{"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/19","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":19,"pages_in_order":255,"rows_per_page":100,"rows":[1801,1900],"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/18","next":"/method/linear-layer/papers/20","papers":[{"paper":null,"slug":"is-relevance-propagated-from-retriever-to","title":"Is Relevance Propagated from Retriever to Generator in RAG?","date":"2025-02-20","arxiv_id":"2502.15025","n_code_links":0,"syntology":null},{"paper":null,"slug":"kitab-bench-a-comprehensive-multi-domain","title":"KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding","date":"2025-02-20","arxiv_id":"2502.14949","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-understanding-of-language-models","title":"Mechanistic Understanding of Language Models in Syntactic Code Completion","date":"2025-02-20","arxiv_id":"2502.18499","n_code_links":0,"syntology":null},{"paper":"/paper/multiscale-byte-language-models-a","slug":"multiscale-byte-language-models-a","title":"Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling","date":"2025-02-20","arxiv_id":"2502.14553","n_code_links":1,"syntology":null},{"paper":"/paper/on-the-influence-of-context-size-and-model","slug":"on-the-influence-of-context-size-and-model","title":"On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems","date":"2025-02-20","arxiv_id":"2502.14759","n_code_links":1,"syntology":null},{"paper":null,"slug":"paperhelper-knowledge-based-llm-qa-paper","title":"PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant","date":"2025-02-20","arxiv_id":"2502.14271","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-fetal-birthweight-from-high","title":"Predicting Fetal Birthweight from High Dimensional Data using Advanced Machine Learning","date":"2025-02-20","arxiv_id":"2502.14270","n_code_links":0,"syntology":null},{"paper":null,"slug":"quad-llm-mltc-large-language-models-ensemble","title":"QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification","date":"2025-02-20","arxiv_id":"2502.14189","n_code_links":0,"syntology":null},{"paper":null,"slug":"relactrl-relevance-guided-efficient-control","title":"RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers","date":"2025-02-20","arxiv_id":"2502.14377","n_code_links":0,"syntology":null},{"paper":null,"slug":"tabular-embeddings-for-tables-with-bi","title":"Tabular Embeddings for Tables with Bi-Dimensional Hierarchical Metadata and Nesting","date":"2025-02-20","arxiv_id":"2502.15819","n_code_links":0,"syntology":null},{"paper":"/paper/towards-economical-inference-enabling","slug":"towards-economical-inference-enabling","title":"Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs","date":"2025-02-20","arxiv_id":"2502.14837","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":10,"n_instrument":0,"unverified":5,"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) · 5 unverified","official":{"repos":["JT-Ushio/MHA2MLA"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wavrag-audio-integrated-retrieval-augmented","title":"WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models","date":"2025-02-20","arxiv_id":"2502.14727","n_code_links":0,"syntology":null},{"paper":null,"slug":"adapting-large-language-models-for-time","title":"Adapting Large Language Models for Time Series Modeling via a Novel Parameter-efficient Adaptation Method","date":"2025-02-19","arxiv_id":"2502.13725","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-large-language-models-in-context-graph","title":"Are Large Language Models In-Context Graph Learners?","date":"2025-02-19","arxiv_id":"2502.13562","n_code_links":0,"syntology":null},{"paper":"/paper/building-age-estimation-a-new-multi-modal","slug":"building-age-estimation-a-new-multi-modal","title":"Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challenge","date":"2025-02-19","arxiv_id":"2502.13818","n_code_links":1,"syntology":null},{"paper":null,"slug":"capturing-rich-behavior-representations-a","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","date":"2025-02-19","arxiv_id":"2502.13754","n_code_links":0,"syntology":null},{"paper":null,"slug":"dh-rag-a-dynamic-historical-context-powered","title":"DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue","date":"2025-02-19","arxiv_id":"2502.13847","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-social-connections-from-finnish","title":"Extracting Social Connections from Finnish Karelian Refugee Interviews Using LLMs","date":"2025-02-19","arxiv_id":"2502.13566","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairkv-balancing-per-head-kv-cache-for-fast","title":"FairKV: Balancing Per-Head KV Cache for Fast Multi-GPU Inference","date":"2025-02-19","arxiv_id":"2502.15804","n_code_links":0,"syntology":null},{"paper":null,"slug":"flextok-resampling-images-into-1d-token","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","date":"2025-02-19","arxiv_id":"2502.13967","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-correctness-to-comprehension-ai-agents","title":"From Correctness to Comprehension: AI Agents for Personalized Error Diagnosis in Education","date":"2025-02-19","arxiv_id":"2502.13789","n_code_links":0,"syntology":null},{"paper":null,"slug":"giving-ai-personalities-leads-to-more-human","title":"Giving AI Personalities Leads to More Human-Like Reasoning","date":"2025-02-19","arxiv_id":"2502.14155","n_code_links":0,"syntology":null},{"paper":null,"slug":"hawkbench-investigating-resilience-of-rag","title":"HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks","date":"2025-02-19","arxiv_id":"2502.13465","n_code_links":0,"syntology":null},{"paper":null,"slug":"hidden-darkness-in-llm-generated-designs","title":"Hidden Darkness in LLM-Generated Designs: Exploring Dark Patterns in Ecommerce Web Components Generated by LLMs","date":"2025-02-19","arxiv_id":"2502.13499","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-place-updates-of-a-graph-index-for","title":"In-Place Updates of a Graph Index for Streaming Approximate Nearest Neighbor Search","date":"2025-02-19","arxiv_id":"2502.13826","n_code_links":0,"syntology":null},{"paper":null,"slug":"inner-thinking-transformer-leveraging-dynamic","title":"Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking","date":"2025-02-19","arxiv_id":"2502.13842","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-novel-transformer-architecture-for","title":"Learning Novel Transformer Architecture for Time-series Forecasting","date":"2025-02-19","arxiv_id":"2502.13721","n_code_links":0,"syntology":null},{"paper":"/paper/medical-image-classification-with-kan","slug":"medical-image-classification-with-kan","title":"Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention","date":"2025-02-19","arxiv_id":"2502.13693","n_code_links":1,"syntology":null},{"paper":"/paper/mom-linear-sequence-modeling-with-mixture-of","slug":"mom-linear-sequence-modeling-with-mixture-of","title":"MoM: Linear Sequence Modeling with Mixture-of-Memories","date":"2025-02-19","arxiv_id":"2502.13685","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"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) · 3 unverified","official":{"repos":["opensparsellms/linear-moe","opensparsellms/mom"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/pitvqa-vector-matrix-low-rank-adaptation-for","slug":"pitvqa-vector-matrix-low-rank-adaptation-for","title":"PitVQA++: Vector Matrix-Low-Rank Adaptation for Open-Ended Visual Question Answering in Pituitary Surgery","date":"2025-02-19","arxiv_id":"2502.14149","n_code_links":1,"syntology":null},{"paper":"/paper/qwen2-5-vl-technical-report","slug":"qwen2-5-vl-technical-report","title":"Qwen2.5-VL Technical Report","date":"2025-02-19","arxiv_id":"2502.13923","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":null}},{"paper":null,"slug":"rag-gym-optimizing-reasoning-and-search","title":"RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision","date":"2025-02-19","arxiv_id":"2502.13957","n_code_links":0,"syntology":null},{"paper":null,"slug":"raptor-refined-approach-for-product-table","title":"RAPTOR: Refined Approach for Product Table Object Recognition","date":"2025-02-19","arxiv_id":"2502.14918","n_code_links":0,"syntology":null},{"paper":null,"slug":"rgar-recurrence-generation-augmented","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","date":"2025-02-19","arxiv_id":"2502.13361","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-point-transformer-for-point-cloud","slug":"spiking-point-transformer-for-point-cloud","title":"Spiking Point Transformer for Point Cloud Classification","date":"2025-02-19","arxiv_id":"2502.15811","n_code_links":1,"syntology":null},{"paper":null,"slug":"star-sql-self-taught-reasoner-for-text-to-sql","title":"STaR-SQL: Self-Taught Reasoner for Text-to-SQL","date":"2025-02-19","arxiv_id":"2502.13550","n_code_links":0,"syntology":null},{"paper":"/paper/token-adaptation-via-side-graph-convolution","slug":"token-adaptation-via-side-graph-convolution","title":"Token Adaptation via Side Graph Convolution for Temporally and Spatially Efficient Fine-tuning of 3D Point Cloud Transformers","date":"2025-02-19","arxiv_id":"2502.14142","n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-semantic-embeddings-of-chemical","title":"Universal Semantic Embeddings of Chemical Elements for Enhanced Materials Inference and Discovery","date":"2025-02-19","arxiv_id":"2502.14912","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-are-models-thinking-about-understanding","title":"What are Models Thinking about? Understanding Large Language Model Hallucinations \"Psychology\" through Model Inner State Analysis","date":"2025-02-19","arxiv_id":"2502.13490","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-llm-powered-agent-for-physiological-data","title":"An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation","date":"2025-02-18","arxiv_id":"2502.12836","n_code_links":0,"syntology":null},{"paper":"/paper/deepresonance-enhancing-multimodal-music","slug":"deepresonance-enhancing-multimodal-music","title":"DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning","date":"2025-02-18","arxiv_id":"2502.12623","n_code_links":0,"syntology":{"ran":7,"of":12,"n_ran_checked":4,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"hoprag-multi-hop-reasoning-for-logic-aware","title":"HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation","date":"2025-02-18","arxiv_id":"2502.12442","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-clinical-question-answering-with","title":"Improving Clinical Question Answering with Multi-Task Learning: A Joint Approach for Answer Extraction and Medical Categorization","date":"2025-02-18","arxiv_id":"2502.13108","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-barriers-evaluating-cross-lingual","title":"Language Barriers: Evaluating Cross-Lingual Performance of CNN and Transformer Architectures for Speech Quality Estimation","date":"2025-02-18","arxiv_id":"2502.13004","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-models-are-few-shot-graders","title":"Language Models are Few-Shot Graders","date":"2025-02-18","arxiv_id":"2502.13337","n_code_links":0,"syntology":null},{"paper":null,"slug":"lmn-a-tool-for-generating-machine-enforceable","title":"LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs","date":"2025-02-18","arxiv_id":"2502.12460","n_code_links":0,"syntology":null},{"paper":null,"slug":"matterchat-a-multi-modal-llm-for-material","title":"MatterChat: A Multi-Modal LLM for Material Science","date":"2025-02-18","arxiv_id":"2502.13107","n_code_links":0,"syntology":null},{"paper":"/paper/multi-view-contrastive-network-mcnet-for","slug":"multi-view-contrastive-network-mcnet-for","title":"MVCNet: Multi-View Contrastive Network for Motor Imagery Classification","date":"2025-02-18","arxiv_id":"2502.17482","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-mamba-decoder-only-multimodal","slug":"multimodal-mamba-decoder-only-multimodal","title":"Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation","date":"2025-02-18","arxiv_id":"2502.13145","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-sleep-stage-and-sleep-apnea","title":"Multimodal Sleep Stage and Sleep Apnea Classification Using Vision Transformer: A Multitask Explainable Learning Approach","date":"2025-02-18","arxiv_id":"2502.17486","n_code_links":0,"syntology":null},{"paper":"/paper/myna-masking-based-contrastive-learning-of","slug":"myna-masking-based-contrastive-learning-of","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","date":"2025-02-18","arxiv_id":"2502.12511","n_code_links":1,"syntology":null},{"paper":null,"slug":"oreo-a-plug-in-context-reconstructor-to","title":"Oreo: A Plug-in Context Reconstructor to Enhance Retrieval-Augmented Generation","date":"2025-02-18","arxiv_id":"2502.13019","n_code_links":0,"syntology":null},{"paper":"/paper/pathrag-pruning-graph-based-retrieval","slug":"pathrag-pruning-graph-based-retrieval","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","date":"2025-02-18","arxiv_id":"2502.14902","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":["bupt-gamma/pathrag"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"ringformer-rethinking-recurrent-transformer","title":"RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals","date":"2025-02-18","arxiv_id":"2502.13181","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-transformers-as-iterative","title":"Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction","date":"2025-02-18","arxiv_id":"2502.15794","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-an-automated-workflow-in-materials","title":"Towards an automated workflow in materials science for combining multi-modal simulative and experimental information using data mining and large language models","date":"2025-02-18","arxiv_id":"2502.14904","n_code_links":0,"syntology":null},{"paper":"/paper/when-segmentation-meets-hyperspectral-image","slug":"when-segmentation-meets-hyperspectral-image","title":"When Segmentation Meets Hyperspectral Image: New Paradigm for Hyperspectral Image Classification","date":"2025-02-18","arxiv_id":"2502.12541","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-on-bridging-eeg-signals-and","title":"A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond","date":"2025-02-17","arxiv_id":"2502.12048","n_code_links":0,"syntology":null},{"paper":"/paper/adasplash-adaptive-sparse-flash-attention","slug":"adasplash-adaptive-sparse-flash-attention","title":"AdaSplash: Adaptive Sparse Flash Attention","date":"2025-02-17","arxiv_id":"2502.12082","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"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) · 1 unverified","official":{"repos":["deep-spin/adasplash"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"ai-generated-text-detection-with-a-gltr-based","title":"AI-generated Text Detection with a GLTR-based Approach","date":"2025-02-17","arxiv_id":"2502.12064","n_code_links":0,"syntology":null},{"paper":null,"slug":"biases-in-edge-language-models-detection","title":"Biases in Edge Language Models: Detection, Analysis, and Mitigation","date":"2025-02-17","arxiv_id":"2502.11349","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-llms-simulate-social-media-engagement-a","title":"Can LLMs Simulate Social Media Engagement? A Study on Action-Guided Response Generation","date":"2025-02-17","arxiv_id":"2502.12073","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmqcic-bench-a-chinese-benchmark-for","title":"CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation","date":"2025-02-17","arxiv_id":"2502.11703","n_code_links":0,"syntology":null},{"paper":"/paper/deep-spatio-temporal-neural-network-for-air","slug":"deep-spatio-temporal-neural-network-for-air","title":"Deep Spatio-Temporal Neural Network for Air Quality Reanalysis","date":"2025-02-17","arxiv_id":"2502.11941","n_code_links":1,"syntology":null},{"paper":null,"slug":"disco-device-server-collaborative-llm-based","title":"DiSCo: Device-Server Collaborative LLM-Based Text Streaming Services","date":"2025-02-17","arxiv_id":"2502.11417","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-rag-really-perform-bad-for-long-context","title":"Does RAG Really Perform Bad For Long-Context Processing?","date":"2025-02-17","arxiv_id":"2502.11444","n_code_links":0,"syntology":null},{"paper":"/paper/fast-or-better-balancing-accuracy-and-cost-in","slug":"fast-or-better-balancing-accuracy-and-cost-in","title":"Fast or Better? Balancing Accuracy and Cost in Retrieval-Augmented Generation with Flexible User Control","date":"2025-02-17","arxiv_id":"2502.12145","n_code_links":1,"syntology":null},{"paper":null,"slug":"finefilter-a-fine-grained-noise-filtering","title":"FineFilter: A Fine-grained Noise Filtering Mechanism for Retrieval-Augmented Large Language Models","date":"2025-02-17","arxiv_id":"2502.11811","n_code_links":0,"syntology":null},{"paper":null,"slug":"gltw-joint-improved-graph-transformer-and-llm","title":"GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion","date":"2025-02-17","arxiv_id":"2502.11471","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-graph-topic-modeling-with-topic","title":"Hierarchical Graph Topic Modeling with Topic Tree-based Transformer","date":"2025-02-17","arxiv_id":"2502.11345","n_code_links":0,"syntology":null},{"paper":null,"slug":"hyperspherical-energy-transformer-with","title":"Hyperspherical Energy Transformer with Recurrent Depth","date":"2025-02-17","arxiv_id":"2502.11646","n_code_links":0,"syntology":null},{"paper":"/paper/if-attention-serves-as-a-cognitive-model-of","slug":"if-attention-serves-as-a-cognitive-model-of","title":"If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?","date":"2025-02-17","arxiv_id":"2502.11469","n_code_links":0,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/maskgwm-a-generalizable-driving-world-model","slug":"maskgwm-a-generalizable-driving-world-model","title":"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction","date":"2025-02-17","arxiv_id":"2502.11663","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":2,"n_instrument":2,"unverified":4,"pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["sensetime-fvg/opendwm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/musc-improving-complex-instruction-following","slug":"musc-improving-complex-instruction-following","title":"MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training","date":"2025-02-17","arxiv_id":"2502.11541","n_code_links":1,"syntology":null},{"paper":null,"slug":"oct-data-is-all-you-need-how-vision","title":"OCT Data is All You Need: How Vision Transformers with and without Pre-training Benefit Imaging","date":"2025-02-17","arxiv_id":"2502.12379","n_code_links":0,"syntology":null},{"paper":null,"slug":"rag-vs-graphrag-a-systematic-evaluation-and","title":"RAG vs. GraphRAG: A Systematic Evaluation and Key Insights","date":"2025-02-17","arxiv_id":"2502.11371","n_code_links":0,"syntology":null},{"paper":null,"slug":"real-mm-rag-a-real-world-multi-modal","title":"REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark","date":"2025-02-17","arxiv_id":"2502.12342","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-financial-sentiment-analysis-a","slug":"revisiting-financial-sentiment-analysis-a","title":"Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting","date":"2025-02-17","arxiv_id":"2502.14897","n_code_links":1,"syntology":null},{"paper":null,"slug":"revisiting-robust-rag-do-we-still-need","title":"Revisiting Robust RAG: Do We Still Need Complex Robust Training in the Era of Powerful LLMs?","date":"2025-02-17","arxiv_id":"2502.11400","n_code_links":0,"syntology":null},{"paper":null,"slug":"s2tx-cross-attention-multi-scale-state-space","title":"S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting","date":"2025-02-17","arxiv_id":"2502.11340","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartllm-smart-contract-auditing-using-custom","title":"SmartLLM: Smart Contract Auditing using Custom Generative AI","date":"2025-02-17","arxiv_id":"2502.13167","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-geometry-of-bert","title":"The geometry of BERT","date":"2025-02-17","arxiv_id":"2502.12033","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-efficient-pre-training-exploring-fp4","title":"Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models","date":"2025-02-17","arxiv_id":"2502.11458","n_code_links":0,"syntology":null},{"paper":"/paper/towards-mechanistic-interpretability-of-graph","slug":"towards-mechanistic-interpretability-of-graph","title":"Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs","date":"2025-02-17","arxiv_id":"2502.12352","n_code_links":1,"syntology":null},{"paper":"/paper/x-il-exploring-the-design-space-of-imitation","slug":"x-il-exploring-the-design-space-of-imitation","title":"X-IL: Exploring the Design Space of Imitation Learning Policies","date":"2025-02-17","arxiv_id":"2502.12330","n_code_links":1,"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":["ALRhub/X_IL"],"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":"zero-token-driven-deep-thinking-in-llms","title":"Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement","date":"2025-02-17","arxiv_id":"2502.12214","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-recurrent-vision-transformer-shows","title":"A recurrent vision transformer shows signatures of primate visual attention","date":"2025-02-16","arxiv_id":"2502.10955","n_code_links":0,"syntology":null},{"paper":null,"slug":"anyrefill-a-unified-data-efficient-framework","title":"AnyRefill: A Unified, Data-Efficient Framework for Left-Prompt-Guided Vision Tasks","date":"2025-02-16","arxiv_id":"2502.11158","n_code_links":0,"syntology":null},{"paper":null,"slug":"audiospa-spatializing-sound-events-with-text","title":"AudioSpa: Spatializing Sound Events with Text","date":"2025-02-16","arxiv_id":"2502.11219","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-the-gap-enabling-natural-language","title":"Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation","date":"2025-02-16","arxiv_id":"2502.11201","n_code_links":0,"syntology":null},{"paper":"/paper/davimnet-ssms-based-domain-adaptive-object","slug":"davimnet-ssms-based-domain-adaptive-object","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","date":"2025-02-16","arxiv_id":"2502.11178","n_code_links":2,"syntology":null},{"paper":null,"slug":"empirical-evaluation-of-llms-in-predicting","title":"Empirical evaluation of LLMs in predicting fixes of Configuration bugs in Smart Home System","date":"2025-02-16","arxiv_id":"2502.10953","n_code_links":0,"syntology":null},{"paper":"/paper/exposing-numeracy-gaps-a-benchmark-to","slug":"exposing-numeracy-gaps-a-benchmark-to","title":"Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models","date":"2025-02-16","arxiv_id":"2502.11075","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-language-models-for-enhanced","title":"Integrating Language Models for Enhanced Network State Monitoring in DRL-Based SFC Provisioning","date":"2025-02-16","arxiv_id":"2502.11298","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-language-preference-of","title":"Investigating Language Preference of Multilingual RAG Systems","date":"2025-02-16","arxiv_id":"2502.11175","n_code_links":0,"syntology":null},{"paper":"/paper/knowing-your-target-target-aware-transformer","slug":"knowing-your-target-target-aware-transformer","title":"Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding","date":"2025-02-16","arxiv_id":"2502.11168","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-conditional-mutual-information-to","title":"Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification","date":"2025-02-16","arxiv_id":"2502.11258","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitend-a-multilingual-benchmark-for","title":"MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translation","date":"2025-02-16","arxiv_id":"2502.11022","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-review-on-llm-for-solving","title":"Performance Review on LLM for solving leetcode problems","date":"2025-02-16","arxiv_id":"2502.15770","n_code_links":0,"syntology":null},{"paper":null,"slug":"quote-question-oriented-text-embeddings","title":"QuOTE: Question-Oriented Text Embeddings","date":"2025-02-16","arxiv_id":"2502.10976","n_code_links":0,"syntology":null}],"record_sha256":"e8d9db8a470521c1a33a9a6102bf06ad745e1d12f46bcbdd86d92ef9b72e54fd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}