deficits","title":"Evidence of Cognitive Deficits andDevelopmental Advances in Generative AI: A Clock Drawing Test Analysis","date":"2024-10-15","arxiv_id":"2410.11756","n_code_links":0,"syntology":null},{"paper":null,"slug":"holistic-reasoning-with-long-context-lms-a","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","date":"2024-10-15","arxiv_id":"2410.11996","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-hate-lost-in-translation-evaluation-of","title":"\"Is Hate Lost in Translation?\": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection","date":"2024-10-15","arxiv_id":"2410.11230","n_code_links":0,"syntology":null},{"paper":"/paper/jigsaw-puzzles-splitting-harmful-questions-to","slug":"jigsaw-puzzles-splitting-harmful-questions-to","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","date":"2024-10-15","arxiv_id":"2410.11459","n_code_links":1,"syntology":null},{"paper":"/paper/meta-dt-offline-meta-rl-as-conditional","slug":"meta-dt-offline-meta-rl-as-conditional","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","date":"2024-10-15","arxiv_id":"2410.11448","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"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) · 2 unverified","official":{"repos":["nju-rl/meta-dt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/moh-multi-head-attention-as-mixture-of-head","slug":"moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","arxiv_id":"2410.11842","n_code_links":3,"syntology":{"ran":14,"of":18,"n_ran_checked":6,"n_instrument":8,"unverified":4,"pointer_only":3,"phrase":"14 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","official":{"repos":["skyworkai/moh"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/mtu-bench-a-multi-granularity-tool-use","slug":"mtu-bench-a-multi-granularity-tool-use","title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","date":"2024-10-15","arxiv_id":"2410.11710","n_code_links":1,"syntology":null},{"paper":"/paper/multiview-scene-graph","slug":"multiview-scene-graph","title":"Multiview Scene Graph","date":"2024-10-15","arxiv_id":"2410.11187","n_code_links":1,"syntology":{"ran":17,"of":37,"n_ran_checked":11,"n_instrument":6,"unverified":20,"pointer_only":37,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified","official":{"repos":["ai4ce/MSG"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":20,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nonlinear-gaussian-process-tomography-with","title":"Nonlinear Gaussian process tomography with imposed non-negativity constraints on physical quantities for plasma diagnostics","date":"2024-10-15","arxiv_id":"2410.11454","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-capacity-of-citation-generation-by","title":"On the Capacity of Citation Generation by Large Language Models","date":"2024-10-15","arxiv_id":"2410.11217","n_code_links":0,"syntology":null},{"paper":"/paper/pixology-probing-the-linguistic-and-visual","slug":"pixology-probing-the-linguistic-and-visual","title":"Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models","date":"2024-10-15","arxiv_id":"2410.12011","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kushaltatariya/Pixology"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"redeep-detecting-hallucination-in-retrieval","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","date":"2024-10-15","arxiv_id":"2410.11414","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-graph-transformer-architecture","title":"Rethinking Graph Transformer Architecture Design for Node Classification","date":"2024-10-15","arxiv_id":"2410.11189","n_code_links":0,"syntology":null},{"paper":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","n_code_links":0,"syntology":null},{"paper":"/paper/rulerag-rule-guided-retrieval-augmented","slug":"rulerag-rule-guided-retrieval-augmented","title":"RuleRAG: Rule-guided retrieval-augmented generation with language models for question answering","date":"2024-10-15","arxiv_id":"2410.22353","n_code_links":1,"syntology":null},{"paper":null,"slug":"seadate-remedy-dual-attention-transformer","title":"SeaDATE: Remedy Dual-Attention Transformer with Semantic Alignment via Contrast Learning for Multimodal Object Detection","date":"2024-10-15","arxiv_id":"2410.11358","n_code_links":0,"syntology":null},{"paper":null,"slug":"seer-self-aligned-evidence-extraction-for","title":"SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11315","n_code_links":0,"syntology":null},{"paper":null,"slug":"selection-p-self-supervised-task-agnostic","title":"Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability","date":"2024-10-15","arxiv_id":"2410.11786","n_code_links":0,"syntology":null},{"paper":"/paper/self-adaptive-multimodal-retrieval-augmented","slug":"self-adaptive-multimodal-retrieval-augmented","title":"Self-adaptive Multimodal Retrieval-Augmented Generation","date":"2024-10-15","arxiv_id":"2410.11321","n_code_links":1,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","n_code_links":0,"syntology":null},{"paper":null,"slug":"sorted-weight-sectioning-for-energy-efficient","title":"Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars","date":"2024-10-15","arxiv_id":"2410.11298","n_code_links":0,"syntology":null},{"paper":null,"slug":"survey-and-evaluation-of-converging","title":"Survey and Evaluation of Converging Architecture in LLMs based on Footsteps of Operations","date":"2024-10-15","arxiv_id":"2410.11381","n_code_links":0,"syntology":null},{"paper":null,"slug":"synthetic-interlocutors-experiments-with","title":"Synthetic Interlocutors. Experiments with Generative AI to Prolong Ethnographic Encounters","date":"2024-10-15","arxiv_id":"2410.11395","n_code_links":0,"syntology":null},{"paper":null,"slug":"telco-dpr-a-hybrid-dataset-for-evaluating","title":"Telco-DPR: A Hybrid Dataset for Evaluating Retrieval Models of 3GPP Technical Specifications","date":"2024-10-15","arxiv_id":"2410.19790","n_code_links":0,"syntology":null},{"paper":"/paper/the-persian-rug-solving-toy-models-of","slug":"the-persian-rug-solving-toy-models-of","title":"The Persian Rug: solving toy models of superposition using large-scale symmetries","date":"2024-10-15","arxiv_id":"2410.12101","n_code_links":1,"syntology":null},{"paper":null,"slug":"tokenization-and-morphology-in-multilingual","title":"Tokenization and Morphology in Multilingual Language Models: A Comparative Analysis of mT5 and ByT5","date":"2024-10-15","arxiv_id":"2410.11627","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-realistic-evaluation-of-commit","title":"Towards Realistic Evaluation of Commit Message Generation by Matching Online and Offline Settings","date":"2024-10-15","arxiv_id":"2410.12046","n_code_links":0,"syntology":null},{"paper":"/paper/tram-enhancing-user-sleep-prediction-with","slug":"tram-enhancing-user-sleep-prediction-with","title":"TraM : Enhancing User Sleep Prediction with Transformer-based Multivariate Time Series Modeling and Machine Learning Ensembles","date":"2024-10-15","arxiv_id":"2410.11293","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformer-layer-injection-a-novel-approach","title":"Transformer Layer Injection: A Novel Approach for Efficient Upscaling of Large Language Models","date":"2024-10-15","arxiv_id":"2410.11654","n_code_links":0,"syntology":null},{"paper":null,"slug":"umambatsf-a-u-shaped-multi-scale-long-term","title":"UmambaTSF: A U-shaped Multi-Scale Long-Term Time Series Forecasting Method Using Mamba","date":"2024-10-15","arxiv_id":"2410.11278","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-mystery-of-visual-attributes-of","slug":"unveiling-the-mystery-of-visual-attributes-of","title":"Unveiling the Mystery of Visual Attributes of Concrete and Abstract Concepts: Variability, Nearest Neighbors, and Challenging Categories","date":"2024-10-15","arxiv_id":"2410.11657","n_code_links":1,"syntology":null},{"paper":null,"slug":"visual-fixation-based-retinal-prosthetic","title":"Visual Fixation-Based Retinal Prosthetic Simulation","date":"2024-10-15","arxiv_id":"2410.11688","n_code_links":0,"syntology":null},{"paper":"/paper/a-consistency-aware-spot-guided-transformer","slug":"a-consistency-aware-spot-guided-transformer","title":"A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration","date":"2024-10-14","arxiv_id":"2410.10295","n_code_links":1,"syntology":null},{"paper":"/paper/an-annotated-dataset-of-errors-in-premodern","slug":"an-annotated-dataset-of-errors-in-premodern","title":"An Annotated Dataset of Errors in Premodern Greek and Baselines for Detecting Them","date":"2024-10-14","arxiv_id":"2410.11071","n_code_links":1,"syntology":null},{"paper":"/paper/audio-captioning-via-generative-pair-to-pair","slug":"audio-captioning-via-generative-pair-to-pair","title":"Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning","date":"2024-10-14","arxiv_id":"2410.10913","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-rag-question-identification-and-answer","title":"Beyond-RAG: Question Identification and Answer Generation in Real-Time Conversations","date":"2024-10-14","arxiv_id":"2410.10136","n_code_links":0,"syntology":null},{"paper":null,"slug":"big-little-vision-transformer-for-efficient","title":"big.LITTLE Vision Transformer for Efficient Visual Recognition","date":"2024-10-14","arxiv_id":"2410.10267","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-mixer-ya-nahi-novel-approaches-to","title":"Code-Mixer Ya Nahi: Novel Approaches to Measuring Multilingual LLMs' Code-Mixing Capabilities","date":"2024-10-14","arxiv_id":"2410.11079","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparison-of-deep-learning-and-conventional","title":"Comparison of deep learning and conventional methods for disease onset prediction","date":"2024-10-14","arxiv_id":"2410.10505","n_code_links":0,"syntology":null},{"paper":"/paper/customize-your-visual-autoregressive-recipe","slug":"customize-your-visual-autoregressive-recipe","title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","date":"2024-10-14","arxiv_id":"2410.10511","n_code_links":1,"syntology":null},{"paper":null,"slug":"dissecting-embedding-method-learning-higher","title":"Dissecting embedding method: learning higher-order structures from data","date":"2024-10-14","arxiv_id":"2410.10917","n_code_links":0,"syntology":null}],"record_sha256":"5ade16ed2482831d222d04b44f0535d74b2aa691a2f074d1445ee17caa297589","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}