Imagen de Portada

When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Robertson, John T., Zhu, Jianing, Vikalo, Haris, Wang, Zhangyang
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Federated Self-Supervised Learning for Automatic Modulation Classification under Non-IID and Class-Imbalanced Data
por: Akram, Usman, et al.
Publicado: (2025)

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
por: Zhu, Jianing, et al.
Publicado: (2026)

Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization
por: Kim, Dongjun, et al.
Publicado: (2026)

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
por: Kiyani, Shayan, et al.
Publicado: (2026)

Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
por: Zhang, Haoran, et al.
Publicado: (2026)

CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
por: Cha, Seohyeon, et al.
Publicado: (2026)

GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
por: Yao, Zhangyang, et al.
Publicado: (2026)

Cut Less, Fold More: Model Compression through the Lens of Projection Geometry
por: Saukh, Olga, et al.
Publicado: (2026)

Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
por: Chen, Huancheng, et al.
Publicado: (2023)

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
por: Cho, Yoonjun, et al.
Publicado: (2026)

MGAA: Multi-Granular Adaptive Allocation fof Low-Rank Compression of LLMs
por: Li, Guangyan, et al.
Publicado: (2025)

Operator Learning with Domain Decomposition for Geometry Generalization in PDE Solving
por: Huang, Jianing, et al.
Publicado: (2025)

The Information Geometry of Softmax: Probing and Steering
por: Park, Kiho, et al.
Publicado: (2026)

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
por: Zhang, Haoran, et al.
Publicado: (2026)

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
por: Jung, Yeonjoon, et al.
Publicado: (2025)

Position: Weight Space Should Be a First-Class Generative AI Modality
por: Wang, Zhangyang, et al.
Publicado: (2026)

Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget
por: Khan, Zohaib, et al.
Publicado: (2026)

Transformers as Implicit State Estimators: In-Context Learning in Dynamical Systems
por: Akram, Usman, et al.
Publicado: (2024)

Recovering Labels from Local Updates in Federated Learning
por: Chen, Huancheng, et al.
Publicado: (2024)

Rich Insights from Cheap Signals: Efficient Evaluations via Tensor Factorization
por: Polo, Felipe Maia, et al.
Publicado: (2026)

PIPA: Preference Alignment as Prior-Informed Statistical Estimation
por: Li, Junbo, et al.
Publicado: (2025)

Revisiting Tree Search for LLMs: Gumbel and Sequential Halving for Budget-Scalable Reasoning
por: Ugadiarov, Leonid, et al.
Publicado: (2026)

MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency
por: Liu, Xiaoyun, et al.
Publicado: (2023)

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
por: Zhang, Jiaying, et al.
Publicado: (2026)

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
por: Perin, Gabriel J., et al.
Publicado: (2025)

Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
por: Li, Yushu, et al.
Publicado: (2026)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
por: Springer, Max, et al.
Publicado: (2026)

Large Language-Geometry Model: When LLM meets Equivariance
por: Li, Zongzhao, et al.
Publicado: (2025)

Ranking-aware Reinforcement Learning for Ordinal Ranking
por: Hao, Aiming, et al.
Publicado: (2026)

Is Monotonic Sampling Necessary in Diffusion Models?
por: Khan, Muhammad Haris
Publicado: (2026)

Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
por: Saveliev, Evgeny S., et al.
Publicado: (2026)

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
por: Wen, Hao, et al.
Publicado: (2025)

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
por: Kossen, Jannik, et al.
Publicado: (2024)

Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
por: Chen, Xi, et al.
Publicado: (2024)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
por: Jiang, Xinyan, et al.
Publicado: (2026)

General and Efficient Steering of Unconditional Diffusion
por: Wang, Qingsong, et al.
Publicado: (2026)

Granular-Ball-Induced Multiple Kernel K-Means
por: Xia, Shuyin, et al.
Publicado: (2025)

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
por: Hossain, Elias, et al.
Publicado: (2026)

BarrierSteer: LLM Safety via Learning Barrier Steering
por: Tran, Thanh Q., et al.
Publicado: (2026)

MidSteer: Optimal Affine Framework for Steering Generative Models
por: Gaintseva, Tatiana, et al.
Publicado: (2026)