{"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/93","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":93,"pages_in_order":375,"rows_per_page":100,"rows":[9201,9300],"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/92","next":"/method/softmax/papers/94","papers":[{"paper":"/paper/qianets-quantum-integrated-adaptive-networks","slug":"qianets-quantum-integrated-adaptive-networks","title":"QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models","date":"2024-10-14","arxiv_id":"2410.10318","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["edwardmagongo/quantum-inspired-model-compression"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/queryable-prototype-multiple-instance","slug":"queryable-prototype-multiple-instance","title":"Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification","date":"2024-10-14","arxiv_id":"2410.10573","n_code_links":1,"syntology":null},{"paper":"/paper/rethinking-legal-judgement-prediction-in-a","slug":"rethinking-legal-judgement-prediction-in-a","title":"Rethinking Legal Judgement Prediction in a Realistic Scenario in the Era of Large Language Models","date":"2024-10-14","arxiv_id":"2410.10542","n_code_links":1,"syntology":null},{"paper":null,"slug":"reverse-refinement-network-for-narrow-rural","title":"Reverse Refinement Network for Narrow Rural Road Detection in High-Resolution Satellite Imagery","date":"2024-10-14","arxiv_id":"2410.10389","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-and-benchmarking-graph","slug":"revisiting-and-benchmarking-graph","title":"Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective","date":"2024-10-14","arxiv_id":"2410.10241","n_code_links":1,"syntology":null},{"paper":null,"slug":"roa-bev-2d-region-oriented-attention-for-bev","title":"ROA-BEV: 2D Region-Oriented Attention for BEV-based 3D Object","date":"2024-10-14","arxiv_id":"2410.10298","n_code_links":0,"syntology":null},{"paper":"/paper/rocoft-efficient-finetuning-of-large-language","slug":"rocoft-efficient-finetuning-of-large-language","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","date":"2024-10-14","arxiv_id":"2410.10075","n_code_links":1,"syntology":null},{"paper":null,"slug":"saliency-guided-optimization-of-diffusion","title":"Saliency Guided Optimization of Diffusion Latents","date":"2024-10-14","arxiv_id":"2410.10257","n_code_links":0,"syntology":null},{"paper":"/paper/sana-efficient-high-resolution-image","slug":"sana-efficient-high-resolution-image","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10629","n_code_links":2,"syntology":null},{"paper":null,"slug":"slanc-static-layernorm-calibration","title":"SLaNC: Static LayerNorm Calibration","date":"2024-10-14","arxiv_id":"2410.10553","n_code_links":0,"syntology":null},{"paper":null,"slug":"stackfeed-structured-textual-actor-critic","title":"STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack","date":"2024-10-14","arxiv_id":"2410.10584","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-ingredients-for-robotic-diffusion","title":"The Ingredients for Robotic Diffusion Transformers","date":"2024-10-14","arxiv_id":"2410.10088","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-multi-head-attention-via","slug":"towards-better-multi-head-attention-via","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","date":"2024-10-14","arxiv_id":"2410.10914","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":7,"phrase":"4 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["dashenzi721/csp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"transforming-game-play-a-comparative-study-of","title":"Transforming Game Play: A Comparative Study of DCQN and DTQN Architectures in Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.10660","n_code_links":0,"syntology":null},{"paper":"/paper/transparent-networks-for-multivariate-time","slug":"transparent-networks-for-multivariate-time","title":"Transparent Networks for Multivariate Time Series","date":"2024-10-14","arxiv_id":"2410.10535","n_code_links":1,"syntology":null},{"paper":"/paper/v2m-visual-2-dimensional-mamba-for-image","slug":"v2m-visual-2-dimensional-mamba-for-image","title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","date":"2024-10-14","arxiv_id":"2410.10382","n_code_links":1,"syntology":null},{"paper":"/paper/visrag-vision-based-retrieval-augmented","slug":"visrag-vision-based-retrieval-augmented","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","date":"2024-10-14","arxiv_id":"2410.10594","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openbmb/visrag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/watching-the-watchers-exposing-gender","slug":"watching-the-watchers-exposing-gender","title":"Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation","date":"2024-10-14","arxiv_id":"2410.10995","n_code_links":1,"syntology":null},{"paper":"/paper/what-does-it-mean-to-be-a-transformer","slug":"what-does-it-mean-to-be-a-transformer","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","date":"2024-10-14","arxiv_id":"2410.10986","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["dalab/transformer-hessian"],"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":"/paper/when-attention-sink-emerges-in-language","slug":"when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","arxiv_id":"2410.10781","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sail-sg/attention-sink"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","n_code_links":1,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["brownfortress/llms-trc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"3ds-decomposed-difficulty-data-selection-s","title":"3DS: Decomposed Difficulty Data Selection's Case Study on LLM Medical Domain Adaptation","date":"2024-10-13","arxiv_id":"2410.10901","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pdf-parsing-tools","title":"A Comparative Study of PDF Parsing Tools Across Diverse Document Categories","date":"2024-10-13","arxiv_id":"2410.09871","n_code_links":0,"syntology":null},{"paper":null,"slug":"bidora-bi-level-optimization-based-weight","title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation","date":"2024-10-13","arxiv_id":"2410.09758","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-in-context-learning-really-generalize-to","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","date":"2024-10-13","arxiv_id":"2410.09695","n_code_links":0,"syntology":null},{"paper":null,"slug":"collu-bench-a-benchmark-for-predicting","title":"Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Code","date":"2024-10-13","arxiv_id":"2410.09997","n_code_links":0,"syntology":null},{"paper":"/paper/dag-aware-transformer-for-causal-effect","slug":"dag-aware-transformer-for-causal-effect","title":"DAG-aware Transformer for Causal Effect Estimation","date":"2024-10-13","arxiv_id":"2410.10044","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-adaptive-few-shot-multi-label","title":"Data Adaptive Few-shot Multi Label Segmentation with Foundation Model","date":"2024-10-13","arxiv_id":"2410.09759","n_code_links":0,"syntology":null},{"paper":null,"slug":"dualformer-controllable-fast-and-slow","title":"Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces","date":"2024-10-13","arxiv_id":"2410.09918","n_code_links":0,"syntology":null},{"paper":"/paper/easyjudge-an-easy-to-use-tool-for","slug":"easyjudge-an-easy-to-use-tool-for","title":"EasyJudge: an Easy-to-use Tool for Comprehensive Response Evaluation of LLMs","date":"2024-10-13","arxiv_id":"2410.09775","n_code_links":1,"syntology":null},{"paper":null,"slug":"ebdm-exemplar-guided-image-translation-with","title":"EBDM: Exemplar-guided Image Translation with Brownian-bridge Diffusion Models","date":"2024-10-13","arxiv_id":"2410.09802","n_code_links":0,"syntology":null},{"paper":null,"slug":"echoprime-a-multi-video-view-informed-vision","title":"EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation","date":"2024-10-13","arxiv_id":"2410.09704","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-dysarthric-speech-leveraging","title":"Empowering Dysarthric Speech: Leveraging Advanced LLMs for Accurate Speech Correction and Multimodal Emotion Analysis","date":"2024-10-13","arxiv_id":"2410.12867","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-gender-bias-of-llms-in-making","title":"Evaluating Gender Bias of LLMs in Making Morality Judgements","date":"2024-10-13","arxiv_id":"2410.09992","n_code_links":0,"syntology":null},{"paper":"/paper/hardmath-a-benchmark-dataset-for-challenging","slug":"hardmath-a-benchmark-dataset-for-challenging","title":"HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics","date":"2024-10-13","arxiv_id":"2410.09988","n_code_links":1,"syntology":null},{"paper":"/paper/hasn-hybrid-attention-separable-network-for","slug":"hasn-hybrid-attention-separable-network-for","title":"HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution","date":"2024-10-13","arxiv_id":"2410.09844","n_code_links":1,"syntology":null},{"paper":null,"slug":"honest-ai-fine-tuning-small-language-models","title":"Honest AI: Fine-Tuning \"Small\" Language Models to Say \"I Don't Know\", and Reducing Hallucination in RAG","date":"2024-10-13","arxiv_id":"2410.09699","n_code_links":0,"syntology":null},{"paper":"/paper/intermask-3d-human-interaction-generation-via","slug":"intermask-3d-human-interaction-generation-via","title":"InterMask: 3D Human Interaction Generation via Collaborative Masked Modelling","date":"2024-10-13","arxiv_id":"2410.10010","n_code_links":1,"syntology":null},{"paper":null,"slug":"investigating-implicit-bias-in-large-language","title":"Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs","date":"2024-10-13","arxiv_id":"2410.12864","n_code_links":0,"syntology":null},{"paper":"/paper/joint-mixing-data-augmentation-for-skeleton","slug":"joint-mixing-data-augmentation-for-skeleton","title":"Joint Mixing Data Augmentation for Skeleton-based Action Recognition","date":"2024-10-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-pattern-specific-experts-for-time","slug":"learning-pattern-specific-experts-for-time","title":"Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift","date":"2024-10-13","arxiv_id":"2410.09836","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-rank-for-multiple-retrieval","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","date":"2024-10-13","arxiv_id":"2410.09942","n_code_links":0,"syntology":null},{"paper":"/paper/libeer-a-comprehensive-benchmark-and","slug":"libeer-a-comprehensive-benchmark-and","title":"LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-based Emotion Recognition","date":"2024-10-13","arxiv_id":"2410.09767","n_code_links":2,"syntology":null},{"paper":null,"slug":"m2m-gen-a-multimodal-framework-for-automated","title":"M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models","date":"2024-10-13","arxiv_id":"2410.09928","n_code_links":0,"syntology":null},{"paper":null,"slug":"meta-reinforcement-learning-with-universal","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","date":"2024-10-13","arxiv_id":"2410.09728","n_code_links":0,"syntology":null},{"paper":null,"slug":"online-multi-modal-root-cause-analysis","title":"Online Multi-modal Root Cause Analysis","date":"2024-10-13","arxiv_id":"2410.10021","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-ground-truth-is-not-enough-add","title":"Single Ground Truth Is Not Enough: Add Linguistic Variability to Aspect-based Sentiment Analysis Evaluation","date":"2024-10-13","arxiv_id":"2410.09807","n_code_links":0,"syntology":null},{"paper":"/paper/sta-unet-rethink-the-semantic-redundant-for","slug":"sta-unet-rethink-the-semantic-redundant-for","title":"STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation","date":"2024-10-13","arxiv_id":"2410.11578","n_code_links":1,"syntology":null},{"paper":null,"slug":"textmaster-universal-controllable-text-edit","title":"TextMaster: Universal Controllable Text Edit","date":"2024-10-13","arxiv_id":"2410.09879","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-speech-recognition-with-bert-and","title":"Automatic Speech Recognition with BERT and CTC Transformers: A Review","date":"2024-10-12","arxiv_id":"2410.09456","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-exact-match-semantically-reassessing","title":"Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models","date":"2024-10-12","arxiv_id":"2410.09418","n_code_links":0,"syntology":null},{"paper":null,"slug":"bi-temporal-gaussian-feature-dependency","title":"Bi-temporal Gaussian Feature Dependency Guided Change Detection in Remote Sensing Images","date":"2024-10-12","arxiv_id":"2410.09539","n_code_links":0,"syntology":null},{"paper":null,"slug":"bridging-text-and-image-for-artist-style","title":"Bridging Text and Image for Artist Style Transfer via Contrastive Learning","date":"2024-10-12","arxiv_id":"2410.09566","n_code_links":0,"syntology":null},{"paper":"/paper/collabedit-towards-non-destructive","slug":"collabedit-towards-non-destructive","title":"CollabEdit: Towards Non-destructive Collaborative Knowledge Editing","date":"2024-10-12","arxiv_id":"2410.09508","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":4,"n_instrument":2,"unverified":3,"pointer_only":6,"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) · 3 unverified","official":{"repos":["lins-lab/collabedit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"diabetic-retinopathy-image-classification","title":"Diabetic retinopathy image classification method based on GreenBen data augmentation","date":"2024-10-12","arxiv_id":"2410.09444","n_code_links":0,"syntology":null},{"paper":null,"slug":"eg-spikeformer-eye-gaze-guided-transformer-on","title":"EG-SpikeFormer: Eye-Gaze Guided Transformer on Spiking Neural Networks for Medical Image Analysis","date":"2024-10-12","arxiv_id":"2410.09674","n_code_links":0,"syntology":null},{"paper":null,"slug":"embodiedcity-a-benchmark-platform-for","title":"EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment","date":"2024-10-12","arxiv_id":"2410.09604","n_code_links":0,"syntology":null},{"paper":null,"slug":"emphasis-rendering-for-conversational-text-to","title":"Emphasis Rendering for Conversational Text-to-Speech with Multi-modal Multi-scale Context Modeling","date":"2024-10-12","arxiv_id":"2410.09524","n_code_links":0,"syntology":null},{"paper":null,"slug":"extended-japanese-commonsense-morality","title":"Extended Japanese Commonsense Morality Dataset with Masked Token and Label Enhancement","date":"2024-10-12","arxiv_id":"2410.09564","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-attention-i-o-complexity","title":"Fine-grained Attention I/O Complexity: Comprehensive Analysis for Backward Passes","date":"2024-10-12","arxiv_id":"2410.09397","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpton-generative-pre-trained-transformers","title":"GPTON: Generative Pre-trained Transformers enhanced with Ontology Narration for accurate annotation of biological data","date":"2024-10-12","arxiv_id":"2410.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"hey-ai-can-you-grade-my-essay-automatic-essay","title":"Hey AI Can You Grade My Essay?: Automatic Essay Grading","date":"2024-10-12","arxiv_id":"2410.09319","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-3d-finger-traits-recognition-via","title":"Improving 3D Finger Traits Recognition via Generalizable Neural Rendering","date":"2024-10-12","arxiv_id":"2410.09582","n_code_links":0,"syntology":null},{"paper":null,"slug":"llinstruct-an-instruction-tuned-model-for","title":"\\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments","date":"2024-10-12","arxiv_id":"2410.09314","n_code_links":0,"syntology":null},{"paper":null,"slug":"looped-relu-mlps-may-be-all-you-need-as","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","date":"2024-10-12","arxiv_id":"2410.09375","n_code_links":0,"syntology":null},{"paper":null,"slug":"power-softmax-towards-secure-llm-inference","title":"Power-Softmax: Towards Secure LLM Inference over Encrypted Data","date":"2024-10-12","arxiv_id":"2410.09457","n_code_links":0,"syntology":null},{"paper":"/paper/relu-s-revival-on-the-entropic-overload-in","slug":"relu-s-revival-on-the-entropic-overload-in","title":"ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models","date":"2024-10-12","arxiv_id":"2410.09637","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":["nandan91/relu-revival-normfree"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"scaled-and-inter-token-relation-enhanced","title":"Scaled and Inter-token Relation Enhanced Transformer for Sample-restricted Residential NILM","date":"2024-10-12","arxiv_id":"2410.12861","n_code_links":0,"syntology":null},{"paper":null,"slug":"simbrainnet-evaluating-brain-network","title":"SimBrainNet: Evaluating Brain Network Similarity for Attention Disorders","date":"2024-10-12","arxiv_id":"2410.09422","n_code_links":0,"syntology":null},{"paper":null,"slug":"token-pruning-using-a-lightweight-background","title":"Token Pruning using a Lightweight Background Aware Vision Transformer","date":"2024-10-12","arxiv_id":"2410.09324","n_code_links":0,"syntology":null},{"paper":"/paper/toward-general-instruction-following","slug":"toward-general-instruction-following","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","date":"2024-10-12","arxiv_id":"2410.09584","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":9,"phrase":"7 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; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["dongguanting/FollowRAG"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"training-dynamics-of-transformers-to","title":"Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis","date":"2024-10-12","arxiv_id":"2410.09605","n_code_links":0,"syntology":null},{"paper":null,"slug":"unraveling-movie-genres-through-cross","title":"Unraveling Movie Genres through Cross-Attention Fusion of Bi-Modal Synergy of Poster","date":"2024-10-12","arxiv_id":"2410.19764","n_code_links":0,"syntology":null},{"paper":null,"slug":"2410-08508","title":"Accelerated Distributed Stochastic Non-Convex Optimization over Time-Varying Directed Networks","date":"2024-10-11","arxiv_id":"2410.08508","n_code_links":0,"syntology":null},{"paper":"/paper/a-methodology-for-evaluating-rag-systems-a","slug":"a-methodology-for-evaluating-rag-systems-a","title":"A Methodology for Evaluating RAG Systems: A Case Study On Configuration Dependency Validation","date":"2024-10-11","arxiv_id":"2410.08801","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-social-context-aware-graph-based-multimodal","title":"A Social Context-aware Graph-based Multimodal Attentive Learning Framework for Disaster Content Classification during Emergencies","date":"2024-10-11","arxiv_id":"2410.08814","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-constraint-integration-for","slug":"adaptive-constraint-integration-for","title":"Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets","date":"2024-10-11","arxiv_id":"2410.08562","n_code_links":1,"syntology":null},{"paper":"/paper/attngcg-enhancing-jailbreaking-attacks-on","slug":"attngcg-enhancing-jailbreaking-attacks-on","title":"AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation","date":"2024-10-11","arxiv_id":"2410.09040","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-design-and","title":"Convolutional Neural Network Design and Evaluation for Real-Time Multivariate Time Series Fault Detection in Spacecraft Attitude Sensors","date":"2024-10-11","arxiv_id":"2410.09126","n_code_links":0,"syntology":null},{"paper":null,"slug":"cotconet-an-optimized-coupled-transformer","title":"CoTCoNet: An Optimized Coupled Transformer-Convolutional Network with an Adaptive Graph Reconstruction for Leukemia Detection","date":"2024-10-11","arxiv_id":"2410.08797","n_code_links":0,"syntology":null},{"paper":"/paper/cross-modal-bidirectional-interaction-model","slug":"cross-modal-bidirectional-interaction-model","title":"Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation","date":"2024-10-11","arxiv_id":"2410.08613","n_code_links":1,"syntology":null},{"paper":"/paper/dat-dialogue-aware-transformer-with-modality","slug":"dat-dialogue-aware-transformer-with-modality","title":"DAT: Dialogue-Aware Transformer with Modality-Group Fusion for Human Engagement Estimation","date":"2024-10-11","arxiv_id":"2410.08470","n_code_links":1,"syntology":null},{"paper":"/paper/debiformer-vision-transformer-with-deformable","slug":"debiformer-vision-transformer-with-deformable","title":"DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention","date":"2024-10-11","arxiv_id":"2410.08582","n_code_links":1,"syntology":null},{"paper":"/paper/developing-a-pragmatic-benchmark-for","slug":"developing-a-pragmatic-benchmark-for","title":"Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models","date":"2024-10-11","arxiv_id":"2410.08731","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficiently-scanning-and-resampling-spatio","title":"Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations","date":"2024-10-11","arxiv_id":"2410.08681","n_code_links":0,"syntology":null},{"paper":null,"slug":"encoding-agent-trajectories-as","title":"Encoding Agent Trajectories as Representations with Sequence Transformers","date":"2024-10-11","arxiv_id":"2410.09204","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-long-context-performance-in-llms","title":"Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism","date":"2024-10-11","arxiv_id":"2410.12859","n_code_links":0,"syntology":null},{"paper":null,"slug":"extra-global-attention-designation-using","title":"Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures","date":"2024-10-11","arxiv_id":"2410.08971","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-in-house-large-language-models-to","title":"Fine-Tuning In-House Large Language Models to Infer Differential Diagnosis from Radiology Reports","date":"2024-10-11","arxiv_id":"2410.09234","n_code_links":0,"syntology":null},{"paper":null,"slug":"horgait-advancing-gait-recognition-with","title":"HorGait: A Hybrid Model for Accurate Gait Recognition in LiDAR Point Cloud Planar Projections","date":"2024-10-11","arxiv_id":"2410.08454","n_code_links":0,"syntology":null},{"paper":null,"slug":"humanity-in-ai-detecting-the-personality-of","title":"Humanity in AI: Detecting the Personality of Large Language Models","date":"2024-10-11","arxiv_id":"2410.08545","n_code_links":0,"syntology":null},{"paper":null,"slug":"hypothesis-only-biases-in-large-language","title":"Hypothesis-only Biases in Large Language Model-Elicited Natural Language Inference","date":"2024-10-11","arxiv_id":"2410.08996","n_code_links":0,"syntology":null},{"paper":"/paper/jailjudge-a-comprehensive-jailbreak-judge","slug":"jailjudge-a-comprehensive-jailbreak-judge","title":"JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework","date":"2024-10-11","arxiv_id":"2410.12855","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/l3cube-mahasum-a-comprehensive-dataset-and","slug":"l3cube-mahasum-a-comprehensive-dataset-and","title":"L3Cube-MahaSum: A Comprehensive Dataset and BART Models for Abstractive Text Summarization in Marathi","date":"2024-10-11","arxiv_id":"2410.09184","n_code_links":1,"syntology":null},{"paper":null,"slug":"large-language-models-for-medical-osce","title":"Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis","date":"2024-10-11","arxiv_id":"2410.12858","n_code_links":0,"syntology":null},{"paper":"/paper/learning-general-representation-of-12-lead","slug":"learning-general-representation-of-12-lead","title":"Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture","date":"2024-10-11","arxiv_id":"2410.08559","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sehunfromdaegu/ecg_jepa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/learning-interaction-aware-3d-gaussian","slug":"learning-interaction-aware-3d-gaussian","title":"Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars","date":"2024-10-11","arxiv_id":"2410.08840","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["xuanhuang0/guassianhand"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"long-range-named-entity-recognition-for","title":"Long Range Named Entity Recognition for Marathi Documents","date":"2024-10-11","arxiv_id":"2410.09192","n_code_links":0,"syntology":null},{"paper":"/paper/low-complexity-attention-based-unsupervised","slug":"low-complexity-attention-based-unsupervised","title":"Low-complexity Attention-based Unsupervised Anomalous Sound Detection exploiting Separable Convolutions and Angular Loss","date":"2024-10-11","arxiv_id":"2410.08919","n_code_links":1,"syntology":null},{"paper":null,"slug":"maximizing-the-potential-of-synthetic-data","title":"Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory","date":"2024-10-11","arxiv_id":"2410.08942","n_code_links":0,"syntology":null}],"record_sha256":"3c94621e7c47c599d4ca515754d4964acd4c2530277c08cee48d73abc319fef8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}