Cover Image

TARDIS: Mitigating Temporal Misalignment via Representation Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shin, Changho, Yan, Xinya, Jo, Suenggwan, Cho, Sungjun, Chaudhuri, Shourjo Aditya, Sala, Frederic
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

LLM-Integrated Bayesian State Space Models for Multimodal Time-Series Forecasting
by: Cho, Sungjun, et al.
Published: (2025)

Weak-to-Strong Generalization Through the Data-Centric Lens
by: Shin, Changho, et al.
Published: (2024)

Personalize Your LLM: Fake it then Align it
by: Zhang, Yijing, et al.
Published: (2025)

Zero-Shot Robustification of Zero-Shot Models
by: Adila, Dyah, et al.
Published: (2023)

Is Free Self-Alignment Possible?
by: Adila, Dyah, et al.
Published: (2024)

OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
by: Shin, Changho, et al.
Published: (2024)

Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check
by: Cho, Sungjun, et al.
Published: (2025)

Multimodal Data Curation via Object Detection and Filter Ensembles
by: Huang, Tzu-Heng, et al.
Published: (2024)

CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
by: Zhao, Jitian, et al.
Published: (2026)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
by: Karnik, Sathwik, et al.
Published: (2025)

Weight Updates as Activation Shifts: A Principled Framework for Steering
by: Adila, Dyah, et al.
Published: (2026)

Temporal Misalignment in ANN-SNN Conversion and Its Mitigation via Probabilistic Spiking Neurons
by: Bojković, Velibor, et al.
Published: (2025)

Federated Time Series Generation on Feature and Temporally Misaligned Data
by: Soi, Zhi Wen, et al.
Published: (2024)

Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning
by: Kim, Seyeon, et al.
Published: (2024)

Product Manifold Representations for Learning on Biological Pathways
by: McNeela, Daniel, et al.
Published: (2024)

Convergent Linear Representations of Emergent Misalignment
by: Soligo, Anna, et al.
Published: (2025)

Test-Time Scaling Makes Overtraining Compute-Optimal
by: Roberts, Nicholas, et al.
Published: (2026)

Imitation Learning from a Single Temporally Misaligned Video
by: Huey, William, et al.
Published: (2025)

Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving
by: Shahriar, Md Hasan, et al.
Published: (2025)

RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation
by: Liang, Kaiqu, et al.
Published: (2025)

Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering
by: Lee, Seojin, et al.
Published: (2026)

Curvature-Guided LoRA: Steering in the pretrained NTK subspace
by: Zheng, Frédéric, et al.
Published: (2026)

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
by: Cha, Sungmin, et al.
Published: (2024)

Steering an Active Learning Workflow Towards Novel Materials Discovery via Queue Prioritization
by: Schwarting, Marcus, et al.
Published: (2025)

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
by: Luan, Yao, et al.
Published: (2025)

Steering Pretrained Drafters during Speculative Decoding
by: Berdoz, Frédéric, et al.
Published: (2025)

Dissecting Representation Misalignment in Contrastive Learning via Influence Function
by: Hu, Lijie, et al.
Published: (2024)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
by: Huang, Yao, et al.
Published: (2025)

GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs
by: Zhang, Xuanqi, et al.
Published: (2026)

Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval
by: Braun, Guillaume, et al.
Published: (2026)

Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift
by: Zhao, Zhiyuan, et al.
Published: (2025)

Unintended Misalignment from Agentic Fine-Tuning: Risks and Mitigation
by: Hahm, Dongyoon, et al.
Published: (2025)

Unveiling the Potential of Superexpressive Networks in Implicit Neural Representations
by: Mudiyanselage, Uvini Balasuriya, et al.
Published: (2025)

MEG-GPT: A transformer-based foundation model for magnetoencephalography data
by: Huang, Rukuang, et al.
Published: (2025)

Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
by: Jo, Sung Ho, et al.
Published: (2025)

AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations
by: Clark, Michael J.
Published: (2026)

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
by: Cai, Yichao, et al.
Published: (2025)

Concept Heterogeneity-aware Representation Steering
by: Abdullaev, Laziz U., et al.
Published: (2026)

Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
by: Cha, Sungmin, et al.
Published: (2023)

COSMOS: Predictable and Cost-Effective Adaptation of LLMs
by: Wang, Jiayu, et al.
Published: (2025)