{"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/adam/papers/3","list_of":"/method/adam","method":"Adam","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":3,"pages_in_order":244,"rows_per_page":100,"rows":[201,300],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/2","next":"/method/adam/papers/4","papers":[{"paper":"/paper/gainrag-preference-alignment-in-retrieval","slug":"gainrag-preference-alignment-in-retrieval","title":"GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis","date":"2025-05-24","arxiv_id":"2505.18710","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-does-sequence-modeling-architecture","title":"How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation","date":"2025-05-24","arxiv_id":"2505.18522","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-for-supply-chain-management","title":"LLMs for Supply Chain Management","date":"2025-05-24","arxiv_id":"2505.18597","n_code_links":0,"syntology":null},{"paper":null,"slug":"localizing-knowledge-in-diffusion","title":"Localizing Knowledge in Diffusion Transformers","date":"2025-05-24","arxiv_id":"2505.18832","n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-for-performance-efficient-idiom-and","title":"Pruning for Performance: Efficient Idiom and Metaphor Classification in Low-Resource Konkani Using mBERT","date":"2025-05-24","arxiv_id":"2506.02005","n_code_links":0,"syntology":null},{"paper":"/paper/removal-of-hallucination-on-hallucination","slug":"removal-of-hallucination-on-hallucination","title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","date":"2025-05-24","arxiv_id":"2505.18581","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["huenao/debate-augmented-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"security-concerns-for-large-language-models-a","title":"Security Concerns for Large Language Models: A Survey","date":"2025-05-24","arxiv_id":"2505.18889","n_code_links":0,"syntology":null},{"paper":null,"slug":"smart-energy-guardian-a-hybrid-deep-learning","title":"Smart Energy Guardian: A Hybrid Deep Learning Model for Detecting Fraudulent PV Generation","date":"2025-05-24","arxiv_id":"2505.18755","n_code_links":0,"syntology":null},{"paper":null,"slug":"strong-membership-inference-attacks-on","title":"Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models","date":"2025-05-24","arxiv_id":"2505.18773","n_code_links":0,"syntology":null},{"paper":null,"slug":"sw-vit-a-spatio-temporal-vision-transformer","title":"SW-ViT: A Spatio-Temporal Vision Transformer Network with Post Denoiser for Sequential Multi-Push Ultrasound Shear Wave Elastography","date":"2025-05-24","arxiv_id":"2505.18865","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-silent-saboteur-imperceptible-adversarial","title":"The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems","date":"2025-05-24","arxiv_id":"2505.18583","n_code_links":0,"syntology":null},{"paper":null,"slug":"trajmoe-spatially-aware-mixture-of-experts","title":"TrajMoE: Spatially-Aware Mixture of Experts for Unified Human Mobility Modeling","date":"2025-05-24","arxiv_id":"2505.18670","n_code_links":0,"syntology":null},{"paper":null,"slug":"unleashing-diffusion-transformers-for-visual","title":"Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations","date":"2025-05-24","arxiv_id":"2505.18584","n_code_links":0,"syntology":null},{"paper":null,"slug":"colora-efficient-fine-tuning-for","title":"COLORA: Efficient Fine-Tuning for Convolutional Models with a Study Case on Optical Coherence Tomography Image Classification","date":"2025-05-23","arxiv_id":"2505.18315","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-distillation-of-emotion-knowledge","slug":"contrastive-distillation-of-emotion-knowledge","title":"Contrastive Distillation of Emotion Knowledge from LLMs for Zero-Shot Emotion Recognition","date":"2025-05-23","arxiv_id":"2505.18040","n_code_links":1,"syntology":null},{"paper":"/paper/direct3d-s2-gigascale-3d-generation-made-easy","slug":"direct3d-s2-gigascale-3d-generation-made-easy","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention","date":"2025-05-23","arxiv_id":"2505.17412","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":4,"n_instrument":2,"unverified":4,"pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"explainable-anatomy-guided-ai-for-prostate","title":"Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment","date":"2025-05-23","arxiv_id":"2505.17971","n_code_links":0,"syntology":null},{"paper":null,"slug":"frequ-fnet-frequency-aware-u-net-for","title":"FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation","date":"2025-05-23","arxiv_id":"2505.17544","n_code_links":0,"syntology":null},{"paper":"/paper/gaming-tool-preferences-in-agentic-llms","slug":"gaming-tool-preferences-in-agentic-llms","title":"Gaming Tool Preferences in Agentic LLMs","date":"2025-05-23","arxiv_id":"2505.18135","n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-mamba-transformer-decoder-for-error","title":"Hybrid Mamba-Transformer Decoder for Error-Correcting Codes","date":"2025-05-23","arxiv_id":"2505.17834","n_code_links":0,"syntology":null},{"paper":null,"slug":"is-it-bad-to-work-all-the-time-cross-cultural","title":"Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4","date":"2025-05-23","arxiv_id":"2505.18322","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-assisted-web-application-functional","title":"LLM assisted web application functional requirements generation: A case study of four popular LLMs over a Mess Management System","date":"2025-05-23","arxiv_id":"2505.18019","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-probabilistic-generation-theory-a","title":"Multi-Scale Probabilistic Generation Theory: A Hierarchical Framework for Interpreting Large Language Models","date":"2025-05-23","arxiv_id":"2505.18244","n_code_links":0,"syntology":null},{"paper":"/paper/one-model-transfer-to-all-on-robust-jailbreak","slug":"one-model-transfer-to-all-on-robust-jailbreak","title":"One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs","date":"2025-05-23","arxiv_id":"2505.17598","n_code_links":1,"syntology":null},{"paper":null,"slug":"reqbrain-task-specific-instruction-tuning-of","title":"ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation","date":"2025-05-23","arxiv_id":"2505.17632","n_code_links":0,"syntology":null},{"paper":"/paper/resolving-conflicting-evidence-in-automated","slug":"resolving-conflicting-evidence-in-automated","title":"Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs","date":"2025-05-23","arxiv_id":"2505.17762","n_code_links":1,"syntology":null},{"paper":"/paper/shioenv-a-cli-behavior-capturing-environment","slug":"shioenv-a-cli-behavior-capturing-environment","title":"ShIOEnv: A CLI Behavior-Capturing Environment Enabling Grammar-Guided Command Synthesis for Dataset Curation","date":"2025-05-23","arxiv_id":"2505.18374","n_code_links":1,"syntology":null},{"paper":"/paper/token-reduction-should-go-beyond-efficiency","slug":"token-reduction-should-go-beyond-efficiency","title":"Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality","date":"2025-05-23","arxiv_id":"2505.18227","n_code_links":1,"syntology":null},{"paper":"/paper/adams-momentum-itself-can-be-a-normalizer-for","slug":"adams-momentum-itself-can-be-a-normalizer-for","title":"AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training","date":"2025-05-22","arxiv_id":"2505.16363","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pku-huzhang/AdamS"],"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":["found_in_text"]}}},{"paper":null,"slug":"align-grag-reasoning-guided-dual-alignment","title":"Align-GRAG: Reasoning-Guided Dual Alignment for Graph Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16237","n_code_links":0,"syntology":null},{"paper":"/paper/attributing-response-to-context-a-jensen","slug":"attributing-response-to-context-a-jensen","title":"Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation","date":"2025-05-22","arxiv_id":"2505.16415","n_code_links":0,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"augmenting-llm-reasoning-with-dynamic-notes","title":"Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA","date":"2025-05-22","arxiv_id":"2505.16293","n_code_links":0,"syntology":null},{"paper":"/paper/beamforming-codebook-aware-channel-knowledge","slug":"beamforming-codebook-aware-channel-knowledge","title":"Beamforming-Codebook-Aware Channel Knowledge Map Construction for Multi-Antenna Systems","date":"2025-05-22","arxiv_id":"2505.16132","n_code_links":1,"syntology":null},{"paper":null,"slug":"bottlenecked-transformers-periodic-kv-cache","title":"Bottlenecked Transformers: Periodic KV Cache Abstraction for Generalised Reasoning","date":"2025-05-22","arxiv_id":"2505.16950","n_code_links":0,"syntology":null},{"paper":null,"slug":"breaking-complexity-barriers-high-resolution","title":"Breaking Complexity Barriers: High-Resolution Image Restoration with Rank Enhanced Linear Attention","date":"2025-05-22","arxiv_id":"2505.16157","n_code_links":0,"syntology":null},{"paper":null,"slug":"caiformer-a-causal-informed-transformer-for","title":"CAIFormer: A Causal Informed Transformer for Multivariate Time Series Forecasting","date":"2025-05-22","arxiv_id":"2505.16308","n_code_links":0,"syntology":null},{"paper":null,"slug":"chain-of-thought-poisoning-attacks-against-r1","title":"Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems","date":"2025-05-22","arxiv_id":"2505.16367","n_code_links":0,"syntology":null},{"paper":null,"slug":"code-graph-model-cgm-a-graph-integrated-large","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","date":"2025-05-22","arxiv_id":"2505.16901","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-driven-breakthroughs-and-future","title":"Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review","date":"2025-05-22","arxiv_id":"2505.16771","n_code_links":0,"syntology":null},{"paper":null,"slug":"explain-less-understand-more-jargon-detection","title":"Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16227","n_code_links":0,"syntology":null},{"paper":null,"slug":"fusion-of-foundation-and-vision-transformer","title":"Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification","date":"2025-05-22","arxiv_id":"2505.16338","n_code_links":0,"syntology":null},{"paper":"/paper/generative-ai-and-creativity-a-systematic","slug":"generative-ai-and-creativity-a-systematic","title":"Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis","date":"2025-05-22","arxiv_id":"2505.17241","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-normal-patterns-in-musical-loops","title":"Learning Normal Patterns in Musical Loops","date":"2025-05-22","arxiv_id":"2505.23784","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-generative-ai-for-story-point","title":"Multimodal Generative AI for Story Point Estimation in Software Development","date":"2025-05-22","arxiv_id":"2505.16290","n_code_links":0,"syntology":null},{"paper":null,"slug":"native-segmentation-vision-transformers","title":"Native Segmentation Vision Transformers","date":"2025-05-22","arxiv_id":"2505.16993","n_code_links":0,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-dynamic","slug":"r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17005","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rucaibox/r1-searcher-plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/scalable-graph-generative-modeling-via","slug":"scalable-graph-generative-modeling-via","title":"Scalable Graph Generative Modeling via Substructure Sequences","date":"2025-05-22","arxiv_id":"2505.16130","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":["zehong-wang/g2pm"],"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":"swin-transformer-for-robust-cgi-images","title":"Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces","date":"2025-05-22","arxiv_id":"2505.16253","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-polar-express-optimal-matrix-sign-methods","title":"The Polar Express: Optimal Matrix Sign Methods and Their Application to the Muon Algorithm","date":"2025-05-22","arxiv_id":"2505.16932","n_code_links":0,"syntology":null},{"paper":null,"slug":"three-minds-one-legend-jailbreak-large","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","date":"2025-05-22","arxiv_id":"2505.16241","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-efficient-video-generation-via","slug":"training-free-efficient-video-generation-via","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","date":"2025-05-22","arxiv_id":"2505.16864","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-copilot-learning-from-the-mistake","slug":"transformer-copilot-learning-from-the-mistake","title":"Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning","date":"2025-05-22","arxiv_id":"2505.16270","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["jiaruzouu/transformercopilot"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"understanding-differential-transformer","title":"Understanding Differential Transformer Unchains Pretrained Self-Attentions","date":"2025-05-22","arxiv_id":"2505.16333","n_code_links":0,"syntology":null},{"paper":null,"slug":"voxrag-a-step-toward-transcription-free-rag","title":"VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering","date":"2025-05-22","arxiv_id":"2505.17326","n_code_links":0,"syntology":null},{"paper":"/paper/walk-retrieve-simple-yet-effective-zero-shot","slug":"walk-retrieve-simple-yet-effective-zero-shot","title":"Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks","date":"2025-05-22","arxiv_id":"2505.16849","n_code_links":1,"syntology":null},{"paper":null,"slug":"adue-improving-uncertainty-estimation-head","title":"AdUE: Improving uncertainty estimation head for LoRA adapters in LLMs","date":"2025-05-21","arxiv_id":"2505.15443","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-private-gpt-never","title":"An Efficient Private GPT Never Autoregressively Decodes","date":"2025-05-21","arxiv_id":"2505.15252","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploratory-approach-towards-investigating","title":"An Exploratory Approach Towards Investigating and Explaining Vision Transformer and Transfer Learning for Brain Disease Detection","date":"2025-05-21","arxiv_id":"2505.16039","n_code_links":0,"syntology":null},{"paper":null,"slug":"bountybench-dollar-impact-of-ai-agent","title":"BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems","date":"2025-05-21","arxiv_id":"2505.15216","n_code_links":0,"syntology":null},{"paper":null,"slug":"br-taxqa-r-a-dataset-for-question-answering","title":"BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law","date":"2025-05-21","arxiv_id":"2505.15916","n_code_links":0,"syntology":null},{"paper":null,"slug":"convergence-of-adam-in-deep-relu-networks-via","title":"Convergence of Adam in Deep ReLU Networks via Directional Complexity and Kakeya Bounds","date":"2025-05-21","arxiv_id":"2505.15013","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-vs-autoregressive-language-models-a","title":"Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective","date":"2025-05-21","arxiv_id":"2505.15045","n_code_links":0,"syntology":null},{"paper":"/paper/hdlxgraph-bridging-large-language-models-and","slug":"hdlxgraph-bridging-large-language-models-and","title":"HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases","date":"2025-05-21","arxiv_id":"2505.15701","n_code_links":1,"syntology":null},{"paper":null,"slug":"infodeepseek-benchmarking-agentic-information","title":"InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation","date":"2025-05-21","arxiv_id":"2505.15872","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-foundation-models-for-multimodal","title":"Leveraging Foundation Models for Multimodal Graph-Based Action Recognition","date":"2025-05-21","arxiv_id":"2505.15192","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-large-language-models-for-command","title":"Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects","date":"2025-05-21","arxiv_id":"2505.15088","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-explorer-a-plug-in-reinforcement-learning","title":"LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models","date":"2025-05-21","arxiv_id":"2505.15293","n_code_links":0,"syntology":null},{"paper":null,"slug":"maxpoolbert-enhancing-bert-classification-via","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","date":"2025-05-21","arxiv_id":"2505.15696","n_code_links":0,"syntology":null},{"paper":null,"slug":"mechanistic-insights-into-grokking-from-the","title":"Mechanistic Insights into Grokking from the Embedding Layer","date":"2025-05-21","arxiv_id":"2505.15624","n_code_links":0,"syntology":null},{"paper":null,"slug":"ranking-free-rag-replacing-re-ranking-with","title":"Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains","date":"2025-05-21","arxiv_id":"2505.16014","n_code_links":0,"syntology":null},{"paper":null,"slug":"reranking-with-compressed-document","title":"Reranking with Compressed Document Representation","date":"2025-05-21","arxiv_id":"2505.15394","n_code_links":0,"syntology":null},{"paper":"/paper/rlbenchnet-the-right-network-for-the-right","slug":"rlbenchnet-the-right-network-for-the-right","title":"RLBenchNet: The Right Network for the Right Reinforcement Learning Task","date":"2025-05-21","arxiv_id":"2505.15040","n_code_links":1,"syntology":null},{"paper":null,"slug":"robo-dm-data-management-for-large-robot","title":"Robo-DM: Data Management For Large Robot Datasets","date":"2025-05-21","arxiv_id":"2505.15558","n_code_links":0,"syntology":null},{"paper":"/paper/sama-unet-enhancing-medical-image","slug":"sama-unet-enhancing-medical-image","title":"SAMA-UNet: Enhancing Medical Image Segmentation with Self-Adaptive Mamba-Like Attention and Causal-Resonance Learning","date":"2025-05-21","arxiv_id":"2505.15234","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-diffusion-transformers-efficiently","slug":"scaling-diffusion-transformers-efficiently","title":"Scaling Diffusion Transformers Efficiently via $μ$P","date":"2025-05-21","arxiv_id":"2505.15270","n_code_links":1,"syntology":null},{"paper":"/paper/silent-leaks-implicit-knowledge-extraction","slug":"silent-leaks-implicit-knowledge-extraction","title":"Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries","date":"2025-05-21","arxiv_id":"2505.15420","n_code_links":1,"syntology":null},{"paper":null,"slug":"single-llm-multiple-roles-a-unified-retrieval","title":"Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization","date":"2025-05-21","arxiv_id":"2505.15444","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-language-models-in-the-real-world","title":"Small Language Models in the Real World: Insights from Industrial Text Classification","date":"2025-05-21","arxiv_id":"2505.16078","n_code_links":0,"syntology":null},{"paper":"/paper/sonnet-spectral-operator-neural-network-for","slug":"sonnet-spectral-operator-neural-network-for","title":"Sonnet: Spectral Operator Neural Network for Multivariable Time Series Forecasting","date":"2025-05-21","arxiv_id":"2505.15312","n_code_links":1,"syntology":null},{"paper":"/paper/articulatory-feature-prediction-from-surface","slug":"articulatory-feature-prediction-from-surface","title":"Articulatory Feature Prediction from Surface EMG during Speech Production","date":"2025-05-20","arxiv_id":"2505.13814","n_code_links":1,"syntology":null},{"paper":null,"slug":"automatic-dataset-generation-for-knowledge","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","date":"2025-05-20","arxiv_id":"2505.14212","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-text-unveiling-privacy-vulnerabilities","title":"Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation","date":"2025-05-20","arxiv_id":"2505.13957","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-bad-tokens-detoxification-of-llms","slug":"breaking-bad-tokens-detoxification-of-llms","title":"Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders","date":"2025-05-20","arxiv_id":"2505.14536","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/cad-coder-an-open-source-vision-language","slug":"cad-coder-an-open-source-vision-language","title":"CAD-Coder: An Open-Source Vision-Language Model for Computer-Aided Design Code Generation","date":"2025-05-20","arxiv_id":"2505.14646","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["anniedoris/cad-coder"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"choosing-a-model-shaping-a-future-comparing","title":"Choosing a Model, Shaping a Future: Comparing LLM Perspectives on Sustainability and its Relationship with AI","date":"2025-05-20","arxiv_id":"2505.14435","n_code_links":0,"syntology":null},{"paper":null,"slug":"cost-augmented-monte-carlo-tree-search-for","title":"Cost-Augmented Monte Carlo Tree Search for LLM-Assisted Planning","date":"2025-05-20","arxiv_id":"2505.14656","n_code_links":0,"syntology":null},{"paper":null,"slug":"divide-by-question-conquer-by-agent-split-rag","title":"Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning","date":"2025-05-20","arxiv_id":"2505.13994","n_code_links":0,"syntology":null},{"paper":"/paper/do-language-models-use-their-depth","slug":"do-language-models-use-their-depth","title":"Do Language Models Use Their Depth Efficiently?","date":"2025-05-20","arxiv_id":"2505.13898","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["robertcsordas/llm_effective_depth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dsmentor-enhancing-data-science-agents-with","title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","date":"2025-05-20","arxiv_id":"2505.14163","n_code_links":0,"syntology":null},{"paper":"/paper/eeg-to-text-translation-a-model-for","slug":"eeg-to-text-translation-a-model-for","title":"EEG-to-Text Translation: A Model for Deciphering Human Brain Activity","date":"2025-05-20","arxiv_id":"2505.13936","n_code_links":1,"syntology":null},{"paper":null,"slug":"energy-efficient-deep-reinforcement-learning","title":"Energy-Efficient Deep Reinforcement Learning with Spiking Transformers","date":"2025-05-20","arxiv_id":"2505.14533","n_code_links":0,"syntology":null},{"paper":null,"slug":"every-pixel-tells-a-story-end-to-end-urdu","title":"Every Pixel Tells a Story: End-to-End Urdu Newspaper OCR","date":"2025-05-20","arxiv_id":"2505.13943","n_code_links":0,"syntology":null},{"paper":"/paper/flashkat-understanding-and-addressing","slug":"flashkat-understanding-and-addressing","title":"FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer","date":"2025-05-20","arxiv_id":"2505.13813","n_code_links":1,"syntology":null},{"paper":null,"slug":"generative-ai-at-the-crossroads-light-bulb","title":"Generative AI at the Crossroads: Light Bulb, Dynamo, or Microscope?","date":"2025-05-20","arxiv_id":"2505.14588","n_code_links":0,"syntology":null},{"paper":"/paper/informatics-for-food-processing","slug":"informatics-for-food-processing","title":"Informatics for Food Processing","date":"2025-05-20","arxiv_id":"2505.17087","n_code_links":1,"syntology":null},{"paper":null,"slug":"ko-kinetics-inspired-neural-optimizer-with","title":"KO: Kinetics-inspired Neural Optimizer with PDE Simulation Approaches","date":"2025-05-20","arxiv_id":"2505.14777","n_code_links":0,"syntology":null},{"paper":"/paper/latent-flow-transformer","slug":"latent-flow-transformer","title":"Latent Flow Transformer","date":"2025-05-20","arxiv_id":"2505.14513","n_code_links":1,"syntology":null},{"paper":"/paper/learning-spatio-temporal-dynamics-for","slug":"learning-spatio-temporal-dynamics-for","title":"Learning Spatio-Temporal Dynamics for Trajectory Recovery via Time-Aware Transformer","date":"2025-05-20","arxiv_id":"2505.13857","n_code_links":2,"syntology":null},{"paper":null,"slug":"low-cost-flashattention-with-fused","title":"Low-Cost FlashAttention with Fused Exponential and Multiplication Hardware Operators","date":"2025-05-20","arxiv_id":"2505.14314","n_code_links":0,"syntology":null},{"paper":"/paper/modrwkv-transformer-multimodality-in-linear","slug":"modrwkv-transformer-multimodality-in-linear","title":"ModRWKV: Transformer Multimodality in Linear Time","date":"2025-05-20","arxiv_id":"2505.14505","n_code_links":1,"syntology":null}],"record_sha256":"9f2458aa04de44456b203a80eda9bf9c37ca87936d231f0639fd8794ee078c22","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}