Copertina

The Topological Trouble With Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mozer, Michael C., Siddiqui, Shoaib Ahmed, Liu, Rosanne
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2025)

Position: Capability Control Should be a Separate Goal From Alignment
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2026)

On Evaluating LLMs' Capabilities as Functional Approximators: A Bayesian Perspective
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2024)

A deeper look at depth pruning of LLMs
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2024)

Exploring the design space of deep-learning-based weather forecasting systems
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2024)

Improving Discrete Optimisation Via Decoupled Straight-Through Estimator
di: Shah, Rushi, et al.
Pubblicazione: (2024)

Blockwise Self-Supervised Learning at Scale
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2023)

Permissive Information-Flow Analysis for Large Language Models
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2024)

Decoupling the "What" and "Where" With Polar Coordinate Positional Embeddings
di: Gopalakrishnan, Anand, et al.
Pubblicazione: (2025)

Logit Scaling for Out-of-Distribution Detection
di: Djurisic, Andrija, et al.
Pubblicazione: (2024)

Unlearning via Sparse Representations
di: Shah, Vedant, et al.
Pubblicazione: (2023)

Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
di: Fernando, Jesseba, et al.
Pubblicazione: (2026)

Interaction Topological Transformer for Multiscale Learning in Porous Materials
di: Chen, Dong, et al.
Pubblicazione: (2025)

Adaptive Computation Depth via Learned Token Routing in Transformers
di: Mohammed, Ahmed Abdelmuniem Abdalla
Pubblicazione: (2026)

Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning
di: Shokry, Ahmed, et al.
Pubblicazione: (2025)

Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
di: Choromanski, Krzysztof, et al.
Pubblicazione: (2024)

Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
di: Didolkar, Aniket, et al.
Pubblicazione: (2024)

GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection
di: Shen, Lingzhi, et al.
Pubblicazione: (2024)

Evaluating Large Language Models for Security Bug Report Prediction
di: Soltaniani, Farnaz, et al.
Pubblicazione: (2026)

AI-Assisted Generation of Difficult Math Questions
di: Shah, Vedant, et al.
Pubblicazione: (2024)

Physics-Guided Memory Network for Building Energy Modeling
di: Danish, Muhammad Umair, et al.
Pubblicazione: (2025)

Enhancing LLM Planning Capabilities through Intrinsic Self-Critique
di: Bohnet, Bernd, et al.
Pubblicazione: (2025)

Towards a More Complete Theory of Function Preserving Transforms
di: Painter, Michael
Pubblicazione: (2024)

Graph Diffusion Transformers are In-Context Molecular Designers
di: Liu, Gang, et al.
Pubblicazione: (2025)

Deep Optimal Experimental Design for Parameter Estimation Problems
di: Siddiqui, Md Shahriar Rahim, et al.
Pubblicazione: (2024)

Visualizing Loss Functions as Topological Landscape Profiles
di: Geniesse, Caleb, et al.
Pubblicazione: (2024)

Topological derivative approach for deep neural network architecture adaptation
di: Krishnanunni, C G, et al.
Pubblicazione: (2025)

Evaluating Loss Landscapes from a Topology Perspective
di: Xie, Tiankai, et al.
Pubblicazione: (2024)

Prediction of Bank Credit Ratings using Heterogeneous Topological Graph Neural Networks
di: Liu, Junyi, et al.
Pubblicazione: (2025)

Topology-aware Reinforcement Feature Space Reconstruction for Graph Data
di: Ying, Wangyang, et al.
Pubblicazione: (2024)

KD-GAT: Combining Knowledge Distillation and Graph Attention Transformer for a Controller Area Network Intrusion Detection System
di: Frenken, Robert, et al.
Pubblicazione: (2025)

Plug-and-Play Transformer Modules for Test-Time Adaptation
di: Chang, Xiangyu, et al.
Pubblicazione: (2024)

Topological Signatures of Grokking
di: Tang, Yifan, et al.
Pubblicazione: (2026)

Generative Topological Networks
di: Levy-Jurgenson, Alona, et al.
Pubblicazione: (2024)

Layer Specialization Underlying Compositional Reasoning in Transformers
di: Liu, Jing
Pubblicazione: (2025)

Supercharging Graph Transformers with Advective Diffusion
di: Wu, Qitian, et al.
Pubblicazione: (2023)

On Limitation of Transformer for Learning HMMs
di: Hu, Jiachen, et al.
Pubblicazione: (2024)

From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning
di: Feng, Chao, et al.
Pubblicazione: (2025)

VARMA-Enhanced Transformer for Time Series Forecasting
di: Song, Jiajun, et al.
Pubblicazione: (2025)

SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy
di: Zou, Xuecheng, et al.
Pubblicazione: (2026)