Cover Image

TrAct: Making First-layer Pre-Activations Trainable

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Petersen, Felix, Borgelt, Christian, Ermon, Stefano
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Convolutional Differentiable Logic Gate Networks
by: Petersen, Felix, et al.
Published: (2024)

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

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

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

Geometric Trajectory Diffusion Models
by: Han, Jiaqi, et al.
Published: (2024)

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

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

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

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

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

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

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

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

dynActivation: A Trainable Activation Family for Adaptive Nonlinearity
by: Bachmann, Alois
Published: (2026)

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

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

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

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

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

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

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

MeanFlow Transformers with Representation Autoencoders
by: Hu, Zheyuan, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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