Copertina

TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Lin, Zhao, Guangxiang, Jian, Xiaoqi, Wu, Yuhan, Lin, Weihong, Zhu, Yongfu, Shi, Qilong, Jia, Change, Yuan, Aomufei, Tian, Yuxuan, Zhang, Linglin, Wu, Jinzhu, Ran, Junfeng, Hu, Sai-er, Jiang, Zihan, Zhou, Junting, Liu, Wenrui, Xiao, Xusen, Cui, Bin, Yang, Tong, Zhang, Xiangzheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
di: Sun, Lin, et al.
Pubblicazione: (2025)

Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
di: Lin, Weihong, et al.
Pubblicazione: (2026)

Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
di: Zhao, Guangxiang, et al.
Pubblicazione: (2025)

Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
di: Zhu, Yongfu, et al.
Pubblicazione: (2025)

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
di: Zhao, Guangxiang, et al.
Pubblicazione: (2026)

BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning
di: Sun, Lin, et al.
Pubblicazione: (2026)

A Primer in Post-Training Reasoning Data: What We Know About How It Works
di: Li, Yaoming, et al.
Pubblicazione: (2026)

When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
di: Sun, Lin, et al.
Pubblicazione: (2026)

Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling
di: Ran, Junfeng, et al.
Pubblicazione: (2025)

Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought
di: Si, Jianfeng, et al.
Pubblicazione: (2026)

Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
di: Zhu, Dawei, et al.
Pubblicazione: (2025)

Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
di: Wang, Chenyang, et al.
Pubblicazione: (2025)

Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models
di: Li, Guo, et al.
Pubblicazione: (2025)

DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders
di: Hong, Susung, et al.
Pubblicazione: (2025)

UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking
di: Fu, Lingling, et al.
Pubblicazione: (2025)

Time‐Resolved Mapping of Interface Charge Transfer for Real‐Time Observation of Microscopic Chemical Reactions
di: Jinyang Zhang, et al.
Pubblicazione: (2026)

Time‐Resolved Mapping of Interface Charge Transfer for Real‐Time Observation of Microscopic Chemical Reactions
di: Jinyang Zhang, et al.
Pubblicazione: (2026)

TPMM-DPO: Trajectory-aware Preference-guided Model Merging for Iterative Direct Preference Optimization
di: Fu, Lingling, et al.
Pubblicazione: (2026)

LongAttn: Selecting Long-context Training Data via Token-level Attention
di: Wu, Longyun, et al.
Pubblicazione: (2025)

Exercise Attenuates Skeletal Muscle Atrophy in Senescent SAMP8 Mice: Metabolic Insights from NMR-Based Metabolomics.
di: Wu, Wenfang, et al.
Pubblicazione: (2025)

Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
di: Si, Jianfeng, et al.
Pubblicazione: (2025)

A remark on $Λ^2$-enlargeable manifolds
di: Su, Guangxiang
Pubblicazione: (2025)

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
di: Yuan, Aomufei, et al.
Pubblicazione: (2025)

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model
di: Chen, Jiali, et al.
Pubblicazione: (2025)

LookCloser: Frequency-aware Radiance Field for Tiny-Detail Scene
di: Zhang, Xiaoyu, et al.
Pubblicazione: (2025)

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
di: Zhang, Liang, et al.
Pubblicazione: (2024)

How to Weight Multitask Finetuning? Fast Previews via Bayesian Model-Merging
di: Maldonado, Hugo Monzón, et al.
Pubblicazione: (2024)

Risk of malignancy of cytologic categories and post‐biopsy clinical management of renal oncocytic neoplasms
di: Xiaoqi Lin
Pubblicazione: (2025)

Observer‐Based Finite‐Time Preview Control of Nonlinear Discrete‐Time Systems
di: Li Li, et al.
Pubblicazione: (2025)

The weak Galerkin finite element method for Stokes interface problems with curved interface
di: Yang, Lin, et al.
Pubblicazione: (2022)

Scalable Co-Clustering for Large-Scale Data through Dynamic Partitioning and Hierarchical Merging
di: Wu, Zihan, et al.
Pubblicazione: (2024)

DiFaR: Enhancing Multimodal Misinformation Detection with Diverse, Factual, and Relevant Rationales
di: Wan, Herun, et al.
Pubblicazione: (2025)

WizardMerge -- Save Us From Merging Without Any Clues
di: Zhang, Qingyu, et al.
Pubblicazione: (2024)

Nocturnal Hypoxemia and Daytime Sleepiness in Epilepsy With Obstructive Sleep Apnea‐Hypopnea Syndrome: A Case–Control Polysomnography Study
di: Meina Wu, et al.
Pubblicazione: (2025)

BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
di: Xie, Yuhan, et al.
Pubblicazione: (2026)

MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning
di: Liu, Siyuan, et al.
Pubblicazione: (2025)

The Immersed Discontinuous Galerkin Method for Elliptic Interface Problems
di: Yang, Lin, et al.
Pubblicazione: (2026)

The Immersed Skeletal Finite Element Method for Elliptic Interface Problems
di: Yang, Lin, et al.
Pubblicazione: (2024)

From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild
di: Zeng, Zhi, et al.
Pubblicazione: (2026)

Automated Lane Merging via Game Theory and Branch Model Predictive Control
di: Zhang, Luyao, et al.
Pubblicazione: (2023)