Cover Image

Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Darade, Ishita, Thorat, Sushrut
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AutoCompress: Critical Layer Isolation for Efficient Transformer Compression
by: Thorat, Archit
Published: (2026)

Path Integration and Object-Location Binding Emerge in an Action-Conditioned Predictive Sequence Network
by: Ventura, Linda Ariel, et al.
Published: (2026)

Sparks of cognitive flexibility: self-guided context inference for flexible stimulus-response mapping by attentional routing
by: Sommers, Rowan P., et al.
Published: (2025)

Adopting a human developmental visual diet yields robust, shape-based AI vision
by: Lu, Zejin, et al.
Published: (2025)

Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks
by: Anthes, Daniel, et al.
Published: (2023)

Brain-language fusion enables interactive neural readout and in-silico experimentation
by: Bosch, Victoria, et al.
Published: (2025)

I See, Therefore I Do: Estimating Causal Effects for Image Treatments
by: Thorat, Abhinav, et al.
Published: (2024)

AeTHERON: Autoregressive Topology-aware Heterogeneous Graph Operator Network for Fluid-Structure Interaction
by: Kumar, Sushrut
Published: (2026)

Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task
by: Curth, Alicia, et al.
Published: (2026)

Which LLMs are Difficult to Detect? A Detailed Analysis of Potential Factors Contributing to Difficulties in LLM Text Detection
by: Thorat, Shantanu, et al.
Published: (2024)

Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
by: Azangulov, Iskander, et al.
Published: (2025)

Can a Transformer Represent a Kalman Filter?
by: Goel, Gautam, et al.
Published: (2023)

Machine learning assisted state prediction of misspecified linear dynamical system via modal reduction
by: Thorat, Rohan Vitthal, et al.
Published: (2026)

Efficient Knowledge Distillation via Curriculum Extraction
by: Gupta, Shivam, et al.
Published: (2025)

DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Models
by: Thorat, Shantanu, et al.
Published: (2025)

Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
by: Bartosh, Grigory, et al.
Published: (2026)

Testing for Causal Fairness
by: Fu, Jiarun, et al.
Published: (2025)

HLogformer: A Hierarchical Transformer for Representing Log Data
by: Hou, Zhichao, et al.
Published: (2024)

Transforming Causality: Transformer-Based Temporal Causal Discovery with Prior Knowledge Integration
by: Huang, Jihua, et al.
Published: (2025)

ILRe: Intermediate Layer Retrieval for Context Compression in Causal Language Models
by: Liang, Manlai, et al.
Published: (2025)

Intent-Aware Neural Query Reformulation for Behavior-Aligned Product Search
by: Yetukuri, Jayanth, et al.
Published: (2025)

Representing Rule-based Chatbots with Transformers
by: Friedman, Dan, et al.
Published: (2024)

Transformers Linearly Represent Highly Structured World Models
by: Kniazev, Roman, et al.
Published: (2026)

Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training
by: Luo, Cheng, et al.
Published: (2024)

GNNMerge: Merging of GNN Models Without Accessing Training Data
by: Garg, Vipul, et al.
Published: (2025)

Test-Time Adaptation by Causal Trimming
by: Liu, Yingnan, et al.
Published: (2025)

Extracting Important Tokens in E-Commerce Queries with a Tag Interaction-Aware Transformer Model
by: Kabir, Md. Ahsanul, et al.
Published: (2025)

Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms
by: Kera, Hiroshi, et al.
Published: (2025)

Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
by: Hellwig, Philipp, et al.
Published: (2026)

CausalFormer: An Interpretable Transformer for Temporal Causal Discovery
by: Kong, Lingbai, et al.
Published: (2024)

Computational characterization of the role of an attention schema in controlling visuospatial attention
by: Piefke, Lotta, et al.
Published: (2024)

Safe Reinforcement Learning-Based Vibration Control: Overcoming Training Risks with LQR Guidance
by: Thorat, Rohan Vitthal, et al.
Published: (2025)

Transformers with Sparse Attention for Granger Causality
by: Mahesh, Riya, et al.
Published: (2024)

TriOpt: A Scalable Algorithm for Linear Causal Discovery
by: Joy, Rafat Ashraf, et al.
Published: (2026)

Robust Learning of a Group DRO Neuron
by: Cao, Guyang, et al.
Published: (2026)

ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding
by: Lee, Megan, et al.
Published: (2026)

Transformer Is Inherently a Causal Learner
by: Wang, Xinyue, et al.
Published: (2026)

Testing Generalizability in Causal Inference
by: Manela, Daniel de Vassimon, et al.
Published: (2024)

Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
by: Li, Shuyao, et al.
Published: (2024)

On Universally Optimal Algorithms for A/B Testing
by: Wang, Po-An, et al.
Published: (2023)