Copertina

Inference-time Alignment via Sparse Junction Steering

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Hu, Runyi, Zhang, Jie, Zhao, Shiqian, Meng, Jiale, Li, Jiwei, Zeng, Jason, Wu, Ming, Heinrich, Michael, Wen, Yonggang, Zhang, Tianwei
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Mask Image Watermarking
di: Hu, Runyi, et al.
Pubblicazione: (2025)

Unifying Watermarking via Dimension-Aware Mapping
di: Meng, Jiale, et al.
Pubblicazione: (2026)

TRACE: Structure-Aware Character Encoding for Robust and Generalizable Document Watermarking
di: Meng, Jiale, et al.
Pubblicazione: (2026)

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
di: Hu, Runyi, et al.
Pubblicazione: (2024)

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
di: Hu, Runyi, et al.
Pubblicazione: (2025)

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution
di: Hu, Runyi, et al.
Pubblicazione: (2024)

SAME: Sample Reconstruction against Model Extraction Attacks
di: Xie, Yi, et al.
Pubblicazione: (2023)

Reinforcement Learning Enhanced LLMs: A Survey
di: Wang, Shuhe, et al.
Pubblicazione: (2024)

TorchGT: A Holistic System for Large-scale Graph Transformer Training
di: Zhang, Meng, et al.
Pubblicazione: (2024)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
di: Zhao, Shiqian, et al.
Pubblicazione: (2025)

InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management
di: Lin, Liangtao, et al.
Pubblicazione: (2025)

DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs
di: Luo, Lizhuo, et al.
Pubblicazione: (2026)

SOPRAG: Multi-view Graph Experts Retrieval for Industrial Standard Operating Procedures
di: Lin, Liangtao, et al.
Pubblicazione: (2026)

Instruction Tuning for Large Language Models: A Survey
di: Zhang, Shengyu, et al.
Pubblicazione: (2023)

LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
di: Li, Runyi, et al.
Pubblicazione: (2025)

Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
di: Li, Guanlin, et al.
Pubblicazione: (2025)

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution
di: Zhang, Yechao, et al.
Pubblicazione: (2026)

Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers
di: Nguyen, Viet-Anh, et al.
Pubblicazione: (2025)

SPPO:Efficient Long-sequence LLM Training via Adaptive Sequence Pipeline Parallel Offloading
di: Chen, Qiaoling, et al.
Pubblicazione: (2025)

Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack
di: Han, Xingshuo, et al.
Pubblicazione: (2024)

Efficient Fuzzy Private Set Intersection from Secret-shared OPRF
di: Yang, Xinpeng, et al.
Pubblicazione: (2026)

Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving
di: Gao, Wei, et al.
Pubblicazione: (2025)

PromptTuner: SLO-Aware Elastic System for LLM Prompt Tuning
di: Gao, Wei, et al.
Pubblicazione: (2026)

CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control
di: Chen, Qiaoling, et al.
Pubblicazione: (2026)

SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference
di: Zhang, Ziyang, et al.
Pubblicazione: (2026)

Iterative Inference-time Scaling with Adaptive Frequency Steering for Image Super-Resolution
di: Zhang, Hexin, et al.
Pubblicazione: (2025)

Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
di: Zhu, Dongxuan, et al.
Pubblicazione: (2026)

Robust and Reversible Thermal/Electro‐Responsive Supramolecular Polymeric Adhesives via Synergistic Hydrogen‐Bonds and Ionic Junctions
di: Qizhe Deng, et al.
Pubblicazione: (2024)

Robust and Reversible Thermal/Electro‐Responsive Supramolecular Polymeric Adhesives via Synergistic Hydrogen‐Bonds and Ionic Junctions
di: Qizhe Deng, et al.
Pubblicazione: (2024)

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
di: Cho, Seonglae, et al.
Pubblicazione: (2025)

The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features
di: Ferrao, Jeremias, et al.
Pubblicazione: (2025)

Interpretable LLM Guardrails via Sparse Representation Steering
di: He, Zeqing, et al.
Pubblicazione: (2025)

TouchGuide: Inference-Time Steering of Visuomotor Policies via Touch Guidance
di: Zhang, Zhemeng, et al.
Pubblicazione: (2026)

Semantic-Aware Scheduling for GPU Clusters with Large Language Models
di: Wang, Zerui, et al.
Pubblicazione: (2025)

InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
di: Tong, Meng, et al.
Pubblicazione: (2023)

FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering
di: Ding, Zikang, et al.
Pubblicazione: (2026)

SteerRM: Debiasing Reward Models via Sparse Autoencoders
di: Sun, Mengyuan, et al.
Pubblicazione: (2026)

Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning
di: Gao, Guanyu, et al.
Pubblicazione: (2019)

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners
di: Ng, Wen Zheng Terence, et al.
Pubblicazione: (2025)