Imagen de Portada

TrAct: Making First-layer Pre-Activations Trainable

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Petersen, Felix, Borgelt, Christian, Ermon, Stefano
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Convolutional Differentiable Logic Gate Networks
por: Petersen, Felix, et al.
Publicado: (2024)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
por: Wang, Austin, et al.
Publicado: (2026)

DreamPropeller: Supercharge Text-to-3D Generation with Parallel Sampling
por: Zhou, Linqi, et al.
Publicado: (2023)

Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation
por: Petersen, Felix, et al.
Publicado: (2024)

Geometric Trajectory Diffusion Models
por: Han, Jiaqi, et al.
Publicado: (2024)

Divergence Minimization Preference Optimization for Diffusion Model Alignment
por: Li, Binxu, et al.
Publicado: (2025)

Personalized Preference Fine-tuning of Diffusion Models
por: Dang, Meihua, et al.
Publicado: (2025)

Semi-Supervised Transfer Boosting (SS-TrBoosting)
por: Deng, Lingfei, et al.
Publicado: (2024)

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
por: Han, Jiaqi, et al.
Publicado: (2026)

Trainable Fixed-Point Quantization for Deep Learning Acceleration on FPGAs
por: Dai, Dingyi, et al.
Publicado: (2024)

Making Sense Of Distributed Representations With Activation Spectroscopy
por: Reing, Kyle, et al.
Publicado: (2025)

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion
por: Li, Yinghui, et al.
Publicado: (2024)

CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models
por: Hu, Zheyuan, et al.
Publicado: (2025)

dynActivation: A Trainable Activation Family for Adaptive Nonlinearity
por: Bachmann, Alois
Publicado: (2026)

RepAct: The Re-parameterizable Adaptive Activation Function
por: Wu, Xian, et al.
Publicado: (2024)

A Trainable Feature Extractor Module for Deep Neural Networks and Scanpath Classification
por: Fuhl, Wolfgang
Publicado: (2024)

Energy Scaling Laws for Diffusion Models: Quantifying Compute in Image Generation
por: Iyengar, Aniketh, et al.
Publicado: (2025)

APTx Neuron: A Unified Trainable Neuron Architecture Integrating Activation and Computation
por: Kumar, Ravin
Publicado: (2025)

HarvestNet: A Dataset for Detecting Smallholder Farming Activity Using Harvest Piles and Remote Sensing
por: Xu, Jonathan, et al.
Publicado: (2023)

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder
por: Lee, Yongmin, et al.
Publicado: (2025)

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
por: Xu, Boxun, et al.
Publicado: (2026)

MeanFlow Transformers with Representation Autoencoders
por: Hu, Zheyuan, et al.
Publicado: (2025)

DistillKac: Few-Step Image Generation via Damped Wave Equations
por: Han, Weiqiao, et al.
Publicado: (2025)

TrACT: A Training Dynamics Aware Contrastive Learning Framework for Long-tail Trajectory Prediction
por: Zhang, Junrui, et al.
Publicado: (2024)

An Interpretable X-ray Style Transfer via Trainable Local Laplacian Filter
por: Eckert, Dominik, et al.
Publicado: (2024)

Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
por: Yang, Ling, et al.
Publicado: (2024)

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
por: Zhang, Jintao, et al.
Publicado: (2026)

Contextualized Diffusion Models for Text-Guided Image and Video Generation
por: Yang, Ling, et al.
Publicado: (2024)

G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving
por: Murata, Naoki, et al.
Publicado: (2024)

Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
por: Li, Hao, et al.
Publicado: (2024)

RefTr: Recurrent Refinement of Confluent Trajectories for 3D Vascular Tree Centerlines
por: Naeem, Roman, et al.
Publicado: (2025)

On the Scalability of Diffusion-based Text-to-Image Generation
por: Li, Hao, et al.
Publicado: (2024)

ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
por: Gong, Dayoung, et al.
Publicado: (2024)

DiffusionSat: A Generative Foundation Model for Satellite Imagery
por: Khanna, Samar, et al.
Publicado: (2023)

Slight Corruption in Pre-training Data Makes Better Diffusion Models
por: Chen, Hao, et al.
Publicado: (2024)

Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
por: Wu, Yang, et al.
Publicado: (2026)

Trainable Highly-expressive Activation Functions
por: Chelly, Irit, et al.
Publicado: (2024)

A Unified View of Score-Based and Drifting Models
por: Lai, Chieh-Hsin, et al.
Publicado: (2026)

Reason--Imagine--Act: Closed-Loop LLM Decision Making with World Models for Autonomous Driving
por: Sun, Zhengqi, et al.
Publicado: (2026)

A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
por: Woerner, Stefano, et al.
Publicado: (2024)