{"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/16","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":16,"pages_in_order":255,"rows_per_page":100,"rows":[1501,1600],"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/15","next":"/method/linear-layer/papers/17","papers":[{"paper":null,"slug":"multimodal-emotion-recognition-and-sentiment","title":"Multimodal Emotion Recognition and Sentiment Analysis in Multi-Party Conversation Contexts","date":"2025-03-09","arxiv_id":"2503.06805","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-delta-parameters-as-jpeg-images-data","title":"Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform","date":"2025-03-09","arxiv_id":"2503.06676","n_code_links":0,"syntology":null},{"paper":null,"slug":"skg-llm-developing-a-mathematical-model-for","title":"SKG-LLM: Developing a Mathematical Model for Stroke Knowledge Graph Construction Using Large Language Models","date":"2025-03-09","arxiv_id":"2503.06475","n_code_links":0,"syntology":null},{"paper":null,"slug":"unigenx-unified-generation-of-sequence-and","title":"UniGenX: Unified Generation of Sequence and Structure with Autoregressive Diffusion","date":"2025-03-09","arxiv_id":"2503.06687","n_code_links":0,"syntology":null},{"paper":"/paper/a-noise-robust-turn-taking-system-for-real","slug":"a-noise-robust-turn-taking-system-for-real","title":"A Noise-Robust Turn-Taking System for Real-World Dialogue Robots: A Field Experiment","date":"2025-03-08","arxiv_id":"2503.06241","n_code_links":1,"syntology":null},{"paper":"/paper/breaking-free-from-mmi-a-new-frontier-in","slug":"breaking-free-from-mmi-a-new-frontier-in","title":"Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization","date":"2025-03-08","arxiv_id":"2503.06202","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jugechengzi/Rationalization-N2R"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/constructions-are-revealed-in-word","slug":"constructions-are-revealed-in-word","title":"Constructions are Revealed in Word Distributions","date":"2025-03-08","arxiv_id":"2503.06048","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-action-segmentation-transformer","title":"End-to-End Action Segmentation Transformer","date":"2025-03-08","arxiv_id":"2503.06316","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-hoi-reconstruction-transformer","title":"End-to-End HOI Reconstruction Transformer with Graph-based Encoding","date":"2025-03-08","arxiv_id":"2503.06012","n_code_links":0,"syntology":null},{"paper":null,"slug":"fish2mesh-transformer-3d-human-mesh-recovery","title":"Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision","date":"2025-03-08","arxiv_id":"2503.06089","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-software-kernels-and-hardware","title":"Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers","date":"2025-03-08","arxiv_id":"2503.06183","n_code_links":0,"syntology":null},{"paper":"/paper/limtopic-llm-based-topic-modeling-and-text","slug":"limtopic-llm-based-topic-modeling-and-text","title":"LimTopic: LLM-based Topic Modeling and Text Summarization for Analyzing Scientific Articles limitations","date":"2025-03-08","arxiv_id":"2503.10658","n_code_links":1,"syntology":null},{"paper":null,"slug":"moemoe-question-guided-dense-and-scalable","title":"MoEMoE: Question Guided Dense and Scalable Sparse Mixture-of-Expert for Multi-source Multi-modal Answering","date":"2025-03-08","arxiv_id":"2503.06296","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-generative-ai-s-accuracy-and","title":"Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison","date":"2025-03-08","arxiv_id":"2503.16485","n_code_links":0,"syntology":null},{"paper":null,"slug":"poisoned-mrag-knowledge-poisoning-attacks-to","title":"Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation","date":"2025-03-08","arxiv_id":"2503.06254","n_code_links":0,"syntology":null},{"paper":"/paper/x2i-seamless-integration-of-multimodal","slug":"x2i-seamless-integration-of-multimodal","title":"X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation","date":"2025-03-08","arxiv_id":"2503.06134","n_code_links":1,"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":{"repos":["oppo-mente-lab/x2i"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"a-hybrid-model-data-driven-solution-to","title":"A Hybrid Model/Data-Driven Solution to Channel, Position and Orientation Tracking in mmWave Vehicular Systems","date":"2025-03-07","arxiv_id":"2503.05091","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-real-time-multimodal-transformer-neural","title":"A Real-time Multimodal Transformer Neural Network-powered Wildfire Forecasting System","date":"2025-03-07","arxiv_id":"2503.05971","n_code_links":0,"syntology":null},{"paper":null,"slug":"bark-a-fully-bayesian-tree-kernel-for-black","title":"BARK: A Fully Bayesian Tree Kernel for Black-box Optimization","date":"2025-03-07","arxiv_id":"2503.05574","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-in-code","title":"Evaluating Large Language Models in Code Generation: INFINITE Methodology for Defining the Inference Index","date":"2025-03-07","arxiv_id":"2503.05852","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-local-and-cloud-based-large","title":"Simulating and Analysing Human Survey Responses with Large Language Models: A Case Study in Energy Stated Preference","date":"2025-03-07","arxiv_id":"2503.10652","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-open-source-large-language-models","title":"Evaluating open-source Large Language Models for automated fact-checking","date":"2025-03-07","arxiv_id":"2503.05565","n_code_links":0,"syntology":null},{"paper":"/paper/fastmap-fast-queries-initialization-based","slug":"fastmap-fast-queries-initialization-based","title":"FastMap: Fast Queries Initialization Based Vectorized HD Map Reconstruction Framework","date":"2025-03-07","arxiv_id":"2503.05492","n_code_links":1,"syntology":null},{"paper":null,"slug":"fmchs-advancing-traditional-chinese-medicine","title":"FMCHS: Advancing Traditional Chinese Medicine Herb Recommendation with Fusion of Multiscale Correlations of Herbs and Symptoms","date":"2025-03-07","arxiv_id":"2503.05167","n_code_links":0,"syntology":null},{"paper":null,"slug":"fmt-a-multimodal-pneumonia-detection-model","title":"FMT:A Multimodal Pneumonia Detection Model Based on Stacking MOE Framework","date":"2025-03-07","arxiv_id":"2503.05626","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modelling-techniques-for-analysing","title":"Language modelling techniques for analysing the impact of human genetic variation","date":"2025-03-07","arxiv_id":"2503.10655","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-approximate-caching-for-faster","title":"Leveraging Approximate Caching for Faster Retrieval-Augmented Generation","date":"2025-03-07","arxiv_id":"2503.05530","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-semantic-type-dependencies-for","title":"Leveraging Semantic Type Dependencies for Clinical Named Entity Recognition","date":"2025-03-07","arxiv_id":"2503.05373","n_code_links":0,"syntology":null},{"paper":null,"slug":"magicinfinite-generating-infinite-talking","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","date":"2025-03-07","arxiv_id":"2503.05978","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-the-robustness-of-retrieval","title":"Quantifying the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data","date":"2025-03-07","arxiv_id":"2503.05587","n_code_links":0,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-search","slug":"r1-searcher-incentivizing-the-search","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05592","n_code_links":5,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"tractable-representations-for-convergent","title":"Tractable Representations for Convergent Approximation of Distributional HJB Equations","date":"2025-03-07","arxiv_id":"2503.05563","n_code_links":0,"syntology":null},{"paper":null,"slug":"zero-shot-medical-event-prediction-using-a","title":"Zero-shot Medical Event Prediction Using a Generative Pre-trained Transformer on Electronic Health Records","date":"2025-03-07","arxiv_id":"2503.05893","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-generalist-cross-domain-molecular-learning","title":"A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery","date":"2025-03-06","arxiv_id":"2503.04362","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-rag-task-aware-kv-cache-compression","title":"Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning","date":"2025-03-06","arxiv_id":"2503.04973","n_code_links":0,"syntology":null},{"paper":null,"slug":"bicliqueencoder-an-efficient-method-for-link","title":"BicliqueEncoder: An Efficient Method for Link Prediction in Bipartite Networks using Formal Concept Analysis and Transformer Encoder","date":"2025-03-06","arxiv_id":"2503.07645","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-we-optimize-deep-rl-policy-weights-as","title":"Can We Optimize Deep RL Policy Weights as Trajectory Modeling?","date":"2025-03-06","arxiv_id":"2503.04074","n_code_links":0,"syntology":null},{"paper":null,"slug":"collapse-of-dense-retrievers-short-early-and","title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","date":"2025-03-06","arxiv_id":"2503.05037","n_code_links":0,"syntology":null},{"paper":null,"slug":"compositional-causal-reasoning-evaluation-in","title":"Compositional Causal Reasoning Evaluation in Language Models","date":"2025-03-06","arxiv_id":"2503.04556","n_code_links":0,"syntology":null},{"paper":null,"slug":"db-explore-automated-database-exploration-and","title":"DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL","date":"2025-03-06","arxiv_id":"2503.04959","n_code_links":0,"syntology":null},{"paper":"/paper/gbt-sam-a-parameter-efficient-depth-aware","slug":"gbt-sam-a-parameter-efficient-depth-aware","title":"GBT-SAM: Adapting a Foundational Deep Learning Model for Generalizable Brain Tumor Segmentation via Efficient Integration of Multi-Parametric MRI Data","date":"2025-03-06","arxiv_id":"2503.04325","n_code_links":1,"syntology":null},{"paper":null,"slug":"hedging-with-sparse-reward-reinforcement","title":"Hedging with Sparse Reward Reinforcement Learning","date":"2025-03-06","arxiv_id":"2503.04218","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-precision-transformer-based-visual","title":"High-Precision Transformer-Based Visual Servoing for Humanoid Robots in Aligning Tiny Objects","date":"2025-03-06","arxiv_id":"2503.04862","n_code_links":0,"syntology":null},{"paper":null,"slug":"hilgen-hierarchically-informed-data","title":"HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models","date":"2025-03-06","arxiv_id":"2503.04930","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-depth-analysis-of-graph-based-rag-in-a","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","date":"2025-03-06","arxiv_id":"2503.04338","n_code_links":0,"syntology":null},{"paper":null,"slug":"incentivizing-multi-tenant-split-federated","title":"Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edge","date":"2025-03-06","arxiv_id":"2503.04971","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-transformer-based-world-models-with","title":"Learning Transformer-based World Models with Contrastive Predictive Coding","date":"2025-03-06","arxiv_id":"2503.04416","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-large-language-models-to-address","slug":"leveraging-large-language-models-to-address","title":"Leveraging Large Language Models to Address Data Scarcity in Machine Learning: Applications in Graphene Synthesis","date":"2025-03-06","arxiv_id":"2503.04870","n_code_links":1,"syntology":null},{"paper":"/paper/toward-lightweight-and-fast-decoders-for","slug":"toward-lightweight-and-fast-decoders-for","title":"Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation","date":"2025-03-06","arxiv_id":"2503.04871","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-autonomous-reinforcement-learning-for","title":"Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models","date":"2025-03-06","arxiv_id":"2503.04280","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multimodal-framework-for-topic-propagation","title":"A Multimodal Framework for Topic Propagation Classification in Social Networks","date":"2025-03-05","arxiv_id":"2503.03112","n_code_links":0,"syntology":null},{"paper":null,"slug":"ahcptq-accurate-and-hardware-compatible-post","title":"AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model","date":"2025-03-05","arxiv_id":"2503.03088","n_code_links":0,"syntology":null},{"paper":"/paper/all-atom-diffusion-transformers-unified","slug":"all-atom-diffusion-transformers-unified","title":"All-atom Diffusion Transformers: Unified generative modelling of molecules and materials","date":"2025-03-05","arxiv_id":"2503.03965","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":7,"phrase":"6 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/all-atom-diffusion-transformer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-frontier-llms-replace-annotators-in","slug":"can-frontier-llms-replace-annotators-in","title":"Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions","date":"2025-03-05","arxiv_id":"2503.03261","n_code_links":1,"syntology":null},{"paper":null,"slug":"dtu-net-a-multi-scale-dilated-transformer","title":"DTU-Net: A Multi-Scale Dilated Transformer Network for Nonlinear Hyperspectral Unmixing","date":"2025-03-05","arxiv_id":"2503.03465","n_code_links":0,"syntology":null},{"paper":null,"slug":"intermediate-task-transfer-learning","title":"Intermediate-Task Transfer Learning: Leveraging Sarcasm Detection for Stance Detection","date":"2025-03-05","arxiv_id":"2503.03172","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-in-finance-estimating","title":"Large language models in finance : what is financial sentiment?","date":"2025-03-05","arxiv_id":"2503.03612","n_code_links":0,"syntology":null},{"paper":"/paper/ma-lot-multi-agent-lean-based-long-chain-of","slug":"ma-lot-multi-agent-lean-based-long-chain-of","title":"MA-LoT: Multi-Agent Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving","date":"2025-03-05","arxiv_id":"2503.03205","n_code_links":1,"syntology":null},{"paper":null,"slug":"pathrwkv-enabling-whole-slide-prediction-with","title":"PathRWKV: Enabling Whole Slide Prediction with Recurrent-Transformer","date":"2025-03-05","arxiv_id":"2503.03199","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-federated-fine-tuning-for","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","date":"2025-03-05","arxiv_id":"2503.03920","n_code_links":0,"syntology":null},{"paper":null,"slug":"pretrained-llms-as-real-time-controllers-for","title":"Pretrained LLMs as Real-Time Controllers for Robot Operated Serial Production Line","date":"2025-03-05","arxiv_id":"2503.03889","n_code_links":0,"syntology":null},{"paper":null,"slug":"riskagent-autonomous-medical-ai-copilot-for","title":"RiskAgent: Autonomous Medical AI Copilot for Generalist Risk Prediction","date":"2025-03-05","arxiv_id":"2503.03802","n_code_links":0,"syntology":null},{"paper":null,"slug":"sarcasm-detection-as-a-catalyst-improving","title":"Sarcasm Detection as a Catalyst: Improving Stance Detection with Cross-Target Capabilities","date":"2025-03-05","arxiv_id":"2503.03787","n_code_links":0,"syntology":null},{"paper":"/paper/scalefusionnet-transformer-guided-multi-scale","slug":"scalefusionnet-transformer-guided-multi-scale","title":"ScaleFusionNet: Transformer-Guided Multi-Scale Feature Fusion for Skin Lesion Segmentation","date":"2025-03-05","arxiv_id":"2503.03327","n_code_links":1,"syntology":null},{"paper":"/paper/the-box-is-in-the-pen-evaluating-commonsense-1","slug":"the-box-is-in-the-pen-evaluating-commonsense-1","title":"The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation","date":"2025-03-05","arxiv_id":"2503.03308","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-transformer-model-for-predicting-chemical","title":"A Transformer Model for Predicting Chemical Reaction Products from Generic Templates","date":"2025-03-04","arxiv_id":"2503.05810","n_code_links":0,"syntology":null},{"paper":"/paper/bhvit-binarized-hybrid-vision-transformer","slug":"bhvit-binarized-hybrid-vision-transformer","title":"BHViT: Binarized Hybrid Vision Transformer","date":"2025-03-04","arxiv_id":"2503.02394","n_code_links":1,"syntology":{"ran":16,"of":29,"n_ran_checked":15,"n_instrument":1,"unverified":13,"pointer_only":0,"phrase":"16 ran (of which 13 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","official":{"repos":["IMRL/BHViT"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":13,"n_ran_no_instrument_failure":15,"n_unverified":13,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"coserve-efficient-collaboration-of-experts","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","date":"2025-03-04","arxiv_id":"2503.02354","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-a-pet-ct-foundation-model-for","title":"Developing a PET/CT Foundation Model for Cross-Modal Anatomical and Functional Imaging","date":"2025-03-04","arxiv_id":"2503.02824","n_code_links":0,"syntology":null},{"paper":null,"slug":"effectively-steer-llm-to-follow-preference","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","date":"2025-03-04","arxiv_id":"2503.02989","n_code_links":0,"syntology":null},{"paper":null,"slug":"fouriernat-a-fourier-mixing-based-non","title":"FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation","date":"2025-03-04","arxiv_id":"2503.07630","n_code_links":0,"syntology":null},{"paper":"/paper/graph-transformer-with-disease-subgraph","slug":"graph-transformer-with-disease-subgraph","title":"Graph Transformer with Disease Subgraph Positional Encoding for Improved Comorbidity Prediction","date":"2025-03-04","arxiv_id":"2503.03046","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretable-few-shot-retinal-disease","title":"Interpretable Few-Shot Retinal Disease Diagnosis with Concept-Guided Prompting of Vision-Language Models","date":"2025-03-04","arxiv_id":"2503.02917","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-precoding-in-multi-user-multi","title":"Learning Precoding in Multi-user Multi-antenna Systems: Transformer or Graph Transformer?","date":"2025-03-04","arxiv_id":"2503.02998","n_code_links":0,"syntology":null},{"paper":null,"slug":"llave-large-language-and-vision-embedding","title":"LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning","date":"2025-03-04","arxiv_id":"2503.04812","n_code_links":0,"syntology":null},{"paper":null,"slug":"network-traffic-classification-using-machine","title":"Network Traffic Classification Using Machine Learning, Transformer, and Large Language Models","date":"2025-03-04","arxiv_id":"2503.02141","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-open-domain-question-answering","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","date":"2025-03-04","arxiv_id":"2503.02922","n_code_links":0,"syntology":null},{"paper":null,"slug":"pennylang-pioneering-llm-based-quantum-code","title":"PennyLang: Pioneering LLM-Based Quantum Code Generation with a Novel PennyLane-Centric Dataset","date":"2025-03-04","arxiv_id":"2503.02497","n_code_links":0,"syntology":null},{"paper":null,"slug":"tabby-tabular-data-synthesis-with-language","title":"Tabby: Tabular Data Synthesis with Language Models","date":"2025-03-04","arxiv_id":"2503.02152","n_code_links":0,"syntology":null},{"paper":null,"slug":"target-return-optimizer-for-multi-game","title":"Target Return Optimizer for Multi-Game Decision Transformer","date":"2025-03-04","arxiv_id":"2503.02311","n_code_links":0,"syntology":null},{"paper":null,"slug":"tetra-vpr-a-ternary-transformer-approach-for","title":"TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition","date":"2025-03-04","arxiv_id":"2503.02511","n_code_links":0,"syntology":null},{"paper":"/paper/union-of-experts-adapting-hierarchical","slug":"union-of-experts-adapting-hierarchical","title":"Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer","date":"2025-03-04","arxiv_id":"2503.02495","n_code_links":1,"syntology":null},{"paper":null,"slug":"use-me-wisely-ai-driven-assessment-for-llm","title":"Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development","date":"2025-03-04","arxiv_id":"2503.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-to-strong-generalization-even-in-random","title":"Weak-to-Strong Generalization Even in Random Feature Networks, Provably","date":"2025-03-04","arxiv_id":"2503.02877","n_code_links":0,"syntology":null},{"paper":"/paper/wikipedia-in-the-era-of-llms-evolution-and","slug":"wikipedia-in-the-era-of-llms-evolution-and","title":"Wikipedia in the Era of LLMs: Evolution and Risks","date":"2025-03-04","arxiv_id":"2503.02879","n_code_links":1,"syntology":null},{"paper":"/paper/wyckoff-transformer-generation-of-symmetric","slug":"wyckoff-transformer-generation-of-symmetric","title":"Wyckoff Transformer: Generation of Symmetric Crystals","date":"2025-03-04","arxiv_id":"2503.02407","n_code_links":1,"syntology":null},{"paper":null,"slug":"zero-shot-multi-label-classification-of","title":"Zero-Shot Multi-Label Classification of Bangla Documents: Large Decoders Vs. Classic Encoders","date":"2025-03-04","arxiv_id":"2503.02993","n_code_links":0,"syntology":null},{"paper":"/paper/2503-01306","slug":"2503-01306","title":"From Claims to Evidence: A Unified Framework and Critical Analysis of CNN vs. Transformer vs. Mamba in Medical Image Segmentation","date":"2025-03-03","arxiv_id":"2503.01306","n_code_links":1,"syntology":null},{"paper":null,"slug":"2503-01394","title":"Enhancing Social Media Rumor Detection: A Semantic and Graph Neural Network Approach for the 2024 Global Election","date":"2025-03-03","arxiv_id":"2503.01394","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01458","title":"SrSv: Integrating Sequential Rollouts with Sequential Value Estimation for Multi-agent Reinforcement Learning","date":"2025-03-03","arxiv_id":"2503.01458","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01592","title":"An Efficient Approach to Detecting Lung Nodules Using Swin Transformer","date":"2025-03-03","arxiv_id":"2503.01592","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01630","title":"Machine Learners Should Acknowledge the Legal Implications of Large Language Models as Personal Data","date":"2025-03-03","arxiv_id":"2503.01630","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01713","title":"SAGE: A Framework of Precise Retrieval for RAG","date":"2025-03-03","arxiv_id":"2503.01713","n_code_links":0,"syntology":null},{"paper":null,"slug":"2503-01814","title":"LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation","date":"2025-03-03","arxiv_id":"2503.01814","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-hybrid-cnn-transformer-model-for-heart","title":"A Hybrid CNN-Transformer Model for Heart Disease Prediction Using Life History Data","date":"2025-03-03","arxiv_id":"2503.02124","n_code_links":0,"syntology":null},{"paper":"/paper/architectural-and-inferential-inductive","slug":"architectural-and-inferential-inductive","title":"Architectural and Inferential Inductive Biases For Exchangeable Sequence Modeling","date":"2025-03-03","arxiv_id":"2503.01215","n_code_links":1,"syntology":null},{"paper":null,"slug":"asktoact-enhancing-llms-tool-use-via-self","title":"AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification","date":"2025-03-03","arxiv_id":"2503.01940","n_code_links":0,"syntology":null},{"paper":null,"slug":"attention-condensation-via-sparsity-induced","title":"Attention Condensation via Sparsity Induced Regularized Training","date":"2025-03-03","arxiv_id":"2503.01564","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-retinal-layer-and-fluid","title":"Comprehensive Evaluation of OCT-based Automated Segmentation of Retinal Layer, Fluid and Hyper-Reflective Foci: Impact on Diabetic Retinopathy Severity Assessment","date":"2025-03-03","arxiv_id":"2503.01248","n_code_links":0,"syntology":null},{"paper":null,"slug":"boolean-aware-attention-for-dense-retrieval","title":"Boolean-aware Attention for Dense Retrieval","date":"2025-03-03","arxiv_id":"2503.01753","n_code_links":0,"syntology":null}],"record_sha256":"40ea2c57667d8f8ff42d1b1a445509800d4b36f311b3b598694caf3925a45c23","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}