Imagen de Portada

APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chang, Kaiyan, Zhu, Chenwei, Luo, Yingfeng, Huo, Yifu, Wang, Chenglong, Liu, Xiaoqian, He, Qiaozhi, Xiao, Tong, Yu, Zhengtao, Zhu, Jingbo
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Efficient Prompting Methods for Large Language Models: A Survey
por: Chang, Kaiyan, et al.
Publicado: (2024)

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
por: Huo, Yifu, et al.
Publicado: (2026)

GRAM: A Generative Foundation Reward Model for Reward Generalization
por: Wang, Chenglong, et al.
Publicado: (2025)

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
por: Chang, Kaiyan, et al.
Publicado: (2025)

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning
por: Mao, Ruixiang, et al.
Publicado: (2026)

Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
por: Wang, Chenglong, et al.
Publicado: (2025)

MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning
por: Wang, Chenglong, et al.
Publicado: (2026)

Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models
por: Mu, Yongyu, et al.
Publicado: (2025)

RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data
por: Wang, Chenglong, et al.
Publicado: (2024)

RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
por: Luo, Yingfeng, et al.
Publicado: (2026)

LRHP: Learning Representations for Human Preferences via Preference Pairs
por: Wang, Chenglong, et al.
Publicado: (2024)

GRAM-R$^2$: Self-Training Generative Foundation Reward Models for Reward Reasoning
por: Wang, Chenglong, et al.
Publicado: (2025)

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
por: Wang, Chenglong, et al.
Publicado: (2026)

One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
por: Luo, Yingfeng, et al.
Publicado: (2025)

Hybrid Alignment Training for Large Language Models
por: Wang, Chenglong, et al.
Publicado: (2024)

Recent Advances in End-to-End Simultaneous Speech Translation
por: Liu, Xiaoqian, et al.
Publicado: (2024)

Prior Constraints-based Reward Model Training for Aligning Large Language Models
por: Zhou, Hang, et al.
Publicado: (2024)

Learning Evaluation Models from Large Language Models for Sequence Generation
por: Wang, Chenglong, et al.
Publicado: (2023)

EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation
por: Niu, Miaohe, et al.
Publicado: (2026)

MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
por: Wang, Chenglong, et al.
Publicado: (2025)

ChartAnchor: Chart Grounding with Structural-Semantic Fidelity
por: Li, Xinhang, et al.
Publicado: (2025)

LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination
por: Zhu, Ziming, et al.
Publicado: (2025)

Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
por: Liu, Xin, et al.
Publicado: (2025)

Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
por: Luo, Yingfeng, et al.
Publicado: (2025)

Foundations of Large Language Models
por: Xiao, Tong, et al.
Publicado: (2025)

Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning
por: Hong, Jialiang, et al.
Publicado: (2025)

FLEXI: Benchmarking Full-duplex Human-LLM Speech Interaction
por: Ge, Yuan, et al.
Publicado: (2025)

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
por: Luo, Yingfeng, et al.
Publicado: (2025)

DaPT: A Dual-Path Framework for Multilingual Multi-hop Question Answering
por: Wang, Yilin, et al.
Publicado: (2026)

Cross-layer Attention Sharing for Pre-trained Large Language Models
por: Mu, Yongyu, et al.
Publicado: (2024)

HEAL: A Hypothesis-Based Preference-Aware Analysis Framework
por: Huo, Yifu, et al.
Publicado: (2025)

Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
por: Shan, Weiqiao, et al.
Publicado: (2024)

MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
por: Wang, Jianjin, et al.
Publicado: (2025)

On the Emotion Understanding of Synthesized Speech
por: Ge, Yuan, et al.
Publicado: (2026)

SUBQRAG: Sub-Question Driven Dynamic Graph RAG
por: Li, Jiaoyang, et al.
Publicado: (2025)

SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
por: Ge, Yuan, et al.
Publicado: (2025)

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
por: Shan, Weiqiao, et al.
Publicado: (2025)

Exploring Scaling Laws for Local SGD in Large Language Model Training
por: He, Qiaozhi, et al.
Publicado: (2024)

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
por: Liu, Xinyu, et al.
Publicado: (2026)

HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation
por: Liu, Changkun, et al.
Publicado: (2024)