{"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/76","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":76,"pages_in_order":375,"rows_per_page":100,"rows":[7501,7600],"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/75","next":"/method/softmax/papers/77","papers":[{"paper":null,"slug":"geometric-point-attention-transformer-for-3d","title":"Geometric Point Attention Transformer for 3D Shape Reassembly","date":"2024-11-26","arxiv_id":"2411.17788","n_code_links":0,"syntology":null},{"paper":null,"slug":"give-me-the-code-log-analysis-of-first-year","title":"\"Give me the code\" -- Log Analysis of First-Year CS Students' Interactions With GPT","date":"2024-11-26","arxiv_id":"2411.17855","n_code_links":0,"syntology":null},{"paper":null,"slug":"gmflow-global-motion-guided-recurrent-flow","title":"GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation","date":"2024-11-26","arxiv_id":"2411.17174","n_code_links":0,"syntology":null},{"paper":"/paper/h-3-fusion-helpful-harmless-honest-fusion-of","slug":"h-3-fusion-helpful-harmless-honest-fusion-of","title":"$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs","date":"2024-11-26","arxiv_id":"2411.17792","n_code_links":1,"syntology":null},{"paper":"/paper/k2ssl-a-faster-and-better-framework-for-self","slug":"k2ssl-a-faster-and-better-framework-for-self","title":"k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning","date":"2024-11-26","arxiv_id":"2411.17100","n_code_links":1,"syntology":null},{"paper":"/paper/lampmark-proactive-deepfake-detection-via","slug":"lampmark-proactive-deepfake-detection-via","title":"LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks","date":"2024-11-26","arxiv_id":"2411.17209","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-chemical-reaction-representation","title":"Learning Chemical Reaction Representation with Reactant-Product Alignment","date":"2024-11-26","arxiv_id":"2411.17629","n_code_links":0,"syntology":null},{"paper":"/paper/learning-monotonic-attention-in-transducer","slug":"learning-monotonic-attention-in-transducer","title":"Learning Monotonic Attention in Transducer for Streaming Generation","date":"2024-11-26","arxiv_id":"2411.17170","n_code_links":1,"syntology":null},{"paper":"/paper/leveraging-large-language-models-and-topic","slug":"leveraging-large-language-models-and-topic","title":"Leveraging Large Language Models and Topic Modeling for Toxicity Classification","date":"2024-11-26","arxiv_id":"2411.17876","n_code_links":1,"syntology":null},{"paper":"/paper/litevar-compressing-visual-autoregressive","slug":"litevar-compressing-visual-autoregressive","title":"LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization","date":"2024-11-26","arxiv_id":"2411.17178","n_code_links":1,"syntology":null},{"paper":null,"slug":"made-graph-backdoor-defense-with-masked","title":"MADE: Graph Backdoor Defense with Masked Unlearning","date":"2024-11-26","arxiv_id":"2411.18648","n_code_links":0,"syntology":null},{"paper":"/paper/marvel-40m-multi-level-visual-elaboration-for","slug":"marvel-40m-multi-level-visual-elaboration-for","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","date":"2024-11-26","arxiv_id":"2411.17945","n_code_links":2,"syntology":{"ran":2,"of":6,"n_ran_checked":2,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["SadilKhan/MARVEL-FX3D","huggingface.co/datasets/sankalpsinha77/MARVEL-40M"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mat-multi-range-attention-transformer-for","slug":"mat-multi-range-attention-transformer-for","title":"MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution","date":"2024-11-26","arxiv_id":"2411.17214","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":4,"n_instrument":0,"unverified":3,"pointer_only":3,"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":["stella-von/MAT"],"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":"mixed-state-quantum-denoising-diffusion","title":"Mixed-State Quantum Denoising Diffusion Probabilistic Model","date":"2024-11-26","arxiv_id":"2411.17608","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-outer-arithmetic-block-dual-fusion","title":"Multimodal Outer Arithmetic Block Dual Fusion of Whole Slide Images and Omics Data for Precision Oncology","date":"2024-11-26","arxiv_id":"2411.17418","n_code_links":0,"syntology":null},{"paper":"/paper/mwformer-multi-weather-image-restoration","slug":"mwformer-multi-weather-image-restoration","title":"MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers","date":"2024-11-26","arxiv_id":"2411.17226","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-limitations-of-llm-as-annotator-for-low","title":"On Limitations of LLM as Annotator for Low Resource Languages","date":"2024-11-26","arxiv_id":"2411.17637","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-mind-many-tongues-a-deep-dive-into","title":"One Mind, Many Tongues: A Deep Dive into Language-Agnostic Knowledge Neurons in Large Language Models","date":"2024-11-26","arxiv_id":"2411.17401","n_code_links":0,"syntology":null},{"paper":null,"slug":"osformer-dual-modal-o-like-super-resolution","title":"ΩSFormer: Dual-Modal Ω-like Super-Resolution Transformer Network for Cross-scale and High-accuracy Terraced Field Vectorization Extraction","date":"2024-11-26","arxiv_id":"2411.17088","n_code_links":0,"syntology":null},{"paper":"/paper/pretrained-llm-adapted-with-lora-as-a","slug":"pretrained-llm-adapted-with-lora-as-a","title":"Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative Trading","date":"2024-11-26","arxiv_id":"2411.17900","n_code_links":1,"syntology":null},{"paper":null,"slug":"push-the-limit-of-multi-modal-emotion","title":"Push the Limit of Multi-modal Emotion Recognition by Prompting LLMs with Receptive-Field-Aware Attention Weighting","date":"2024-11-26","arxiv_id":"2411.17674","n_code_links":0,"syntology":null},{"paper":"/paper/satvision-toa-a-geospatial-foundation-model","slug":"satvision-toa-a-geospatial-foundation-model","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","date":"2024-11-26","arxiv_id":"2411.17000","n_code_links":1,"syntology":null},{"paper":null,"slug":"scalable-iterative-pruning-of-large-language","title":"Scalable iterative pruning of large language and vision models using block coordinate descent","date":"2024-11-26","arxiv_id":"2411.17796","n_code_links":0,"syntology":null},{"paper":null,"slug":"scaseg-strip-cross-attention-for-efficient","title":"SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation","date":"2024-11-26","arxiv_id":"2411.17061","n_code_links":0,"syntology":null},{"paper":null,"slug":"softmap-software-hardware-co-design-for","title":"SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors","date":"2024-11-26","arxiv_id":"2411.17847","n_code_links":0,"syntology":null},{"paper":"/paper/star-attention-efficient-llm-inference-over","slug":"star-attention-efficient-llm-inference-over","title":"Star Attention: Efficient LLM Inference over Long Sequences","date":"2024-11-26","arxiv_id":"2411.17116","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":5,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["NVIDIA/Star-Attention"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"structure-guided-mr-to-ct-synthesis-with","title":"Structure-Guided MR-to-CT Synthesis with Spatial and Semantic Alignments for Attenuation Correction of Whole-Body PET/MR Imaging","date":"2024-11-26","arxiv_id":"2411.17488","n_code_links":0,"syntology":null},{"paper":null,"slug":"tafm-net-a-novel-approach-to-skin-lesion","title":"TAFM-Net: A Novel Approach to Skin Lesion Segmentation Using Transformer Attention and Focal Modulation","date":"2024-11-26","arxiv_id":"2411.17556","n_code_links":0,"syntology":null},{"paper":"/paper/ted-viton-transformer-empowered-diffusion","slug":"ted-viton-transformer-empowered-diffusion","title":"TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On","date":"2024-11-26","arxiv_id":"2411.17017","n_code_links":1,"syntology":null},{"paper":"/paper/tinyvim-frequency-decoupling-for-tiny-hybrid","slug":"tinyvim-frequency-decoupling-for-tiny-hybrid","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","date":"2024-11-26","arxiv_id":"2411.17473","n_code_links":1,"syntology":null},{"paper":"/paper/what-differentiates-educational-literature-a","slug":"what-differentiates-educational-literature-a","title":"What Differentiates Educational Literature? A Multimodal Fusion Approach of Transformers and Computational Linguistics","date":"2024-11-26","arxiv_id":"2411.17593","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-s-in-the-image-a-deep-dive-into-the","title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models","date":"2024-11-26","arxiv_id":"2411.17491","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-circuit-behavior-and-generalization","title":"Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability","date":"2024-11-25","arxiv_id":"2411.16105","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-transformers-truly-foundational-for","title":"Are Transformers Truly Foundational for Robotics?","date":"2024-11-25","arxiv_id":"2411.16917","n_code_links":0,"syntology":null},{"paper":"/paper/atomr-atomic-operator-empowered-large","slug":"atomr-atomic-operator-empowered-large","title":"AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning","date":"2024-11-25","arxiv_id":"2411.16495","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":13,"n_instrument":0,"unverified":0,"pointer_only":13,"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) · 0 unverified","official":{"repos":["THU-KEG/AtomR"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/augmenting-multimodal-llms-with-self","slug":"augmenting-multimodal-llms-with-self","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","date":"2024-11-25","arxiv_id":"2411.16863","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":4,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aimagelab/reflectiva"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"boosting-3d-object-generation-through-pbr","title":"Boosting 3D Object Generation through PBR Materials","date":"2024-11-25","arxiv_id":"2411.16080","n_code_links":0,"syntology":null},{"paper":null,"slug":"can-ai-grade-your-essays-a-comparative","title":"Can AI grade your essays? A comparative analysis of large language models and teacher ratings in multidimensional essay scoring","date":"2024-11-25","arxiv_id":"2411.16337","n_code_links":0,"syntology":null},{"paper":null,"slug":"care-transformer-mobile-friendly-linear","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","date":"2024-11-25","arxiv_id":"2411.16170","n_code_links":0,"syntology":null},{"paper":null,"slug":"catp-llm-empowering-large-language-models-for","title":"CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning","date":"2024-11-25","arxiv_id":"2411.16313","n_code_links":0,"syntology":null},{"paper":null,"slug":"cmavit-integrating-climate-managment-and","title":"CMAViT: Integrating Climate, Managment, and Remote Sensing Data for Crop Yield Estimation with Multimodel Vision Transformers","date":"2024-11-25","arxiv_id":"2411.16989","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocono-attention-contrast-and-complete-for","title":"CoCoNO: Attention Contrast-and-Complete for Initial Noise Optimization in Text-to-Image Synthesis","date":"2024-11-25","arxiv_id":"2411.16783","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparative-analysis-of-machine-learning-8","title":"Comparative Analysis of Machine Learning Models for Short-Term Distribution System Load Forecasting","date":"2024-11-25","arxiv_id":"2411.16118","n_code_links":0,"syntology":null},{"paper":"/paper/contrastive-multi-graph-learning-with","slug":"contrastive-multi-graph-learning-with","title":"Contrastive Multi-graph Learning with Neighbor Hierarchical Sifting for Semi-supervised Text Classification","date":"2024-11-25","arxiv_id":"2411.16787","n_code_links":1,"syntology":null},{"paper":"/paper/df-gnn-dynamic-fusion-framework-for-attention","slug":"df-gnn-dynamic-fusion-framework-for-attention","title":"DF-GNN: Dynamic Fusion Framework for Attention Graph Neural Networks on GPUs","date":"2024-11-25","arxiv_id":"2411.16127","n_code_links":1,"syntology":null},{"paper":null,"slug":"dreamrunner-fine-grained-storytelling-video","title":"DreamRunner: Fine-Grained Storytelling Video Generation with Retrieval-Augmented Motion Adaptation","date":"2024-11-25","arxiv_id":"2411.16657","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamic-self-distillation-via-previous-mini","title":"Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models","date":"2024-11-25","arxiv_id":"2411.16991","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-answer-reliability-through-inter","title":"Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models","date":"2024-11-25","arxiv_id":"2411.16797","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-fluorescence-lifetime-parameter","title":"Enhancing Fluorescence Lifetime Parameter Estimation Accuracy with Differential Transformer Based Deep Learning Model Incorporating Pixelwise Instrument Response Function","date":"2024-11-25","arxiv_id":"2411.16896","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-multi-agent-consensus-through-third","title":"Enhancing Multi-Agent Consensus through Third-Party LLM Integration: Analyzing Uncertainty and Mitigating Hallucinations in Large Language Models","date":"2024-11-25","arxiv_id":"2411.16189","n_code_links":0,"syntology":null},{"paper":"/paper/even-sparser-graph-transformers","slug":"even-sparser-graph-transformers","title":"Even Sparser Graph Transformers","date":"2024-11-25","arxiv_id":"2411.16278","n_code_links":1,"syntology":{"ran":7,"of":11,"n_ran_checked":7,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["hamed1375/Sp_Exphormer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"explainable-ai-approach-using-near-misses","title":"Explainable AI Approach using Near Misses Analysis","date":"2024-11-25","arxiv_id":"2411.16895","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-visual-tokenization-and-generation","title":"Factorized Visual Tokenization and Generation","date":"2024-11-25","arxiv_id":"2411.16681","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-tuning-llms-with-noisy-data-for","title":"Fine-Tuning LLMs with Noisy Data for Political Argument Generation and Post Guidance","date":"2024-11-25","arxiv_id":"2411.16813","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-superclasses-for-learning-from","slug":"harnessing-superclasses-for-learning-from","title":"Harnessing Superclasses for Learning from Hierarchical Databases","date":"2024-11-25","arxiv_id":"2411.16438","n_code_links":1,"syntology":null},{"paper":null,"slug":"human-calibrated-automated-testing-and","title":"Human-Calibrated Automated Testing and Validation of Generative Language Models","date":"2024-11-25","arxiv_id":"2411.16391","n_code_links":0,"syntology":null},{"paper":"/paper/image-generation-diversity-issues-and-how-to","slug":"image-generation-diversity-issues-and-how-to","title":"Image Generation Diversity Issues and How to Tame Them","date":"2024-11-25","arxiv_id":"2411.16171","n_code_links":1,"syntology":null},{"paper":"/paper/interpreting-object-level-foundation-models","slug":"interpreting-object-level-foundation-models","title":"Interpreting Object-level Foundation Models via Visual Precision Search","date":"2024-11-25","arxiv_id":"2411.16198","n_code_links":2,"syntology":null},{"paper":null,"slug":"j-capa-joint-channel-and-pyramid-attention","title":"J-CaPA : Joint Channel and Pyramid Attention Improves Medical Image Segmentation","date":"2024-11-25","arxiv_id":"2411.16568","n_code_links":0,"syntology":null},{"paper":"/paper/lab-rag-label-boosted-retrieval-augmented","slug":"lab-rag-label-boosted-retrieval-augmented","title":"LaB-RAG: Label Boosted Retrieval Augmented Generation for Radiology Report Generation","date":"2024-11-25","arxiv_id":"2411.16523","n_code_links":1,"syntology":null},{"paper":null,"slug":"local-and-global-feature-attention-fusion","title":"Local and Global Feature Attention Fusion Network for Face Recognition","date":"2024-11-25","arxiv_id":"2411.16169","n_code_links":0,"syntology":null},{"paper":"/paper/marketgpt-developing-a-pre-trained","slug":"marketgpt-developing-a-pre-trained","title":"MarketGPT: Developing a Pre-trained transformer (GPT) for Modeling Financial Time Series","date":"2024-11-25","arxiv_id":"2411.16585","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["aaron-wheeler/marketgpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"noise-diffusion-for-enhancing-semantic","title":"Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis","date":"2024-11-25","arxiv_id":"2411.16503","n_code_links":0,"syntology":null},{"paper":null,"slug":"normxlogit-the-head-on-top-never-lies","title":"NormXLogit: The Head-on-Top Never Lies","date":"2024-11-25","arxiv_id":"2411.16252","n_code_links":0,"syntology":null},{"paper":null,"slug":"predictive-power-of-llms-in-financial-markets","title":"Predictive Power of LLMs in Financial Markets","date":"2024-11-25","arxiv_id":"2411.16569","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-protection-in-personalized-diffusion","title":"Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack","date":"2024-11-25","arxiv_id":"2411.16437","n_code_links":0,"syntology":null},{"paper":"/paper/ptychoformer-a-physics-guided-deep-learning","slug":"ptychoformer-a-physics-guided-deep-learning","title":"A Physics-Inspired Deep Learning Framework with Polar Coordinate Attention for Ptychographic Imaging","date":"2024-11-25","arxiv_id":"2412.06806","n_code_links":1,"syntology":null},{"paper":null,"slug":"quadratic-gaussian-splatting-for-efficient","title":"Quadratic Gaussian Splatting for Efficient and Detailed Surface Reconstruction","date":"2024-11-25","arxiv_id":"2411.16392","n_code_links":0,"syntology":null},{"paper":"/paper/scaling-spike-driven-transformer-with","slug":"scaling-spike-driven-transformer-with","title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","date":"2024-11-25","arxiv_id":"2411.16061","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["biclab/spike-driven-transformer-v3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semu-net-a-segmentation-based-corrector-for","title":"SEMU-Net: A Segmentation-based Corrector for Fabrication Process Variations of Nanophotonics with Microscopic Images","date":"2024-11-25","arxiv_id":"2411.16973","n_code_links":0,"syntology":null},{"paper":"/paper/soft-transformers-for-continual-learning","slug":"soft-transformers-for-continual-learning","title":"Soft-TransFormers for Continual Learning","date":"2024-11-25","arxiv_id":"2411.16073","n_code_links":1,"syntology":null},{"paper":null,"slug":"solaris-a-foundation-model-of-the-sun","title":"Solaris: A Foundation Model of the Sun","date":"2024-11-25","arxiv_id":"2411.16339","n_code_links":0,"syntology":null},{"paper":null,"slug":"structformer-document-structure-based-masked","title":"StructFormer: Document Structure-based Masked Attention and its Impact on Language Model Pre-Training","date":"2024-11-25","arxiv_id":"2411.16618","n_code_links":0,"syntology":null},{"paper":null,"slug":"swin-fmri-transformer-predicts-early","title":"Swin fMRI Transformer Predicts Early Neurodevelopmental Outcomes from Neonatal fMRI","date":"2024-11-25","arxiv_id":"2412.07783","n_code_links":0,"syntology":null},{"paper":null,"slug":"tree-transformers-are-an-ineffective-model-of","title":"Tree Transformers are an Ineffective Model of Syntactic Constituency","date":"2024-11-25","arxiv_id":"2411.16993","n_code_links":0,"syntology":null},{"paper":"/paper/ultrasam-a-foundation-model-for-ultrasound","slug":"ultrasam-a-foundation-model-for-ultrasound","title":"UltraSam: A Foundation Model for Ultrasound using Large Open-Access Segmentation Datasets","date":"2024-11-25","arxiv_id":"2411.16222","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-the-potential-of-text-to-image","title":"Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory","date":"2024-11-25","arxiv_id":"2411.17472","n_code_links":0,"syntology":null},{"paper":null,"slug":"unraveling-arithmetic-in-large-language","title":"Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures","date":"2024-11-25","arxiv_id":"2411.16260","n_code_links":0,"syntology":null},{"paper":"/paper/vicon-vision-in-context-operator-networks-for","slug":"vicon-vision-in-context-operator-networks-for","title":"VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction","date":"2024-11-25","arxiv_id":"2411.16063","n_code_links":1,"syntology":null},{"paper":null,"slug":"vires-video-instance-repainting-with-sketch","title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation","date":"2024-11-25","arxiv_id":"2411.16199","n_code_links":0,"syntology":null},{"paper":null,"slug":"vq-sgen-a-vector-quantized-stroke","title":"VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation","date":"2024-11-25","arxiv_id":"2411.16446","n_code_links":0,"syntology":null},{"paper":null,"slug":"wtdun-wavelet-tree-structured-sampling-and","title":"WTDUN: Wavelet Tree-Structured Sampling and Deep Unfolding Network for Image Compressed Sensing","date":"2024-11-25","arxiv_id":"2411.16336","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-general-sensing-assisted-channel-estimation","title":"A General Sensing-assisted Channel Estimation Framework in Distributed MIMO Network","date":"2024-11-24","arxiv_id":"2411.15995","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-method-for-building-large-language-models","title":"A Method for Building Large Language Models with Predefined KV Cache Capacity","date":"2024-11-24","arxiv_id":"2411.15785","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-adaptive-gradient-fast-controlled","slug":"beyond-adaptive-gradient-fast-controlled","title":"Beyond adaptive gradient: Fast-Controlled Minibatch Algorithm for large-scale optimization","date":"2024-11-24","arxiv_id":"2411.15795","n_code_links":1,"syntology":null},{"paper":"/paper/development-of-pre-trained-transformer-based","slug":"development-of-pre-trained-transformer-based","title":"Development of Pre-Trained Transformer-based Models for the Nepali Language","date":"2024-11-24","arxiv_id":"2411.15734","n_code_links":0,"syntology":null},{"paper":null,"slug":"fasttracktr-towards-fast-multi-object","title":"FastTrackTr:Towards Fast Multi-Object Tracking with Transformers","date":"2024-11-24","arxiv_id":"2411.15811","n_code_links":0,"syntology":null},{"paper":null,"slug":"fixing-the-perspective-a-critical-examination","title":"Fixing the Perspective: A Critical Examination of Zero-1-to-3","date":"2024-11-24","arxiv_id":"2411.15706","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-norm-regularization-second-order","title":"Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems","date":"2024-11-24","arxiv_id":"2411.15769","n_code_links":0,"syntology":null},{"paper":null,"slug":"investigating-factuality-in-long-form-text","title":"Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown","date":"2024-11-24","arxiv_id":"2411.15993","n_code_links":0,"syntology":null},{"paper":null,"slug":"letstalk-latent-diffusion-transformer-for","title":"LetsTalk: Latent Diffusion Transformer for Talking Video Synthesis","date":"2024-11-24","arxiv_id":"2411.16748","n_code_links":0,"syntology":null},{"paper":"/paper/llama-moe-v2-exploring-sparsity-of-llama-from","slug":"llama-moe-v2-exploring-sparsity-of-llama-from","title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training","date":"2024-11-24","arxiv_id":"2411.15708","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":["opensparsellms/llama-moe-v2"],"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":"ltcf-net-a-transformer-enhanced-dual-channel","title":"LTCF-Net: A Transformer-Enhanced Dual-Channel Fourier Framework for Low-Light Image Restoration","date":"2024-11-24","arxiv_id":"2411.15740","n_code_links":0,"syntology":null},{"paper":"/paper/medical-slice-transformer-improved-diagnosis","slug":"medical-slice-transformer-improved-diagnosis","title":"Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2","date":"2024-11-24","arxiv_id":"2411.15802","n_code_links":1,"syntology":null},{"paper":"/paper/nimbus-secure-and-efficient-two-party","slug":"nimbus-secure-and-efficient-two-party","title":"Nimbus: Secure and Efficient Two-Party Inference for Transformers","date":"2024-11-24","arxiv_id":"2411.15707","n_code_links":1,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"0 ran · 5 unverified","official":{"repos":["secretflow/spu"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":[]}}},{"paper":null,"slug":"pr-mim-delving-deeper-into-partial","title":"PR-MIM: Delving Deeper into Partial Reconstruction in Masked Image Modeling","date":"2024-11-24","arxiv_id":"2411.15746","n_code_links":0,"syntology":null},{"paper":null,"slug":"ramie-retrieval-augmented-multi-task","title":"RAMIE: Retrieval-Augmented Multi-task Information Extraction with Large Language Models on Dietary Supplements","date":"2024-11-24","arxiv_id":"2411.15700","n_code_links":0,"syntology":null},{"paper":"/paper/resclip-residual-attention-for-training-free","slug":"resclip-residual-attention-for-training-free","title":"ResCLIP: Residual Attention for Training-free Dense Vision-language Inference","date":"2024-11-24","arxiv_id":"2411.15851","n_code_links":1,"syntology":null},{"paper":"/paper/self-calibrated-clip-for-training-free-open","slug":"self-calibrated-clip-for-training-free-open","title":"Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation","date":"2024-11-24","arxiv_id":"2411.15869","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sulebai/sc-clip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/test-time-alignment-enhanced-adapter-for","slug":"test-time-alignment-enhanced-adapter-for","title":"Test-time Alignment-Enhanced Adapter for Vision-Language Models","date":"2024-11-24","arxiv_id":"2411.15735","n_code_links":1,"syntology":null}],"record_sha256":"4b2da6283f542c93a4a193d3c736974557944f6f3414d2732dd38a971307013e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}