Copertina

Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chhabra, Vishnu Kabir, Zhu, Ding, Khalili, Mohammad Mahdi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the transferability of Sparse Autoencoders for interpreting compressed models
di: Gupte, Suchit, et al.
Pubblicazione: (2025)

Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability
di: Chhabra, Vishnu Kabir, et al.
Pubblicazione: (2025)

ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers
di: Zhu, Ding, et al.
Pubblicazione: (2024)

An Efficient Training Algorithm for Models with Block-wise Sparsity
di: Zhu, Ding, et al.
Pubblicazione: (2025)

Post-processing for Fair Regression via Explainable SVD
di: Zuo, Zhiqun, et al.
Pubblicazione: (2025)

Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
di: Nahin, Shahriar Kabir, et al.
Pubblicazione: (2025)

Individual Fairness In Strategic Classification
di: Zuo, Zhiqun, et al.
Pubblicazione: (2026)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
di: Zhu, Xudong, et al.
Pubblicazione: (2025)

From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
di: Zhu, Xudong, et al.
Pubblicazione: (2025)

Unraveling Indirect In-Context Learning Using Influence Functions
di: Askari, Hadi, et al.
Pubblicazione: (2025)

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
di: Monjur, Ocean, et al.
Pubblicazione: (2026)

Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers
di: Adhikari, Rabin
Pubblicazione: (2025)

Lookahead Counterfactual Fairness
di: Zuo, Zhiqun, et al.
Pubblicazione: (2024)

Neuroplasticity-inspired dynamic ANNs for multi-task demand forecasting
di: Żarski, Mateusz, et al.
Pubblicazione: (2025)

Advancing Out-of-Distribution Detection via Local Neuroplasticity
di: Canevaro, Alessandro, et al.
Pubblicazione: (2025)

Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
di: Datta, Shrestha, et al.
Pubblicazione: (2026)

First is Not Really Better Than Last: Evaluating Layer Choice and Aggregation Strategies in Language Model Data Influence Estimation
di: Vitel, Dmytro, et al.
Pubblicazione: (2025)

Learning Tennis Strategy Through Curriculum-Based Dueling Double Deep Q-Networks
di: Mohan, Vishnu
Pubblicazione: (2025)

Representation Stability in a Minimal Continual Learning Agent
di: Subramanian, Vishnu
Pubblicazione: (2026)

Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
di: Hu, James, et al.
Pubblicazione: (2026)

Controlling the Risk of Corrupted Contexts for Language Models via Early-Exiting
di: Wynn, Andrea, et al.
Pubblicazione: (2025)

The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
di: Internò, Christian, et al.
Pubblicazione: (2026)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
di: Xu, Jiawei, et al.
Pubblicazione: (2024)

Split Federated Learning Architectures for High-Accuracy and Low-Delay Model Training
di: Papageorgiou, Yiannis, et al.
Pubblicazione: (2026)

Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models
di: Chhabra, Anshuman, et al.
Pubblicazione: (2024)

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior
di: Mayne, Harry, et al.
Pubblicazione: (2026)

Gate Recurrent Unit for Efficient Industrial Gas Identification
di: Wang, Ding
Pubblicazione: (2024)

Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants
di: Modi, Chirag, et al.
Pubblicazione: (2025)

CNN Autoencoders for Hierarchical Feature Extraction and Fusion in Multi-sensor Human Activity Recognition
di: Arabzadeh, Saeed, et al.
Pubblicazione: (2025)

Corruption Robust Offline Reinforcement Learning with Human Feedback
di: Mandal, Debmalya, et al.
Pubblicazione: (2024)

FAMOUS: Flexible Accelerator for the Attention Mechanism of Transformer on UltraScale+ FPGAs
di: Kabir, Ehsan, et al.
Pubblicazione: (2024)

ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning
di: Naseri, Mahdi, et al.
Pubblicazione: (2024)

Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
di: Amaefuna, Theophilus, et al.
Pubblicazione: (2026)

Efficient Zero-Order Federated Finetuning of Language Models for Resource-Constrained Devices
di: Ahmed, Mohamed Aboelenien, et al.
Pubblicazione: (2025)

Analytic Continual Test-Time Adaptation for Multi-Modality Corruption
di: Zhang, Yufei, et al.
Pubblicazione: (2024)

Toward Optimal Regret in Robust Pricing: Decoupling Corruption and Time
di: Kalupahana, Kalana, et al.
Pubblicazione: (2026)

Indirect Attention: Turning Context Misalignment into a Feature
di: Bahaduri, Bissmella, et al.
Pubblicazione: (2025)

Generalization and Membership Inference Attack a Practical Perspective
di: Rahmani, Fateme, et al.
Pubblicazione: (2026)

Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning
di: Xiao, Qian, et al.
Pubblicazione: (2024)

Forecasting Application Counts in Talent Acquisition Platforms: Harnessing Multimodal Signals using LMs
di: Kabir, Md Ahsanul, et al.
Pubblicazione: (2024)