Cover Image

Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Jillian, Zhou, Dylan, Shukla, Vinay, Yang, Yang, Ruan, Junrui, Lin, Shuhuai, Zou, Wenfei, Liu, Yinxiao, Lakshmanan, Karthik
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
by: Zhang, Shutong, et al.
Published: (2026)

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
by: Tian, Xinyu, et al.
Published: (2025)

Agentic-R1: Distilled Dual-Strategy Reasoning
by: Du, Weihua, et al.
Published: (2025)

NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
by: Li, Yang, et al.
Published: (2025)

Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
by: Yang, Penghui, et al.
Published: (2024)

Beyond Imitation: Learning Key Reasoning Steps from Dual Chain-of-Thoughts in Reasoning Distillation
by: Dai, Chengwei, et al.
Published: (2024)

Improving In-Context Learning with Reasoning Distillation
by: Sadeq, Nafis, et al.
Published: (2025)

Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
by: Gu, Jing, et al.
Published: (2026)

Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention
by: Lin, Wenye, et al.
Published: (2026)

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
by: Wang, Yuchi, et al.
Published: (2025)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
by: Chegini, Atoosa, et al.
Published: (2025)

Reasoning Compression with Mixed-Policy Distillation
by: Yang, Han, et al.
Published: (2026)

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

Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning
by: Kim, Minwu, et al.
Published: (2025)

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation
by: Zhang, Yong, et al.
Published: (2025)

Learning Only with Images: Visual Reinforcement Learning with Reasoning, Rendering, and Visual Feedback
by: Chen, Yang, et al.
Published: (2025)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
by: Xu, Xin, et al.
Published: (2025)

Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs
by: Ranasinghe, Kanchana, et al.
Published: (2024)

Improve Mathematical Reasoning in Language Models by Automated Process Supervision
by: Luo, Liangchen, et al.
Published: (2024)

Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
by: Shao, Shitong, et al.
Published: (2023)

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
by: Han, Simeng, et al.
Published: (2024)

Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
by: Kim, Minsang, et al.
Published: (2026)

Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models
by: Zheng, Chen, et al.
Published: (2025)

Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
by: Wu, Tong, et al.
Published: (2025)

Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
by: Phan, Phuc, et al.
Published: (2024)

Structural Rationale Distillation via Reasoning Space Compression
by: Yang, Jialin, et al.
Published: (2026)

Effective Distillation of Table-based Reasoning Ability from LLMs
by: Yang, Bohao, et al.
Published: (2023)

TED: Training-Free Experience Distillation for Multimodal Reasoning
by: Yuan, Shuozhi, et al.
Published: (2026)

Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge Distillation
by: Hong, Zong-Wei, et al.
Published: (2024)

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning
by: Zou, Jiaru, et al.
Published: (2025)

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
by: Wei, Yishu, et al.
Published: (2026)

Reasoning Distillation and Structural Alignment for Improved Code Generation
by: Jalilifard, Amir, et al.
Published: (2025)

Improve Student's Reasoning Generalizability through Cascading Decomposed CoTs Distillation
by: Dai, Chengwei, et al.
Published: (2024)

Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning
by: Yang, Songyuan, et al.
Published: (2026)

Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
by: Li, Yicong, et al.
Published: (2024)

SMAGDi: Socratic Multi Agent Interaction Graph Distillation for Efficient High Accuracy Reasoning
by: Aluru, Aayush, et al.
Published: (2025)

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
by: Cao, Lang, et al.
Published: (2024)

Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning
by: Park, Chan Young, et al.
Published: (2025)

Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
by: Zhao, Zhengyang, et al.
Published: (2026)

Visual Reasoning over Time Series via Multi-Agent System
by: Ruan, Weilin, et al.
Published: (2026)