{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/softmax/papers/88","list_of":"/method/softmax","method":"Softmax","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":88,"pages_in_order":375,"rows_per_page":100,"rows":[8701,8800],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/softmax","prev":"/method/softmax/papers/87","next":"/method/softmax/papers/89","papers":[{"paper":null,"slug":"emotion-recognition-with-facial-attention-and","title":"Emotion Recognition with Facial Attention and Objective Activation Functions","date":"2024-10-23","arxiv_id":"2410.17740","n_code_links":0,"syntology":null},{"paper":"/paper/escaping-the-forest-sparse-interpretable","slug":"escaping-the-forest-sparse-interpretable","title":"Escaping the Forest: Sparse Interpretable Neural Networks for Tabular Data","date":"2024-10-23","arxiv_id":"2410.17758","n_code_links":1,"syntology":null},{"paper":"/paper/federated-transformer-multi-party-vertical","slug":"federated-transformer-multi-party-vertical","title":"Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data","date":"2024-10-23","arxiv_id":"2410.17986","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xtra-computing/fet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fiper-generalizable-factorized-fields-for","title":"FIPER: Generalizable Factorized Features for Robust Low-Level Vision Models","date":"2024-10-23","arxiv_id":"2410.18083","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-pdfs-to-structured-data-utilizing-llm","title":"From PDFs to Structured Data: Utilizing LLM Analysis in Sports Database Management","date":"2024-10-23","arxiv_id":"2410.17619","n_code_links":0,"syntology":null},{"paper":null,"slug":"future-token-prediction-causal-language","title":"Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction","date":"2024-10-23","arxiv_id":"2410.18160","n_code_links":0,"syntology":null},{"paper":null,"slug":"gazelle-an-instruction-dataset-for-arabic","title":"Gazelle: An Instruction Dataset for Arabic Writing Assistance","date":"2024-10-23","arxiv_id":"2410.18163","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendp-3d-semantic-fields-for-category-level","title":"GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy","date":"2024-10-23","arxiv_id":"2410.17488","n_code_links":0,"syntology":null},{"paper":"/paper/hcdn-a-change-detection-network-for","slug":"hcdn-a-change-detection-network-for","title":"HCDN: A Change Detection Network for Construction Housekeeping Using Feature Fusion and Large Vision Models","date":"2024-10-23","arxiv_id":"2410.17513","n_code_links":1,"syntology":null},{"paper":null,"slug":"holistic-structure-of-neural-pathways","title":"Holistic structure of neural pathways underlies brain perceptual rivalry: Physical mechanism of auditory stream segregation","date":"2024-10-23","arxiv_id":"2410.17620","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-continually-adapt-text-to-image","slug":"how-to-continually-adapt-text-to-image","title":"How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?","date":"2024-10-23","arxiv_id":"2410.17594","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-the-domain-adaptation-of-retrieval","title":"Leveraging the Domain Adaptation of Retrieval Augmented Generation Models for Question Answering and Reducing Hallucination","date":"2024-10-23","arxiv_id":"2410.17783","n_code_links":0,"syntology":null},{"paper":null,"slug":"lightweight-neural-app-control","title":"Lightweight Neural App Control","date":"2024-10-23","arxiv_id":"2410.17883","n_code_links":0,"syntology":null},{"paper":null,"slug":"locating-information-in-large-language-models","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","date":"2024-10-23","arxiv_id":"2410.17770","n_code_links":0,"syntology":null},{"paper":"/paper/longrag-a-dual-perspective-retrieval","slug":"longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","arxiv_id":"2410.18050","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":7,"n_instrument":1,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qingfei1/longrag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mcubert-memory-efficient-bert-inference-on","title":"MCUBERT: Memory-Efficient BERT Inference on Commodity Microcontrollers","date":"2024-10-23","arxiv_id":"2410.17957","n_code_links":0,"syntology":null},{"paper":"/paper/mia-dpo-multi-image-augmented-direct","slug":"mia-dpo-multi-image-augmented-direct","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","date":"2024-10-23","arxiv_id":"2410.17637","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":7,"n_instrument":3,"unverified":1,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["liuziyu77/mia-dpo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"milora-efficient-mixture-of-low-rank","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","date":"2024-10-23","arxiv_id":"2410.18035","n_code_links":0,"syntology":null},{"paper":null,"slug":"mojobench-language-modeling-and-benchmarks","title":"MojoBench: Language Modeling and Benchmarks for Mojo","date":"2024-10-23","arxiv_id":"2410.17736","n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-feature-reconstruction-network","slug":"multi-scale-feature-reconstruction-network","title":"Multi-scale feature reconstruction network for industrial anomaly detection","date":"2024-10-23","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"nexusindex-integrating-advanced-vector","title":"NexusIndex: Integrating Advanced Vector Indexing and Multi-Model Embeddings for Robust Fake News Detection","date":"2024-10-23","arxiv_id":"2410.18294","n_code_links":0,"syntology":null},{"paper":"/paper/omniflatten-an-end-to-end-gpt-model-for","slug":"omniflatten-an-end-to-end-gpt-model-for","title":"OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation","date":"2024-10-23","arxiv_id":"2410.17799","n_code_links":1,"syntology":null},{"paper":null,"slug":"petah-parameter-efficient-task-adaptation-for","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","date":"2024-10-23","arxiv_id":"2410.17661","n_code_links":0,"syntology":null},{"paper":null,"slug":"pgdiffseg-prior-guided-denoising-diffusion","title":"PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentation","date":"2024-10-23","arxiv_id":"2410.17812","n_code_links":0,"syntology":null},{"paper":"/paper/pod-attention-unlocking-full-prefill-decode","slug":"pod-attention-unlocking-full-prefill-decode","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","date":"2024-10-23","arxiv_id":"2410.18038","n_code_links":1,"syntology":null},{"paper":null,"slug":"simrag-self-improving-retrieval-augmented","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","date":"2024-10-23","arxiv_id":"2410.17952","n_code_links":0,"syntology":null},{"paper":"/paper/spiking-graph-neural-network-on-riemannian","slug":"spiking-graph-neural-network-on-riemannian","title":"Spiking Graph Neural Network on Riemannian Manifolds","date":"2024-10-23","arxiv_id":"2410.17941","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ZhenhHuang/MSG"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/stick-breaking-attention","slug":"stick-breaking-attention","title":"Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study","date":"2024-10-23","arxiv_id":"2410.17980","n_code_links":2,"syntology":{"ran":13,"of":15,"n_ran_checked":13,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["ibm/dolomite-engine","shawntan/stickbreaking-attention"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/surgical-scene-segmentation-by-transformer","slug":"surgical-scene-segmentation-by-transformer","title":"Surgical Scene Segmentation by Transformer With Asymmetric Feature Enhancement","date":"2024-10-23","arxiv_id":"2410.17642","n_code_links":1,"syntology":null},{"paper":"/paper/tabdpt-scaling-tabular-foundation-models","slug":"tabdpt-scaling-tabular-foundation-models","title":"TabDPT: Scaling Tabular Foundation Models","date":"2024-10-23","arxiv_id":"2410.18164","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["layer6ai-labs/TabDPT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"tage-trustworthy-attribute-group-editing-for","title":"TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation","date":"2024-10-23","arxiv_id":"2410.17855","n_code_links":0,"syntology":null},{"paper":null,"slug":"tp-eval-tap-multimodal-llms-potential-in","title":"TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts","date":"2024-10-23","arxiv_id":"2410.18071","n_code_links":0,"syntology":null},{"paper":null,"slug":"transportmer-a-holistic-approach-to","title":"TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports","date":"2024-10-23","arxiv_id":"2410.17785","n_code_links":0,"syntology":null},{"paper":"/paper/value-residual-learning-for-alleviating","slug":"value-residual-learning-for-alleviating","title":"Value Residual Learning For Alleviating Attention Concentration In Transformers","date":"2024-10-23","arxiv_id":"2410.17897","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":6,"n_instrument":3,"unverified":3,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["Zcchill/Value-Residual-Learning"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"which-client-is-reliable-a-reliable-and","title":"Which Client is Reliable?: A Reliable and Personalized Prompt-based Federated Learning for Medical Image Question Answering","date":"2024-10-23","arxiv_id":"2410.17484","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-bayesian-perspective-on-the-maximum-score","title":"A Bayesian Perspective on the Maximum Score Problem","date":"2024-10-22","arxiv_id":"2410.17153","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-statistical-analysis-of-llms-self","title":"A Statistical Analysis of LLMs' Self-Evaluation Using Proverbs","date":"2024-10-22","arxiv_id":"2410.16640","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-eye-for-an-ai-evaluating-gpt-4o-s-visual","title":"An Eye for an AI: Evaluating GPT-4o's Visual Perception Skills and Geometric Reasoning Skills Using Computer Graphics Questions","date":"2024-10-22","arxiv_id":"2410.16991","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessment-of-transformer-based-encoder","title":"Assessment of Transformer-Based Encoder-Decoder Model for Human-Like Summarization","date":"2024-10-22","arxiv_id":"2410.16842","n_code_links":0,"syntology":null},{"paper":null,"slug":"audio-to-score-conversion-model-based-on","title":"Audio-to-Score Conversion Model Based on Whisper methodology","date":"2024-10-22","arxiv_id":"2410.17209","n_code_links":0,"syntology":null},{"paper":"/paper/automated-spinal-mri-labelling-from-reports","slug":"automated-spinal-mri-labelling-from-reports","title":"Automated Spinal MRI Labelling from Reports Using a Large Language Model","date":"2024-10-22","arxiv_id":"2410.17235","n_code_links":1,"syntology":null},{"paper":null,"slug":"captions-speak-louder-than-images-caslie","title":"Captions Speak Louder than Images (CASLIE): Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data","date":"2024-10-22","arxiv_id":"2410.17337","n_code_links":0,"syntology":null},{"paper":"/paper/dhoroni-exploring-bengali-climate-change-and","slug":"dhoroni-exploring-bengali-climate-change-and","title":"Dhoroni: Exploring Bengali Climate Change and Environmental Views with a Multi-Perspective News Dataset and Natural Language Processing","date":"2024-10-22","arxiv_id":"2410.17225","n_code_links":1,"syntology":null},{"paper":"/paper/di-maskdino-a-joint-object-detection-and","slug":"di-maskdino-a-joint-object-detection-and","title":"DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model","date":"2024-10-22","arxiv_id":"2410.16707","n_code_links":1,"syntology":null},{"paper":null,"slug":"distill-synthkg-distilling-knowledge-graph","title":"Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency","date":"2024-10-22","arxiv_id":"2410.16597","n_code_links":0,"syntology":null},{"paper":"/paper/dnahlm-dna-sequence-and-human-language-mixed","slug":"dnahlm-dna-sequence-and-human-language-mixed","title":"DNAHLM -- DNA sequence and Human Language mixed large language Model","date":"2024-10-22","arxiv_id":"2410.16917","n_code_links":1,"syntology":null},{"paper":"/paper/do-vision-language-models-represent-space-and","slug":"do-vision-language-models-represent-space-and","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","date":"2024-10-22","arxiv_id":"2410.17385","n_code_links":1,"syntology":{"ran":13,"of":17,"n_ran_checked":11,"n_instrument":2,"unverified":4,"pointer_only":17,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["sled-group/COMFORT"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-graph-neural-networks-for-enhanced","title":"Dynamic graph neural networks for enhanced volatility prediction in financial markets","date":"2024-10-22","arxiv_id":"2410.16858","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-feature-extraction-using-light","title":"Efficient Feature Extraction Using Light-Weight CNN Attention-Based Deep Learning Architectures for Ultrasound Fetal Plane Classification","date":"2024-10-22","arxiv_id":"2410.17396","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-optimization-and-learning-of-fair","title":"End-to-End Optimization and Learning of Fair Court Schedules","date":"2024-10-22","arxiv_id":"2410.17415","n_code_links":0,"syntology":null},{"paper":null,"slug":"envbridge-bridging-diverse-environments-with","title":"EnvBridge: Bridging Diverse Environments with Cross-Environment Knowledge Transfer for Embodied AI","date":"2024-10-22","arxiv_id":"2410.16919","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-possibilities-of-ai-powered-legal","slug":"exploring-possibilities-of-ai-powered-legal","title":"Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling","date":"2024-10-22","arxiv_id":"2410.17210","n_code_links":1,"syntology":null},{"paper":null,"slug":"fairlora-unpacking-bias-mitigation-in-vision","title":"FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Driven Low-Rank Adaptation","date":"2024-10-22","arxiv_id":"2410.17358","n_code_links":0,"syntology":null},{"paper":null,"slug":"fastattention-extend-flashattention2-to-npus","title":"FastAttention: Extend FlashAttention2 to NPUs and Low-resource GPUs","date":"2024-10-22","arxiv_id":"2410.16663","n_code_links":0,"syntology":null},{"paper":null,"slug":"from-attention-to-activation-unravelling-the","title":"From Attention to Activation: Unravelling the Enigmas of Large Language Models","date":"2024-10-22","arxiv_id":"2410.17174","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-transformers-dream-of-electric-flow","title":"Graph Transformers Dream of Electric Flow","date":"2024-10-22","arxiv_id":"2410.16699","n_code_links":0,"syntology":null},{"paper":"/paper/high-order-associative-learning-based-on","slug":"high-order-associative-learning-based-on","title":"High-Order Associative Learning Based on Memristive Circuits for Efficient Learning","date":"2024-10-22","arxiv_id":"2410.16734","n_code_links":1,"syntology":null},{"paper":"/paper/in-context-learning-and-reasoning-for","slug":"in-context-learning-and-reasoning-for","title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","date":"2024-10-22","arxiv_id":"2410.17448","n_code_links":1,"syntology":null},{"paper":null,"slug":"interchangeable-token-embeddings-for","title":"Interchangeable Token Embeddings for Extendable Vocabulary and Alpha-Equivalence","date":"2024-10-22","arxiv_id":"2410.17161","n_code_links":0,"syntology":null},{"paper":"/paper/lino-advancing-recursive-residual","slug":"lino-advancing-recursive-residual","title":"LiNo: Advancing Recursive Residual Decomposition of Linear and Nonlinear Patterns for Robust Time Series Forecasting","date":"2024-10-22","arxiv_id":"2410.17159","n_code_links":1,"syntology":null},{"paper":null,"slug":"methods-of-improving-llm-training-stability","title":"Methods of improving LLM training stability","date":"2024-10-22","arxiv_id":"2410.16682","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-design-for-reward-modeling-in-rlhf","title":"Optimal Design for Reward Modeling in RLHF","date":"2024-10-22","arxiv_id":"2410.17055","n_code_links":0,"syntology":null},{"paper":null,"slug":"order-matters-exploring-order-sensitivity-in","title":"Order Matters: Exploring Order Sensitivity in Multimodal Large Language Models","date":"2024-10-22","arxiv_id":"2410.16983","n_code_links":0,"syntology":null},{"paper":"/paper/pldr-llm-large-language-model-from-power-law","slug":"pldr-llm-large-language-model-from-power-law","title":"PLDR-LLM: Large Language Model from Power Law Decoder Representations","date":"2024-10-22","arxiv_id":"2410.16703","n_code_links":2,"syntology":null},{"paper":"/paper/representation-shattering-in-transformers-a","slug":"representation-shattering-in-transformers-a","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","date":"2024-10-22","arxiv_id":"2410.17194","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"scattered-forest-search-smarter-code-space","title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","date":"2024-10-22","arxiv_id":"2411.05010","n_code_links":0,"syntology":null},{"paper":null,"slug":"smartrag-jointly-learn-rag-related-tasks-from","title":"SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback","date":"2024-10-22","arxiv_id":"2410.18141","n_code_links":0,"syntology":null},{"paper":"/paper/spikmamba-when-snn-meets-mamba-in-event-based","slug":"spikmamba-when-snn-meets-mamba-in-event-based","title":"SpikMamba: When SNN meets Mamba in Event-based Human Action Recognition","date":"2024-10-22","arxiv_id":"2410.16746","n_code_links":1,"syntology":null},{"paper":null,"slug":"survival-of-the-fittest-evolutionary","title":"Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts","date":"2024-10-22","arxiv_id":"2410.19852","n_code_links":0,"syntology":null},{"paper":"/paper/tracing-the-development-of-the-virtual","slug":"tracing-the-development-of-the-virtual","title":"Tracing the Development of the Virtual Particle Concept Using Semantic Change Detection","date":"2024-10-22","arxiv_id":"2410.16855","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-dual-process-vla-efficient-robotic","title":"A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM","date":"2024-10-21","arxiv_id":"2410.15549","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-fusion-driven-approach-of-attention-based","title":"A Fusion-Driven Approach of Attention-Based CNN-BiLSTM for Protein Family Classification -- ProFamNet","date":"2024-10-21","arxiv_id":"2410.17293","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-troublemaker-with-contagious-jailbreak","title":"A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns","date":"2024-10-21","arxiv_id":"2410.16155","n_code_links":0,"syntology":null},{"paper":"/paper/alignvsr-audio-visual-cross-modal-alignment","slug":"alignvsr-audio-visual-cross-modal-alignment","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","date":"2024-10-21","arxiv_id":"2410.16438","n_code_links":1,"syntology":null},{"paper":null,"slug":"all-you-need-is-an-improving-column-enhancing","title":"All You Need is an Improving Column: Enhancing Column Generation for Parallel Machine Scheduling via Transformers","date":"2024-10-21","arxiv_id":"2410.15601","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-system-for-automatic-map","slug":"an-efficient-system-for-automatic-map","title":"An Efficient System for Automatic Map Storytelling -- A Case Study on Historical Maps","date":"2024-10-21","arxiv_id":"2410.15780","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-explainable-contrastive-based-dilated","title":"An Explainable Contrastive-based Dilated Convolutional Network with Transformer for Pediatric Pneumonia Detection","date":"2024-10-21","arxiv_id":"2410.16143","n_code_links":0,"syntology":null},{"paper":"/paper/arithmetic-transformers-can-length-generalize","slug":"arithmetic-transformers-can-length-generalize","title":"Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count","date":"2024-10-21","arxiv_id":"2410.15787","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-2-4-exploring-v-n-m-sparsity-for","title":"Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs","date":"2024-10-21","arxiv_id":"2410.16135","n_code_links":0,"syntology":null},{"paper":"/paper/boosting-jailbreak-transferability-for-large","slug":"boosting-jailbreak-transferability-for-large","title":"Boosting Jailbreak Transferability for Large Language Models","date":"2024-10-21","arxiv_id":"2410.15645","n_code_links":1,"syntology":null},{"paper":"/paper/building-a-coding-assistant-via-the-retrieval","slug":"building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","n_code_links":1,"syntology":null},{"paper":null,"slug":"calibration-of-ordinal-regression-networks","title":"Calibration of ordinal regression networks","date":"2024-10-21","arxiv_id":"2410.15658","n_code_links":0,"syntology":null},{"paper":"/paper/cami2v-camera-controlled-image-to-video","slug":"cami2v-camera-controlled-image-to-video","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","date":"2024-10-21","arxiv_id":"2410.15957","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["ZGCTroy/CamI2V"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/cartesianmoe-boosting-knowledge-sharing-among","slug":"cartesianmoe-boosting-knowledge-sharing-among","title":"CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts","date":"2024-10-21","arxiv_id":"2410.16077","n_code_links":1,"syntology":null},{"paper":"/paper/causalgraph2llm-evaluating-llms-for-causal","slug":"causalgraph2llm-evaluating-llms-for-causal","title":"CausalGraph2LLM: Evaluating LLMs for Causal Queries","date":"2024-10-21","arxiv_id":"2410.15939","n_code_links":1,"syntology":null},{"paper":"/paper/compassjudger-1-all-in-one-judge-model-helps","slug":"compassjudger-1-all-in-one-judge-model-helps","title":"CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution","date":"2024-10-21","arxiv_id":"2410.16256","n_code_links":1,"syntology":null},{"paper":"/paper/deep-graph-attention-networks","slug":"deep-graph-attention-networks","title":"Deep Graph Attention Networks","date":"2024-10-21","arxiv_id":"2410.15640","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-and-data-augmentation-for","slug":"deep-learning-and-data-augmentation-for","title":"Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt","date":"2024-10-21","arxiv_id":"2410.15804","n_code_links":1,"syntology":null},{"paper":"/paper/developing-retrieval-augmented-generation-rag","slug":"developing-retrieval-augmented-generation-rag","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","date":"2024-10-21","arxiv_id":"2410.15944","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-transformer-policy","slug":"diffusion-transformer-policy","title":"Diffusion Transformer Policy","date":"2024-10-21","arxiv_id":"2410.15959","n_code_links":1,"syntology":null},{"paper":null,"slug":"disambiguating-monocular-reconstruction-of-3d","title":"Disambiguating Monocular Reconstruction of 3D Clothed Human with Spatial-Temporal Transformer","date":"2024-10-21","arxiv_id":"2410.16337","n_code_links":0,"syntology":null},{"paper":"/paper/does-your-llm-truly-unlearn-an-embarrassingly","slug":"does-your-llm-truly-unlearn-an-embarrassingly","title":"Catastrophic Failure of LLM Unlearning via Quantization","date":"2024-10-21","arxiv_id":"2410.16454","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["zzwjames/failurellmunlearning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/domain-adaptive-pre-training-of-self","slug":"domain-adaptive-pre-training-of-self","title":"Domain-Adaptive Pre-training of Self-Supervised Foundation Models for Medical Image Classification in Gastrointestinal Endoscopy","date":"2024-10-21","arxiv_id":"2410.21302","n_code_links":1,"syntology":null},{"paper":null,"slug":"enabling-energy-efficient-deployment-of-large","title":"Enabling Energy-Efficient Deployment of Large Language Models on Memristor Crossbar: A Synergy of Large and Small","date":"2024-10-21","arxiv_id":"2410.15977","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-snn-based-spatio-temporal-learning","slug":"enhancing-snn-based-spatio-temporal-learning","title":"Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model","date":"2024-10-21","arxiv_id":"2410.15689","n_code_links":1,"syntology":null},{"paper":null,"slug":"exdbn-exact-learning-of-dynamic-bayesian","title":"ExDBN: Exact learning of Dynamic Bayesian Networks","date":"2024-10-21","arxiv_id":"2410.16100","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-pretraining-via-active-forgetting","title":"Exploring Pretraining via Active Forgetting for Improving Cross Lingual Transfer for Decoder Language Models","date":"2024-10-21","arxiv_id":"2410.16168","n_code_links":0,"syntology":null},{"paper":null,"slug":"focus-where-it-matters-graph-selective-state","title":"Focus Where It Matters: Graph Selective State Focused Attention Networks","date":"2024-10-21","arxiv_id":"2410.15849","n_code_links":0,"syntology":null},{"paper":"/paper/fusionlungnet-multi-scale-fusion-convolution","slug":"fusionlungnet-multi-scale-fusion-convolution","title":"FusionLungNet: Multi-scale Fusion Convolution with Refinement Network for Lung CT Image Segmentation","date":"2024-10-21","arxiv_id":"2410.15812","n_code_links":2,"syntology":null},{"paper":null,"slug":"generalized-probabilistic-attention-mechanism","title":"Generalized Probabilistic Attention Mechanism in Transformers","date":"2024-10-21","arxiv_id":"2410.15578","n_code_links":0,"syntology":null}],"record_sha256":"fe61011fbd78f18cebda7afc7497a40a73d60030a757bb9a3c33498b70ea745b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}