Cover Image

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Ruixiang, Wen, Yuntao, Zhou, Silin, Shi, Ke, Wang, Yifan, Le, Ran, An, Zhenwei, Chen, Zongchao, Yang, Chen, Peng, Guangyue, Jia, Yiming, Wang, Dongsheng, Zhang, Tao, Chen, Lisi, Song, Yang, Gao, Shen, Shang, Shuo
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions
by: Feng, Ruixiang, et al.
Published: (2025)

Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
by: Yang, Chen, et al.
Published: (2026)

Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
by: Peng, Guangyue, et al.
Published: (2026)

From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
by: Zhou, Silin, et al.
Published: (2026)

Region-Point Joint Representation for Effective Trajectory Similarity Learning
by: Long, Hao, et al.
Published: (2025)

ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset
by: Yang, Chen, et al.
Published: (2025)

CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis
by: Feng, Ruixiang, et al.
Published: (2025)

RED: Effective Trajectory Representation Learning with Comprehensive Information
by: Zhou, Silin, et al.
Published: (2024)

Grid and Road Expressions Are Complementary for Trajectory Representation Learning
by: Zhou, Silin, et al.
Published: (2024)

Nanbeige4-3B Technical Report: Exploring the Frontier of Small Language Models
by: Yang, Chen, et al.
Published: (2025)

Blurred Encoding for Trajectory Representation Learning
by: Zhou, Silin, et al.
Published: (2025)

How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors
by: Xu, Yifan, et al.
Published: (2026)

DRE: Generating Recommendation Explanations by Aligning Large Language Models at Data-level
by: Gao, Shen, et al.
Published: (2024)

PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization
by: Zuo, Dongsheng, et al.
Published: (2025)

Efficient Model-Agnostic Continual Learning for Next POI Recommendation
by: Wang, Chenhao, et al.
Published: (2025)

TOOL4POI: A Tool-Augmented LLM Framework for Next POI Recommendation
by: Wang, Dongsheng, et al.
Published: (2025)

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
by: Luo, Qin-Wen, et al.
Published: (2026)

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
by: Liu, Zhenghao, et al.
Published: (2026)

APAO: Adaptive Prefix-Aware Optimization for Generative Recommendation
by: Yu, Yuanqing, et al.
Published: (2026)

PACE: Prune-And-Compress Ensemble Models
by: Akkerman, Fabian, et al.
Published: (2026)

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
by: Wang, Zhuoyu, et al.
Published: (2026)

Hypothesis testing under uniform-block covariance structures
by: Yang, Yifan, et al.
Published: (2023)

Emotion-Aware Prefix: Towards Explicit Emotion Control in Voice Conversion Models
by: Yang, Haoyuan, et al.
Published: (2026)

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot
by: Jiang, Ruixiang, et al.
Published: (2025)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
by: Sun, Yiliu, et al.
Published: (2025)

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
by: Wang, Haonan, et al.
Published: (2025)

Covariance Matrix Estimation for High-Throughput Biomedical Data with Interconnected Communities
by: Yang, Yifan, et al.
Published: (2023)

RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs
by: Fernandez, Nigel, et al.
Published: (2025)

Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
by: Chen, Mingrui, et al.
Published: (2025)

Generative Next POI Recommendation with Semantic ID
by: Wang, Dongsheng, et al.
Published: (2025)

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
by: Wu, Yifan, et al.
Published: (2025)

PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
by: Yu, Chenglei, et al.
Published: (2026)

PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
by: Chen, Mengzhao, et al.
Published: (2024)

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
by: Ji, Ke, et al.
Published: (2025)

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
by: Chen, Shuang, et al.
Published: (2025)

Photolabile ortho‐Nitro‐Benzyl Carbonate as a Permanent Hydroxyl Protecting Group for the Synthesis of Digalactosyl Diacylglycerol
by: Jibin Zheng, et al.
Published: (2024)

Explainable Session-based Recommendation via Path Reasoning
by: Cao, Yang, et al.
Published: (2024)

Quantitative Representation of Scenario Difficulty for Autonomous Driving Based on Adversarial Policy Search
by: Yang, Shuo, et al.
Published: (2024)

Modeling Interconnected Modules in Multivariate Outcomes: Evaluating the Impact of Alcohol Intake on Plasma Metabolomics
by: Yang, Yifan, et al.
Published: (2024)

DAST: Difficulty-Aware Self-Training on Large Language Models
by: Xue, Boyang, et al.
Published: (2025)