Cover Image

Understanding the Staged Dynamics of Transformers in Learning Latent Structure

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Saha, Rohan, Aminmansour, Farzane, Fyshe, Alona
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training
by: Saha, Rohan, et al.
Published: (2024)

RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models
by: Najafi, Saeed, et al.
Published: (2024)

Offline Preference Optimization via Maximum Marginal Likelihood Estimation
by: Najafi, Saeed, et al.
Published: (2025)

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
by: Fahim, Abrar, et al.
Published: (2024)

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
by: Aminmansour, Farzane, et al.
Published: (2020)

Finding Shared Decodable Concepts and their Negations in the Brain
by: Efird, Cory, et al.
Published: (2024)

Goal-Space Planning with Subgoal Models
by: Lo, Chunlok, et al.
Published: (2022)

RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?
by: Gupta, Rohan, et al.
Published: (2025)

Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks
by: Murphy, Alex, et al.
Published: (2024)

Understanding Learning Dynamics Through Structured Representations
by: Nikooroo, Saleh, et al.
Published: (2025)

Latent Chain-of-Thought Improves Structured-Data Transformers
by: Dudley, Carson, et al.
Published: (2026)

Two-Scale Latent Dynamics for Recurrent-Depth Transformers
by: Pappone, Francesco, et al.
Published: (2025)

Stage-Aware Learning for Dynamic Treatments
by: Ye, Hanwen, et al.
Published: (2023)

Generative Topological Networks
by: Levy-Jurgenson, Alona, et al.
Published: (2024)

Two-Stage Feature Generation with Transformer and Reinforcement Learning
by: Gao, Wanfu, et al.
Published: (2025)

Understanding Self-Supervised Learning via Latent Distribution Matching
by: Mikulasch, Fabian A, et al.
Published: (2026)

Identify Then Project: Contrastive Learning of Latent Dynamics from Partial Observations with Port-Hamiltonian Structure
by: Li, Peilun, et al.
Published: (2026)

Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics
by: Sristi, Ram Dyuthi, et al.
Published: (2025)

Disentangling Feature Structure: A Mathematically Provable Two-Stage Training Dynamics in Transformers
by: Gong, Zixuan, et al.
Published: (2025)

Learning Coupled System Dynamics under Incomplete Physical Constraints and Missing Data
by: Saha, Esha, et al.
Published: (2025)

A Comparative Analysis of Transformer Models in Social Bot Detection
by: Veit, Rohan, et al.
Published: (2025)

Next-Latent Prediction Transformers Learn Compact World Models
by: Teoh, Jayden, et al.
Published: (2025)

Securing Social Spaces: Harnessing Deep Learning to Eradicate Cyberbullying
by: Biswas, Rohan, et al.
Published: (2024)

The Impossibility of Inverse Permutation Learning in Transformer Models
by: Alur, Rohan, et al.
Published: (2025)

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics
by: Chen, Zheng-An, et al.
Published: (2025)

Learning Latent Graph Structures and their Uncertainty
by: Manenti, Alessandro, et al.
Published: (2024)

Maximum Likelihood Learning of Latent Dynamics Without Reconstruction
by: Hromadka, Samo, et al.
Published: (2025)

Dynamics of Learning: Generative Schedules from Latent ODEs
by: Sampson, Matt L., et al.
Published: (2025)

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
by: Song, Yuda, et al.
Published: (2024)

Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributions
by: Saha, Surojit, et al.
Published: (2025)

Towards Understanding Transformers in Learning Random Walks
by: Shi, Wei, et al.
Published: (2025)

Dynamic Latent Separation for Deep Learning
by: Tuan, Yi-Lin, et al.
Published: (2022)

Transformers Learn Latent Mixture Models In-Context via Mirror Descent
by: D'Angelo, Francesco, et al.
Published: (2026)

Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework
by: Ye, Yubo, et al.
Published: (2024)

ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders
by: Saha, Surojit, et al.
Published: (2025)

Understanding Lookahead Dynamics Through Laplace Transform
by: Sanyal, Aniket, et al.
Published: (2025)

Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
by: Xu, Tian, et al.
Published: (2022)

AdaSwarm: Augmenting Gradient-Based optimizers in Deep Learning with Swarm Intelligence
by: Mohapatra, Rohan, et al.
Published: (2020)

Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
by: Sandilya, Ruchi, et al.
Published: (2025)

The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
by: Sam, Tyler, et al.
Published: (2024)