Imagen de Portada

Manifold-Guided Attention Steering

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Ian, Guruprasad, Kapilesh, Sengupta, Raunak, Satish, Ninad, D'Antoni, Loris, Yu, Rose
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
por: Zhang, Yuhao, et al.
Publicado: (2023)

Bootstrapping Fuzzers for Compilers of Low-Resource Language Dialects Using Language Models
por: Vaidya, Sairam, et al.
Publicado: (2025)

Continuous Diffusion Models Can Obey Formal Syntax
por: Kim, Jinwoo, et al.
Publicado: (2026)

Learning the Error Patterns of Language Models
por: Kim, Jinwoo, et al.
Publicado: (2026)

Verified Training for Counterfactual Explanation Robustness under Data Shift
por: Meyer, Anna P., et al.
Publicado: (2024)

Constrained Adaptive Rejection Sampling
por: Parys, Paweł, et al.
Publicado: (2025)

Grammar-Aligned Decoding
por: Park, Kanghee, et al.
Publicado: (2024)

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
por: Gonzalez, Emmanuel Anaya, et al.
Publicado: (2025)

Zero-shot Factual Consistency Evaluation Across Domains
por: Agarwal, Raunak
Publicado: (2024)

Verifying Solutions to Semantics-Guided Synthesis Problems
por: Murphy, Charlie, et al.
Publicado: (2024)

Fixed-Budget Constrained Best Arm Identification in Grouped Bandits
por: Mukherjee, Raunak, et al.
Publicado: (2026)

Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
por: Keswani, Mahesh, et al.
Publicado: (2025)

Probabilistic Consensus through Ensemble Validation: A Framework for LLM Reliability
por: Naik, Ninad
Publicado: (2024)

Language-Based Agent Control
por: Zhou, Timothy, et al.
Publicado: (2026)

Unrealizability Logic
por: Kim, Jinwoo, et al.
Publicado: (2022)

A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness
por: Zhang, Yuhao, et al.
Publicado: (2024)

Flexible and Efficient Grammar-Constrained Decoding
por: Park, Kanghee, et al.
Publicado: (2025)

Synthesizing Specifications
por: Park, Kanghee, et al.
Publicado: (2023)

LOUD: Synthesizing Strongest and Weakest Specifications
por: Park, Kanghee, et al.
Publicado: (2024)

X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention
por: Raghavan, Guruprasad, et al.
Publicado: (2026)

Collaborative Causal Sensemaking: Closing the Complementarity Gap in Human-AI Decision Support
por: Jain, Raunak
Publicado: (2025)

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
por: Wurgaft, Daniel, et al.
Publicado: (2026)

Predicting NCAP Safety Ratings: An Analysis of Vehicle Characteristics and ADAS Features Using Machine Learning
por: Kunwar, Raunak, et al.
Publicado: (2025)

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds
por: Wu, Honghan, et al.
Publicado: (2026)

Safe Langevin Soft Actor Critic
por: Keswani, Mahesh, et al.
Publicado: (2026)

Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering
por: Venkateswaran, Praveen, et al.
Publicado: (2025)

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

Online Convex Optimization with Unbounded Memory
por: Kumar, Raunak, et al.
Publicado: (2022)

Dynamic Graph Attention Networks for Travel Time Distribution Prediction in Urban Arterial Roads
por: Yousefzadeh, Nooshin, et al.
Publicado: (2024)

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

Guided Random Forest and its application to data approximation
por: Gupta, Prashant, et al.
Publicado: (2019)

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
por: Zhang, Qingru, et al.
Publicado: (2023)

Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders
por: Rhodes, Jake S., et al.
Publicado: (2025)

The Format Tax
por: Lee, Ivan Yee, et al.
Publicado: (2026)

Virtualidad crítica en el aula universitaria en la pandemia (y más allá)
por: Maurizia D’Antoni
Publicado: (2020)

VIGOTSKI, DESARROLLO INFANTIL Y APORTES PARA EL AULA COSTARRICENSE
por: Maurizia D'Antoni
Publicado: (2009)

Derechos humanos de la infancia en un trabajo comunal universitario
por: Maurizia D'Antoni
Publicado: (2006)

Competencia cultural e inteligencia cultural. Aportes a la mediación cultural docente
por: Maurizia D'Antoni
Publicado: (2011)

Crisis en la educación secundaria: ¿reproducir o transformar?
por: Maurizia D'Antoni
Publicado: (2005)

Búsqueda de disonancias en discursos y prácticas sobre música
por: Maurizia D'Antoni
Publicado: (2017)