FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
hub
Attention is all you need
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DBR-AF decouples cross-variable correlations in reconstruction and applies autoregressive flows to model residual densities for improved anomaly detection in multivariate time series.
Nepco offloads network foundation models to SmartNICs using localized byte-sequence modeling and a pattern-aware convolutional architecture to achieve competitive macro F1 scores with 328x lower end-to-end latency than prior foundation models.
AutoPV applies neural architecture search with a custom search space drawn from time series forecasting and photovoltaic models to automatically produce architectures that outperform predefined state-of-the-art models on a Chinese solar station dataset.
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
An attention-based DRL agent with Transformer encoder and GNN learns heuristics for qubit-to-core allocation in multi-core quantum systems to minimize state transfers and online compilation time.
Diff-PCR uses a diffusion model to learn denoising directions for refining doubly stochastic correspondence matrices, improving point cloud registration over one-shot normalization methods.
netFound is a pretrained network foundation model using protocol-aware tokenization, context embedding, hierarchical attention, and privacy design that reaches F1 0.95 on exogenous context discrimination versus under 0.62 for prior models.
TRACE improves project-wise subsequent code editing by interleaving neural-based induction for semantic edits and tool-based deduction for syntactic edits.
SMFD-UNet deblurs faces by generating semantic component masks from blurry inputs and fusing them via multi-stage UNet with residual dense blocks and attention, reporting higher PSNR and SSIM on CelebA than prior models.
RouteFormer is a transformer-RL hybrid for single-agent graph routing that reports 10% and 7% shorter distances than Concorde and LKH-3 on mission-like graphs by incorporating constraints the solvers ignore.
A centralized HRL planner with HTAN, multi-stage curricula, and counterfactual baseline scales multi-robot task planning to 200 robots and 1000 racks on unlearned maps in RMFS.
Flemme is a modular platform separating encoders (conv/transformer/SSM) from encoder-decoder architectures for medical images, with a hierarchical pyramid loss yielding reported average gains of 5.6% Dice and 5.57% PSNR.
A knowledge-transfer network reconstructs missing audio features and uses cross-modality attention to improve multimodal sentiment analysis, showing gains over baselines on three datasets.
PePNet combines an adaptive periodicity detector with an Achilles' Heel loss to raise heavy-workload prediction accuracy by 21% on real cloud traces.
LSTAN-GERPE uses spatio-temporal attention, graph embedding, and grid-searched rotational position encoding to achieve advanced accuracy on PeMS04 and PeMS08 traffic forecasting datasets without heavy feature engineering.
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.
citing papers explorer
-
Toward Generalizable Forgery Detection and Reasoning
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
-
Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation
DBR-AF decouples cross-variable correlations in reconstruction and applies autoregressive flows to model residual densities for improved anomaly detection in multivariate time series.
-
Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC
Nepco offloads network foundation models to SmartNICs using localized byte-sequence modeling and a pattern-aware convolutional architecture to achieve competitive macro F1 scores with 328x lower end-to-end latency than prior foundation models.
-
AutoPV: Automatically Design Your Photovoltaic Power Forecasting Model
AutoPV applies neural architecture search with a custom search space drawn from time series forecasting and photovoltaic models to automatically produce architectures that outperform predefined state-of-the-art models on a Chinese solar station dataset.
-
Robust Adaptation of Foundation Models with Black-Box Visual Prompting
BlackVIP adapts foundation models via a Coordinator for input-dependent visual prompts and SPSA-GC for gradient estimation, enabling robust transfer on 19 datasets with low memory use and a link to randomized smoothing robustness.
-
Attention-Based Deep Reinforcement Learning for Qubit Allocation in Modular Quantum Architectures
An attention-based DRL agent with Transformer encoder and GNN learns heuristics for qubit-to-core allocation in multi-core quantum systems to minimize state transfers and online compilation time.
-
Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration
Diff-PCR uses a diffusion model to learn denoising directions for refining doubly stochastic correspondence matrices, improving point cloud registration over one-shot normalization methods.
-
netFound: Principled Design for Network Foundation Models
netFound is a pretrained network foundation model using protocol-aware tokenization, context embedding, hierarchical attention, and privacy design that reaches F1 0.95 on exogenous context discrimination versus under 0.62 for prior models.
-
Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction
TRACE improves project-wise subsequent code editing by interleaving neural-based induction for semantic edits and tool-based deduction for syntactic edits.
-
SMFD-UNet: Semantic Face Mask Is The Only Thing You Need To Deblur Faces
SMFD-UNet deblurs faces by generating semantic component masks from blurry inputs and fusing them via multi-stage UNet with residual dense blocks and attention, reporting higher PSNR and SSIM on CelebA than prior models.
-
RouteFormer: A Transformer-Based Routing Framework for Autonomous Vehicles
RouteFormer is a transformer-RL hybrid for single-agent graph routing that reports 10% and 7% shorter distances than Concorde and LKH-3 on mission-like graphs by incorporating constraints the solvers ignore.
-
Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning
A centralized HRL planner with HTAN, multi-stage curricula, and counterfactual baseline scales multi-robot task planning to 200 robots and 1000 racks on unlearned maps in RMFS.
-
Flemme: A Flexible and Modular Learning Platform for Medical Images
Flemme is a modular platform separating encoders (conv/transformer/SSM) from encoder-decoder architectures for medical images, with a hierarchical pyramid loss yielding reported average gains of 5.6% Dice and 5.57% PSNR.
-
Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach
A knowledge-transfer network reconstructs missing audio features and uses cross-modality attention to improve multimodal sentiment analysis, showing gains over baselines on three datasets.
-
A Heavy-Load-Enhanced and Changeable-Periodicity-Perceived Workload Prediction Network
PePNet combines an adaptive periodicity detector with an Achilles' Heel loss to raise heavy-workload prediction accuracy by 21% on real cloud traces.
-
Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
LSTAN-GERPE uses spatio-temporal attention, graph embedding, and grid-searched rotational position encoding to achieve advanced accuracy on PeMS04 and PeMS08 traffic forecasting datasets without heavy feature engineering.
-
A Survey on Efficient Inference for Large Language Models
The paper surveys techniques to speed up and reduce the resource needs of LLM inference, organized by data-level, model-level, and system-level changes, with comparative experiments on representative methods.
-
NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.