{"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/position-wise-feed-forward-layer/papers/14","list_of":"/method/position-wise-feed-forward-layer","method":"Position-Wise Feed-Forward Layer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":14,"pages_in_order":139,"rows_per_page":100,"rows":[1301,1400],"of":13895,"counts":{"archive_papers_tagged":13895,"with_a_code_link":6514,"where_syntology_ran_a_sample":2229,"not_listed_spam_title":0,"listed":13895,"listed_where_code_ran":2229,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1902,"every_run_a_failure_of_syntologys_instrument":327,"listed_with_a_run_with_no_instrument_failure":1902,"listed_every_run_a_failure_of_syntologys_instrument":327,"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/position-wise-feed-forward-layer","prev":"/method/position-wise-feed-forward-layer/papers/13","next":"/method/position-wise-feed-forward-layer/papers/15","papers":[{"paper":null,"slug":"longvitu-instruction-tuning-for-long-form","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","date":"2025-01-09","arxiv_id":"2501.05037","n_code_links":0,"syntology":null},{"paper":null,"slug":"openai-chatgpt-interprets-radiological-images","title":"OpenAI ChatGPT interprets Radiological Images: GPT-4 as a Medical Doctor for a Fast Check-Up","date":"2025-01-09","arxiv_id":"2501.06269","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-multitask-industrial-processes","title":"Optimizing Multitask Industrial Processes with Predictive Action Guidance","date":"2025-01-09","arxiv_id":"2501.05108","n_code_links":0,"syntology":null},{"paper":"/paper/spectf-transformers-enable-data-driven","slug":"spectf-transformers-enable-data-driven","title":"SpecTf: Transformers Enable Data-Driven Imaging Spectroscopy Cloud Detection","date":"2025-01-09","arxiv_id":"2501.04916","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-dynamics-of-meaning-through-time","title":"The dynamics of meaning through time: Assessment of Large Language Models","date":"2025-01-09","arxiv_id":"2501.05552","n_code_links":0,"syntology":null},{"paper":null,"slug":"circuit-complexity-bounds-for-visual","title":"Circuit Complexity Bounds for Visual Autoregressive Model","date":"2025-01-08","arxiv_id":"2501.04299","n_code_links":0,"syntology":null},{"paper":"/paper/mb-taylorformer-v2-improved-multi-branch","slug":"mb-taylorformer-v2-improved-multi-branch","title":"MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration","date":"2025-01-08","arxiv_id":"2501.04486","n_code_links":2,"syntology":null},{"paper":null,"slug":"auxdepthnet-real-time-monocular-3d-object","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","date":"2025-01-07","arxiv_id":"2501.03700","n_code_links":0,"syntology":null},{"paper":null,"slug":"cfformer-cross-cnn-transformer-channel","title":"CFFormer: Cross CNN-Transformer Channel Attention and Spatial Feature Fusion for Improved Segmentation of Low Quality Medical Images","date":"2025-01-07","arxiv_id":"2501.03629","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-accurate-tuberculosis-diagnosis","title":"Efficient and Accurate Tuberculosis Diagnosis: Attention Residual U-Net and Vision Transformer Based Detection Framework","date":"2025-01-07","arxiv_id":"2501.03538","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-and-planning-in-robotic-navigation-a","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","date":"2025-01-07","arxiv_id":"2501.05478","n_code_links":0,"syntology":null},{"paper":"/paper/lm-net-a-light-weight-and-multi-scale-network","slug":"lm-net-a-light-weight-and-multi-scale-network","title":"LM-Net: A Light-weight and Multi-scale Network for Medical Image Segmentation","date":"2025-01-07","arxiv_id":"2501.03838","n_code_links":1,"syntology":null},{"paper":null,"slug":"snr-eq-jscc-joint-source-channel-coding-with","title":"SNR-EQ-JSCC: Joint Source-Channel Coding with SNR-Based Embedding and Query","date":"2025-01-07","arxiv_id":"2501.04732","n_code_links":0,"syntology":null},{"paper":null,"slug":"three-dimensional-attention-transformer-for","title":"Three-dimensional attention Transformer for state evaluation in real-time strategy games","date":"2025-01-07","arxiv_id":"2501.03832","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-vision-transformer-for-camera-lidar","title":"A Novel Vision Transformer for Camera-LiDAR Fusion based Traffic Object Segmentation","date":"2025-01-06","arxiv_id":"2501.02858","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-pruning-of-pretrained-transformer","title":"Adaptive Pruning of Pretrained Transformer via Differential Inclusions","date":"2025-01-06","arxiv_id":"2501.03289","n_code_links":0,"syntology":null},{"paper":null,"slug":"chat-beyond-contrastive-graph-transformer-for","title":"CHAT: Beyond Contrastive Graph Transformer for Link Prediction in Heterogeneous Networks","date":"2025-01-06","arxiv_id":"2501.02760","n_code_links":0,"syntology":null},{"paper":null,"slug":"developing-an-artificial-intelligence-tool","title":"Developing an Artificial Intelligence Tool for Personalized Breast Cancer Treatment Plans based on the NCCN Guidelines","date":"2025-01-06","arxiv_id":"2502.15698","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-robot-route-optimization-in-smart","title":"Intelligent logistics management robot path planning algorithm integrating transformer and GCN network","date":"2025-01-06","arxiv_id":"2501.02749","n_code_links":0,"syntology":null},{"paper":"/paper/glog-csunet-enhancing-vision-transformers","slug":"glog-csunet-enhancing-vision-transformers","title":"GLoG-CSUnet: Enhancing Vision Transformers with Adaptable Radiomic Features for Medical Image Segmentation","date":"2025-01-06","arxiv_id":"2501.02788","n_code_links":1,"syntology":null},{"paper":null,"slug":"integrating-language-image-prior-into-eeg","title":"Integrating Language-Image Prior into EEG Decoding for Cross-Task Zero-Calibration RSVP-BCI","date":"2025-01-06","arxiv_id":"2501.02841","n_code_links":0,"syntology":null},{"paper":"/paper/mixture-of-experts-graph-transformers-for","slug":"mixture-of-experts-graph-transformers-for","title":"Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection","date":"2025-01-06","arxiv_id":"2501.03432","n_code_links":1,"syntology":null},{"paper":"/paper/salt-sales-autocompletion-linked-business","slug":"salt-sales-autocompletion-linked-business","title":"SALT: Sales Autocompletion Linked Business Tables Dataset","date":"2025-01-06","arxiv_id":"2501.03413","n_code_links":1,"syntology":null},{"paper":null,"slug":"sensorformer-cross-patch-attention-with","title":"Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting","date":"2025-01-06","arxiv_id":"2501.03284","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-complementor-complementing","title":"Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences","date":"2025-01-06","arxiv_id":"2501.02735","n_code_links":0,"syntology":null},{"paper":null,"slug":"vicsim-enhancing-victim-simulation-with","title":"VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelity","date":"2025-01-06","arxiv_id":"2501.03139","n_code_links":0,"syntology":null},{"paper":null,"slug":"detrack-in-model-latent-denoising-learning","title":"DeTrack: In-model Latent Denoising Learning for Visual Object Tracking","date":"2025-01-05","arxiv_id":"2501.02467","n_code_links":0,"syntology":null},{"paper":null,"slug":"empowering-bengali-education-with-ai-solving","title":"Empowering Bengali Education with AI: Solving Bengali Math Word Problems through Transformer Models","date":"2025-01-05","arxiv_id":"2501.02599","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-large-language-models-against","title":"Evaluating Large Language Models Against Human Annotators in Latent Content Analysis: Sentiment, Political Leaning, Emotional Intensity, and Sarcasm","date":"2025-01-05","arxiv_id":"2501.02532","n_code_links":0,"syntology":null},{"paper":null,"slug":"gs-dit-advancing-video-generation-with-pseudo","title":"GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking","date":"2025-01-05","arxiv_id":"2501.02690","n_code_links":0,"syntology":null},{"paper":null,"slug":"honkaichat-companions-from-anime-that-feel","title":"HonkaiChat: Companions from Anime that feel alive!","date":"2025-01-05","arxiv_id":"2501.03277","n_code_links":0,"syntology":null},{"paper":null,"slug":"lwfnet-coherent-doppler-wind-lidar-based","title":"LWFNet: Coherent Doppler Wind Lidar-Based Network for Wind Field Retrieval","date":"2025-01-05","arxiv_id":"2501.02613","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-new-benchmark-for-ai-alignment","title":"Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI","date":"2025-01-05","arxiv_id":"2501.02531","n_code_links":0,"syntology":null},{"paper":null,"slug":"examining-the-robustness-of-homogeneity-bias","title":"Examining the Robustness of Homogeneity Bias to Hyperparameter Adjustments in GPT-4","date":"2025-01-04","arxiv_id":"2501.02211","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-capabilities-and-limitations-of-1","title":"Exploring the Capabilities and Limitations of Large Language Models for Radiation Oncology Decision Support","date":"2025-01-04","arxiv_id":"2501.02346","n_code_links":0,"syntology":null},{"paper":"/paper/graph-aware-isomorphic-attention-for-adaptive","slug":"graph-aware-isomorphic-attention-for-adaptive","title":"Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers","date":"2025-01-04","arxiv_id":"2501.02393","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-application-of-large-language-models-in","title":"The Application of Large Language Models in Recommendation Systems","date":"2025-01-04","arxiv_id":"2501.02178","n_code_links":0,"syntology":null},{"paper":"/paper/a-separable-self-attention-inspired-by-the","slug":"a-separable-self-attention-inspired-by-the","title":"A Separable Self-attention Inspired by the State Space Model for Computer Vision","date":"2025-01-03","arxiv_id":"2501.02040","n_code_links":1,"syntology":null},{"paper":null,"slug":"classifier-guided-captioning-across","title":"Classifier-Guided Captioning Across Modalities","date":"2025-01-03","arxiv_id":"2501.03183","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-legal-aid-understanding-legal-needs","title":"LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries","date":"2025-01-03","arxiv_id":"2501.01711","n_code_links":0,"syntology":null},{"paper":"/paper/mirage-exploring-how-large-language-models","slug":"mirage-exploring-how-large-language-models","title":"MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments","date":"2025-01-03","arxiv_id":"2501.01652","n_code_links":1,"syntology":null},{"paper":"/paper/quantitative-gait-analysis-from-single-rgb","slug":"quantitative-gait-analysis-from-single-rgb","title":"Quantitative Gait Analysis from Single RGB Videos Using a Dual-Input Transformer-Based Network","date":"2025-01-03","arxiv_id":"2501.01689","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-hard-and-soft-shadow-removal-via-dual","title":"Towards Hard and Soft Shadow Removal via Dual-Branch Separation Network and Vision Transformer","date":"2025-01-03","arxiv_id":"2501.01864","n_code_links":0,"syntology":null},{"paper":"/paper/turning-logic-against-itself-probing-model","slug":"turning-logic-against-itself-probing-model","title":"Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions","date":"2025-01-03","arxiv_id":"2501.01872","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ukplab/poate-attack"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"paper":null,"slug":"vidformer-a-novel-end-to-end-framework-fused","title":"VidFormer: A novel end-to-end framework fused by 3DCNN and Transformer for Video-based Remote Physiological Measurement","date":"2025-01-03","arxiv_id":"2501.01691","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-llava-towards-generalist-3d-lmms-with-omni","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","date":"2025-01-02","arxiv_id":"2501.01163","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-attention-mechanism-for","title":"An Efficient Attention Mechanism for Sequential Recommendation Tasks: HydraRec","date":"2025-01-02","arxiv_id":"2501.01242","n_code_links":0,"syntology":null},{"paper":null,"slug":"disambiguation-of-chinese-polyphones-in-an","title":"Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-trained BERT","date":"2025-01-02","arxiv_id":"2501.01102","n_code_links":0,"syntology":null},{"paper":null,"slug":"ehctnet-enhanced-hybrid-of-cnn-and","title":"EHCTNet: Enhanced Hybrid of CNN and Transformer Network for Remote Sensing Image Change Detection","date":"2025-01-02","arxiv_id":"2501.01238","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-generative-pre-trained-transformer","title":"Graph Generative Pre-trained Transformer","date":"2025-01-02","arxiv_id":"2501.01073","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-spectral-methods-by-transformers","title":"Learning Spectral Methods by Transformers","date":"2025-01-02","arxiv_id":"2501.01312","n_code_links":0,"syntology":null},{"paper":"/paper/long-range-brain-graph-transformer","slug":"long-range-brain-graph-transformer","title":"Long-range Brain Graph Transformer","date":"2025-01-02","arxiv_id":"2501.01100","n_code_links":1,"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":{"repos":["yushuowiki/alter"],"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":"/paper/missing-data-as-augmentation-in-the-earth","slug":"missing-data-as-augmentation-in-the-earth","title":"Missing Data as Augmentation in the Earth Observation Domain: A Multi-View Learning Approach","date":"2025-01-02","arxiv_id":"2501.01132","n_code_links":1,"syntology":null},{"paper":null,"slug":"mswa-refining-local-attention-with-multi","title":"MSWA: Refining Local Attention with Multi-ScaleWindow Attention","date":"2025-01-02","arxiv_id":"2501.01039","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-head-explainer-a-general-framework-to","title":"Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers","date":"2025-01-02","arxiv_id":"2501.01311","n_code_links":0,"syntology":null},{"paper":null,"slug":"nny-net-swin-next-with-cross-attention-for-3d","title":"nnY-Net: Swin-NeXt with Cross-Attention for 3D Medical Images Segmentation","date":"2025-01-02","arxiv_id":"2501.01406","n_code_links":0,"syntology":null},{"paper":null,"slug":"operator-learning-for-reconstructing-flow","title":"Operator Learning for Reconstructing Flow Fields from Sparse Measurements: an Energy Transformer Approach","date":"2025-01-02","arxiv_id":"2501.08339","n_code_links":0,"syntology":null},{"paper":"/paper/reconstruction-vs-generation-taming-1","slug":"reconstruction-vs-generation-taming-1","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","date":"2025-01-02","arxiv_id":"2501.01423","n_code_links":2,"syntology":null},{"paper":"/paper/tart-token-based-architecture-transformer-for","slug":"tart-token-based-architecture-transformer-for","title":"TART: Token-based Architecture Transformer for Neural Network Performance Prediction","date":"2025-01-02","arxiv_id":"2501.02007","n_code_links":1,"syntology":null},{"paper":null,"slug":"toward-inclusive-educational-ai-auditing","title":"Toward Inclusive Educational AI: Auditing Frontier LLMs through a Multiplexity Lens","date":"2025-01-02","arxiv_id":"2501.03259","n_code_links":0,"syntology":null},{"paper":null,"slug":"3d-mvp-3d-multiview-pretraining-for","title":"3D-MVP: 3D Multiview Pretraining for Manipulation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-polarization-aided-transformer-for-image","slug":"a-polarization-aided-transformer-for-image","title":"A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/a-universal-scale-adaptive-deformable","slug":"a-universal-scale-adaptive-deformable","title":"A Universal Scale-Adaptive Deformable Transformer for Image Restoration across Diverse Artifacts","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/abc-former-auxiliary-bimodal-cross-domain","slug":"abc-former-auxiliary-bimodal-cross-domain","title":"ABC-Former: Auxiliary Bimodal Cross-domain Transformer with Interactive Channel Attention for White Balance","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"activating-sparse-part-concepts-for-3d-class","title":"Activating Sparse Part Concepts for 3D Class Incremental Learning","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"animate-and-sound-an-image","title":"Animate and Sound an Image","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"boe-vit-boosting-orientation-estimation-with","title":"BOE-ViT: Boosting Orientation Estimation with Equivariance in Self-Supervised 3D Subtomogram Alignment","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-point-supervised-temporal-action","title":"Boosting Point-Supervised Temporal Action Localization through Integrating Query Reformation and Optimal Transport","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"boosting-the-accuracy-of-stock-market","title":"Boosting the Accuracy of Stock Market Prediction via Multi-Layer Hybrid MTL Structure","date":"2025-01-01","arxiv_id":"2501.09760","n_code_links":0,"syntology":null},{"paper":"/paper/column-property-annotation-using-large","slug":"column-property-annotation-using-large","title":"Column Property Annotation using Large Language Models","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"correlative-and-discriminative-label-grouping","title":"Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"d-2it-dynamic-diffusion-transformer-for","title":"D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"decoupling-knowledge-and-reasoning-in","title":"Decoupling Knowledge and Reasoning in Transformers: A Modular Architecture with Generalized Cross-Attention","date":"2025-01-01","arxiv_id":"2501.00823","n_code_links":0,"syntology":null},{"paper":null,"slug":"disentangled-pose-and-appearance-guidance-for","title":"Disentangled Pose and Appearance Guidance for Multi-Pose Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"drivescape-high-resolution-driving-video","title":"DriveScape: High-Resolution Driving Video Generation by Multi-View Feature Fusion","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/dropex-disaster-rescue-operations-and-probing","slug":"dropex-disaster-rescue-operations-and-probing","title":"DROPEX: Disaster Rescue Operations and Probing using EXpert drones","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-focus-attention-transformer-for-robust","title":"Dual Focus-Attention Transformer for Robust Point Cloud Registration","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-diversity-for-data-free","title":"Enhancing Diversity for Data-free Quantization","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/faster-focal-token-acquiring-and-scaling-1","slug":"faster-focal-token-acquiring-and-scaling-1","title":"FASTer: Focal token Acquiring-and-Scaling Transformer for Long-term 3D Objection Detection","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"gs-dit-advancing-video-generation-with","title":"GS-DiT: Advancing Video Generation with Dynamic 3D Gaussian Fields through Efficient Dense 3D Point Tracking","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hazy-low-quality-satellite-video-restoration","title":"Hazy Low-Quality Satellite Video Restoration Via Learning Optimal Joint Degradation Patterns and Continuous-Scale Super-Resolution Reconstruction","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/hunet-homotopy-unfolding-network-for-image","slug":"hunet-homotopy-unfolding-network-for-image","title":"HUNet: Homotopy Unfolding Network for Image Compressive Sensing","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"less-attention-is-more-prompt-transformer-for","title":"Less Attention is More: Prompt Transformer for Generalized Category Discovery","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"mask-2dit-dual-mask-based-diffusion","title":"Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-large-models-are-effective-action","slug":"multimodal-large-models-are-effective-action","title":"Multimodal Large Models Are Effective Action Anticipators","date":"2025-01-01","arxiv_id":"2501.00795","n_code_links":1,"syntology":null},{"paper":null,"slug":"multiscaled-multi-head-attention-based-video","title":"Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition","date":"2025-01-01","arxiv_id":"2501.00935","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-barrier-event-triggered-pde","title":"Performance-Barrier Event-Triggered PDE Control of Traffic Flow","date":"2025-01-01","arxiv_id":"2501.00722","n_code_links":0,"syntology":null},{"paper":null,"slug":"prompthash-affinity-prompted-collaborative-1","title":"PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"r2c-mapping-room-to-chessboard-to-unlock-llm","title":"R2C: Mapping Room to Chessboard to Unlock LLM As Low-Level Action Planner","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-spiking-self-attention-mechanism","title":"Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"revisiting-audio-visual-segmentation-with","title":"Revisiting Audio-Visual Segmentation with Vision-Centric Transformer","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-multimodal-survival-prediction-with-1","title":"Robust Multimodal Survival Prediction with Conditional Latent Differentiation Variational AutoEncoder","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"separation-of-powers-on-segregating-knowledge","title":"Separation of Powers: On Segregating Knowledge from Observation in LLM-enabled Knowledge-based Visual Question Answering","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"spatial-temporal-attention-based-target","title":"Spatial Temporal Attention based Target Vehicle Trajectory Prediction for Internet of Vehicles","date":"2025-01-01","arxiv_id":"2501.00890","n_code_links":0,"syntology":null},{"paper":null,"slug":"spiking-transformer-introducing-accurate-1","title":"Spiking Transformer: Introducing Accurate Addition-Only Spiking Self-Attention for Transformer","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"task-aware-cross-modal-feature-refinement","title":"Task-aware Cross-modal Feature Refinement Transformer with Large Language Models for Visual Grounding","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"texgarment-consistent-garment-uv-texture","title":"TexGarment: Consistent Garment UV Texture Generation via Efficient 3D Structure-Guided Diffusion Transformer","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/volformer-explore-more-comprehensive-cube","slug":"volformer-explore-more-comprehensive-cube","title":"VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/wavelet-and-prototype-augmented-query-based","slug":"wavelet-and-prototype-augmented-query-based","title":"Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection","date":"2025-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"yo-chameleon-personalized-vision-and-language","title":"Yo'Chameleon: Personalized Vision and Language Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"f26f4290eb26171b90bd62b37d46e8a544a81bafb9e2d4f6025b0700e0d01a76","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}