Feed-Forward

Ask about this topic

Momentum

11 papers in the last four weeks, up 38% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 108

All topics
CardsList

  1. MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs

    Oct 1, 2026Xudong Wang, Hao Wu, Haozhe Hu +5Visual Token PruningLarge Language Model Compression

    EIT-NLP Lab, Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University · The Hong Kong Polytechnic University +1

  2. ARROW: Arbitrary Reconstruction and Tracking of 4D Observations in the Wild

    Oct 1, 2026Ilya Fradlin, Christian Schmidt, Jens Piekenbrinck +33D ReconstructionMulti-Object Tracking

    RWTH Aachen University

  3. Multi-Depth Temporal Fusion for Feedforward, Locally Trained Spiking Neural Networks

    Sep 29, 2026Aidin Attar, Eleonora Cicciarella, Michele RossiSpiking Neural NetworksTime-To-First-Spike

    Department of Information Engineering, University of Padua Padua, Italy

  4. Many Eyes, One World: Feed-Forward 3D Reconstruction from Mixed Cameras

    Sep 28, 2026Qiaoge Li, Yifan Zhan, Haijun Yang +3Feed-Forward 3D ReconstructionCamera

    China Mobile Communications Company Limited Research Institute · The University of Tokyo

  5. Hidden Activations are not Enough I: Knowledge Matrices as Higher Representations

    Sep 28, 2026Marco ArmentaRepresentation SpaceFeed-Forward

    Institut quantique, Université de Sherbrooke

  6. Geometric Inductive Biases for Semi-Supervised Equalization: The Constellation-Aware Transformer

    Sep 27, 2026Avi CaciularuChannel EstimationMultiple-Input Multiple-Output

    Google Research

  7. DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mapping

    Sep 23, 2026Jaafar Mahmoud, Arthur Movsesyan, Mikhail Iumanov +1Simultaneous Localization And MappingOdometry

    Biomechatronics and Energy-Efficient Robotics (BE2R) Lab, ITMO University, Saint Petersburg, Russia.

  8. When Wider Views Fail: Stress-Testing Feed-Forward 3D Reconstruction

    Sep 21, 2026Daisy Li, Kyle Gao, Quanyun Wu +3Feed-Forward 3D ReconstructionSparse-View

    University of Waterloo · Aalto University

  9. Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision Ceiling

    Sep 14, 2026Homayoon Beigi, Grace ConneelyLearning-Based ControlFriction

    Department of Mechanical Engineering, Columbia University, New York, NY, USA · Department of Electrical Engineering, Columbia University, New York, NY, USA · Recognition Technologies, Inc., South Salem, NY, USA

  10. LILA: Calibration-Free Structured Pruning of Large Language Models via Latent Spectral Geometry

    Sep 11, 2026Sankar Behera, Dhruv Singh, Anshika Agnihotri +3Large Language Model CompressionUnstructured Pruning

    CSE, IIT Jammu · Mathematics, IIT Jammu · IT, EC Bikaner +1

  11. FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute

    Sep 8, 2026Hongchi Xia, Tianhang Cheng, Wei-Chiu Ma +1Feed-Forward 3D Reconstruction3D Reconstruction

    University of Illinois Urbana-Champaign · Cornell University

  12. SCoNE: Selective Context-aware Neuron Editing for Robust Retrieval-Augmented Generation

    Sep 1, 2026Chaewon Kim, Seo Yeon ParkAgentic Retrieval-Augmented Generation SystemsSearch-Augmented Reasoning

    Hanyang University

  13. GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame

    Aug 30, 2026Zhe Dong, Wanqing Wu, Yuzhe Sun +5Feed-Forward 3D Reconstruction3D Foundation Models

    School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China · 54th Research Institute, China Electronics Technology Group Corporation, Shijiazhuang 050081, China · State Key Laboratory of Comprehensive PNT Network and Equipment Technology, Shijiazhuang 050081, China +1

  14. Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks

    Aug 28, 2026Munawar Hasan, Apostol VassilevFeed-ForwardTransformer Architectures

    National Institute of Standards and Technology, USA · Michigan Technological University, USA

  15. GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mapping

    Aug 28, 2026Xiang Yang, Yongli Wang, Yunsheng Zhang +3Feed-Forward 3D ReconstructionSimultaneous Localization And Mapping

    School of Geosciences and Info-Physics, Central South University, Changsha, China · Hunan Engineering Research Center of 3D Real Scene Construction and Application Technology, Changsha, China · College of Electronic Science and Technology, National University of Defense Technology, Changsha, China

  16. A concentration result for multilayer feedforward neural networks

    Aug 15, 2026Vera KoponenNeural NetworkMultilayer Perceptrons

  17. Convergence Guarantees of Gradient Descent for Neural Networks via Generalized Lipschitz Smoothness

    Aug 11, 2026Siqiao Mu, Diego KlabjanGradient DescentLipschitz Continuity

  18. Compact Feed-Forward 3D Gaussians via Saliency-Guided Primitive Merging

    Aug 11, 2026Tim-Felix Faasch, Jochen Kall, Cyrill Stachniss3D GaussianFeed-Forward

    Bosch Research Hildesheim, Germany · University of Bonn Bonn, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence Bonn, Germany

  19. DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning

    Aug 10, 2026Mainak Singha, Niccolò Biondi, Elisa Ricci +1Multimodal Continual Instruction TuningMixture-Of-Experts

    University of Trento, Italy · Fondazione Bruno Kessler, Italy · University of Bergamo, Italy

  20. AdaDINO: Pair-Aware In-Backbone Adaptation of Frozen DINO for Efficient Remote Sensing Change Detection

    Aug 8, 2026Xu Zhang, Xinqing Li, Jianpeng Xie +3Change DetectionRemote Sensing

    VCIP, College of Computer Science, Nankai University · School of Computer Science and Engineering, Tianjin University of Technology · Academy for Advanced Interdisciplinary Studies, Nankai University +1

  21. Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separation

    Aug 6, 2026Chunhui Shi, Xinwen FuRectified Linear Unit NetworksFeed-Forward

  22. Geometry-Guided Layerwise FFN Width Allocation in Transformers

    Aug 3, 2026Timur Mudarisov, Mikhail Burtsev, Radu StateBatch NormalizationTransformer Architectures

    University of Luxembourg · London Institute of Mathematical Sciences

  23. EntropyMoE: Entropy-Aware Sparse Expert Routing for Tokenizer-Free LLMs

    Jul 31, 2026Bo Liu, Muxuab Yu, Yu Zhang +2ExpertsEntropy

    University of Bristol · School of Automation Science and Electrical Engineering,Beihang University, Beijing, China · University of Manchester

  24. MeshFM: 2D Features Are All You Need for 3D Shape Understanding

    Jul 30, 2026Jinfan Zhou, Richard Liu, Itai Lang +1Shape Correspondence3D Generation

    University of Chicago, Chicago IL 60637, USA

  25. Prox: Training-Free FFN Activation Sparsity via Approximate Intermediate-Channel Salience in LLMs

    Jul 30, 2026Jinyi Liu, Wei Chen, Pengyu Chen +4LLM Inference OptimizationModel Activations

    Institute of Software, Chinese Academy of Sciences · University of Chinese Academy of Sciences · School of Computer Science, Nanjing University of Posts and Telecommunications

  26. Searching the Space of Feed-Forward Neural-Network Weight-Update Rules with Fixed Depth Symbolic Regression

    Jul 23, 2026Charles Brum, Edward FinkelsteinSymbolic RegressionNeural Network

    San Diego, California, USA · UCI, USA

  27. Exact ReLU realization of affine one-dimensional refinement iterates via residual memory and offset frames

    Jul 22, 2026Boldsaikhan Bolorkhuu, Tsogtgerel GantumurAffineRectified Linear Unit

    2National University of Mongolia · 1McGill University · Institute of Mathematics and Digital Technology, Mongolian Academy of Sciences

  28. A Controlled Study of Attention-Only Transformers

    Jul 20, 2026Henry Ndubuaku, Karen Mosoyan, Jakub Mroz +5Transformer AttentionTransformer Encoder

    Cactus Compute, Inc.

  29. How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA

    Jul 17, 2026Navya Gupta, Bingjie Xu, Avinash Anand +2Visual Grounding BenchmarksMisalignment Persona

    Singapore Institute of Technology Singapore · NVIDIA Singapore

  30. From Preimage Search To Source-Grounded Feature Inversion

    Jul 14, 2026Kaixiang ShuInverse DesignFeature Learning

    Independent Researcher

  31. RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration

    Jul 13, 2026Jiahao Luo, Hao Zhang, Jianqi Chen +9Animatable 3D Human AvatarsCross-Embodiment Retargeting

    1UCSC · 2UIUC · 3KAUST +1

  32. Sparse Inter-Layer Dependencies of Transformer FFN Neurons

    Jul 13, 2026Johannes Knittel, Hanspeter PfisterTransformer AttentionFeed-Forward

    Harvard University

  33. Backpropagation as a Nilpotent Linear System

    Jul 13, 2026Ahmed BoughammouraBackpropagationBackward Passes

    Higher Institute of Informatics and Mathematics of Monastir, University of Monastir, 5000 Monastir, Tunisia.

  34. Amplitude-Only FFN Intervention for Tool-Structured LLM Inference Method: Gated Evaluation Protocol, and Cross-Model Empirical Results

    Jul 13, 2026Sheng Xu, Junhua Wang, Boyuan Huang +3LLM Inference OptimizationFast Inference

    Alibaba Cloud

  35. Video Generation Models are General-Purpose Vision Learners

    Jul 10, 2026Letian Wang, Chuhan Zhang, Rishabh Kabra +9Generative Video ModelsVideo Generation

    Google DeepMind · University of Toronto · University College London +3

  36. Legible-by-Construction: Attention and End-to-End Transformers

    Jul 5, 2026Mark OskinTransformer ArchitecturesLanguage Modeling

    School of Computer Science and Engineering University of Washington

  37. InvSplat: Inverse Feed-Forward Scene Splatting

    Jul 2, 2026Polina Karpikova, Wenjing Bian, Haofei Xu +2Inverse RenderingFeed-Forward 3D Gaussian Splatting

    University of Tübingen, Tübingen AI Center · ETH Zurich

  38. Black-Box Inference of LLM Architectural Properties with Restrictive API Access

    Jul 1, 2026Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3Attacker Large Language ModelLarge Language Model Tool Use

    Carnegie Mellon University Pittsburgh, PA 15213 · Pittsburgh Supercomputing Center

  39. K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks

    Jul 1, 2026Gil PasternakImbalanced ClassificationNeural Network

    UNIVERSITY OF CALIFORNIA SAN DIEGO

  40. FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

    Jun 30, 2026Kartik Narayan, Vishal M. PatelFace Recognition ModelLow-Resolution

    Johns Hopkins University

  41. Low-dimensional topology of deep neural networks

    Jun 30, 2026Junyu Ren, Lek-Heng LimFeed-ForwardNeural Network

    University of Chicago, Chicago, IL, USA.

  42. Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

    Jun 30, 2026Mark OskinTransformer ArchitecturesFeed-Forward

    School of Computer Science and Engineering University of Washington

  43. Nonlinearity-Aware LoRA: Structured Gate Adaptation under Low-Rank Constraints

    Jun 30, 2026Shuai Yuan, Sudong Cai, Bingzhi Chen +4Feed-ForwardScaling Laws

    1Beijing Institute of Technology, Zhuhai · 2The Hong Kong Polytechnic University · 3The University of Osaka +1

  44. RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering

    Jun 29, 2026Huangsheng Du, Haoran Zhu, Youcheng Cai +2Neural RenderingVisual Geometry Grounded Transformer

    University of Science and Technology of China, China

  45. FastPano3D: Feed-Forward Indoor Panoramic 3D Reconstruction from a Single Image

    Jun 29, 2026Jianqiang Li, Liumei Zhang, Wenjia Guo +53D Reconstruction3D Gaussian

    Xi’an Shiyou University, Shaanxi, China · Xidian University, Shaanxi, China · Swansea University, Swansea, United Kingdom +1

  46. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images

    Jun 29, 2026Jianjiang Yao, Ke Xian, Renxiang Dai +1Animatable 3D Human AvatarsAvatars

    School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China

  47. Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes

    Jun 29, 2026Xi Li, Linyuan Li, Yan Wu +43D ReconstructionLocal Camera Pose

    Realsee, China · Quanzhou University of Information Engineering, China

  48. CLEAR-MoE: Shared-Basis Expert Extraction from Frozen Vision Transformers via Calibration-Driven Layer Selection

    Jun 26, 2026Md Irtiza Hossain, Humaira Ayesha, Junaid Ahmed SifatVision TransformerLocalized Lora-Moe

    Brac University

  49. FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models

    Jun 26, 2026Fan Mo, Yuxuan Han, Geng Zhang +2Mixture-Of-Experts Large Language ModelsMixture-Of-Experts

    National University of Singapore

  50. Algorithmic Foundations of Deep Learning: Complexity-Theoretic Rates and a Characterization of Universal Approximation

    Jun 25, 2026Anastasis Kratsios, Simone Brugiapaglia, Bum Jun Kim +2Neural ApproximationsApproximation

    McMaster University & Vector Institute, Toronto, ON, Canada · Concordia University, Montréal, QC, Canada · University of Tokyo, Tokyo, Japan +2

  51. Beyond Feedforward Networks: Reentry Neural Systems as the Fundamental Basis of Subjecthood and Intrinsic Safety of Next-Generation AGI

    Jun 24, 2026A. S. Ushakov, Yu. N. BerdinskArtificial Intelligence SafetyArtificial Intelligence Systems

    Saint Petersburg State University, Department of High Energy Physics and Elementary Particles

  52. FiCA: Feed-forward instant Gaussian Codec Avatars from a Single Portrait Image

    Jun 23, 2026Kim Youwang, Zhengyu Yang, Liuhao Ge +8Animatable 3D Human AvatarsAvatars

    Codec Avatars Lab, Meta · Dept. of Electrical Engineering, POSTECH

  53. Learning Entropy Signature for Image Representation and Classification

    Jun 21, 2026Jan Glaser, Ivo Bukovsky, Noriyasu Homma +1Image ClassificationFeed-Forward

    Dpt. of Applied Mathematics Czech Technical University in Prague Prague, Czech Republic · Dpt. of Computer Science University of South Bohemia in Ceske Budejovice Ceske Budejovice, Czech Republic · Dpt. of Radiological Imaging and Informatics Tohoku University Graduate School of Medicine Sendai, Japan

  54. MeshLoom: Feed-Forward Non-Rigid Registration of Mesh Sequences

    Jun 15, 2026Jianqi Chen, Jiraphon Yenphraphai, Xiangjun Tang +4Image RegistrationMeshes

    KAUST, Saudi Arabia · Snap Inc., United States of America · Purdue University, United States of America

  55. How Linear Is a Transformer Feed-Forward Block? Per-Block Linear Recoverability Is Learned, Not Architectural

    Jun 12, 2026Stuart WhippFeed-ForwardTransformer Architectures

    Independent Research

  56. AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects

    Jun 9, 2026Yiming Zhao, Haoyu Sun, Aoyu Wang3D Generative Models3D Generation

    1Bytedance

  57. ScaRF-SLAM: Scale-Consistent Reconstruction with Feed-Forward Models and Classical Visual SLAM

    May 29, 2026Yuhao Zhang, Yifu Tao, Frank Dellaert +1Orb-Slam2Simultaneous Localization And Mapping

    Oxford Robotics Institute, University of Oxford, UK · School of Interactive Computing, Georgia Institute of Technology, USA

  58. Reducing Experimental Testing in Space Propulsion Film Cooling Analyses by Pixelwise Generative Image Interpolation

    May 28, 2026Adam T. Müller, Philipp J. Teuffel, Konstantin Manassis +1Thermal ImagingImage Reconstruction

    Heilbronn University of Applied Sciences, Center for Machine Learning, Max-Planck-Str. 39, 74081 Heilbronn, Germany · German Aerospace Center (DLR), Institute of Space Propulsion

  59. Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data

    May 28, 2026Collin Cranston, Zhichao Wang, Todd Kemp +1Kernel MethodSpectral Decomposition

    Department of Mathematics University of California, San Diego, USA · ICSI and Department of Statistics University of California, Berkeley, USA · ICSI, LBNL and Department of Statistics University of California, Berkeley, USA

  60. The Complexity of Verifying Feedforward Neural Networks in Quantised Settings

    May 28, 2026Eric Alsmann, Martin Lange, Marco SälzerNeural Network VerificationQuantum Neural Networks

    University of Kassel · RPTU University Kaiserslautern-Landau