Cover Image

Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Kounianhua, Liu, Jianxing, Zhang, Kangning, Jiao, Wenxiang, Lu, Yuan, Jin, Jiarui, Liu, Weiwen, Yu, Yong, Zhang, Weinan
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls
by: Zhang, Kangning, et al.
Published: (2025)

LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation
by: Chen, Jizheng, et al.
Published: (2026)

MMSkills: Towards Multimodal Skills for General Visual Agents
by: Zhang, Kangning, et al.
Published: (2026)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
by: Weng, Zixuan, et al.
Published: (2026)

D2K: Turning Historical Data into Retrievable Knowledge for Recommender Systems
by: Qin, Jiarui, et al.
Published: (2024)

FINED: Feed Instance-Wise Information Need with Essential and Disentangled Parametric Knowledge from the Past
by: Du, Kounianhua, et al.
Published: (2024)

DREAM: A Dual Representation Learning Model for Multimodal Recommendation
by: Zhang, Kangning, et al.
Published: (2024)

NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debugging
by: Zhang, Weiming, et al.
Published: (2025)

Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
by: Du, Kounianhua, et al.
Published: (2025)

SoDA: An Efficient Interaction Paradigm for the Agentic Web
by: Cui, Zicai, et al.
Published: (2025)

Learning ID-free Item Representation with Token Crossing for Multimodal Recommendation
by: Zhang, Kangning, et al.
Published: (2024)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
by: Li, Yichen, et al.
Published: (2025)

APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training
by: Qin, Jiarui, et al.
Published: (2025)

Agentic Information Retrieval
by: Zhang, Weinan, et al.
Published: (2024)

ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
by: Huang, Junjie, et al.
Published: (2026)

Learning Structure and Knowledge Aware Representation with Large Language Models for Concept Recommendation
by: Li, Qingyao, et al.
Published: (2024)

AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
by: Li, Qingyao, et al.
Published: (2026)

Guided Profile Generation Improves Personalization with LLMs
by: Zhang, Jiarui
Published: (2024)

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
by: Fu, Lingyue, et al.
Published: (2025)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
by: Pan, Xinglin, et al.
Published: (2025)

AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
by: Jin, Jiarui, et al.
Published: (2026)

ELCoRec: Enhance Language Understanding with Co-Propagation of Numerical and Categorical Features for Recommendation
by: Chen, Jizheng, et al.
Published: (2024)

DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control
by: Du, Shiyan, et al.
Published: (2026)

AlignRec: Aligning and Training in Multimodal Recommendations
by: Liu, Yifan, et al.
Published: (2024)

SkillPager: Query-Adaptive Intra-Skill Navigation via Semantic Node Retrieval
by: Cui, Zicai, et al.
Published: (2026)

Context Steering: Controllable Personalization at Inference Time
by: He, Jerry Zhi-Yang, et al.
Published: (2024)

Scenario-Adaptive Fine-Grained Personalization Network: Tailoring User Behavior Representation to the Scenario Context
by: Zhang, Moyu, et al.
Published: (2024)

Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
by: Li, Ning, et al.
Published: (2025)

Unleashing the Potential of Multi-Channel Fusion in Retrieval for Personalized Recommendations
by: Huang, Junjie, et al.
Published: (2024)

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
by: Li, Qingyao, et al.
Published: (2024)

Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
by: Zhu, Jiachen, et al.
Published: (2025)

SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
by: Guan, Hao, et al.
Published: (2026)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
by: Jin, Zehao, et al.
Published: (2026)

Fine-Grained Activation Steering: Steering Less, Achieving More
by: Feng, Zijian, et al.
Published: (2026)

Fast, Slow, and Tool-augmented Thinking for LLMs: A Review
by: Jia, Xinda, et al.
Published: (2025)

Fine-Grained Urban Flow Inference with Multi-scale Representation Learning
by: Yuan, Shilu, et al.
Published: (2024)

Why Not Together? A Multiple-Round Recommender System for Queries and Items
by: Jin, Jiarui, et al.
Published: (2024)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
by: Lv, Hang, et al.
Published: (2025)

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
by: Qi, Siyuan, et al.
Published: (2026)

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
by: Huang, Jianuo, et al.
Published: (2025)