:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Ming, Li, Yanhong, Li, Ziyue, Zhou, Tianyi
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	https://arxiv.org/abs/2504.10766
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
por: Li, Ming, et al.
Publicado: (2024)

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning
por: Li, Ming, et al.
Publicado: (2024)

RuleR: Improving LLM Controllability by Rule-based Data Recycling
por: Li, Ming, et al.
Publicado: (2024)

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?
por: Fan, Chenrui, et al.
Publicado: (2025)

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
por: Zhao, Chengshuai, et al.
Publicado: (2025)

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
por: Li, Ming, et al.
Publicado: (2025)

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding
por: Li, Ming, et al.
Publicado: (2025)

Influential Language Data Selection via Gradient Trajectory Pursuit
por: Deng, Zhiwei, et al.
Publicado: (2024)

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness
por: Liang, Yijun, et al.
Publicado: (2025)

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
por: Yuan, Zhihang, et al.
Publicado: (2026)

Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient
por: Li, Changming, et al.
Publicado: (2026)

How to Train Data-Efficient LLMs
por: Sachdeva, Noveen, et al.
Publicado: (2024)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
por: Tang, Yao, et al.
Publicado: (2026)

BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
por: Zou, Bo, et al.
Publicado: (2026)

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements
por: Li, Ming, et al.
Publicado: (2024)

GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
por: Bai, Yuyang, et al.
Publicado: (2026)

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
por: Zhang, Jipeng, et al.
Publicado: (2024)

Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
por: Chan, Willy, et al.
Publicado: (2025)

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification
por: Guo, Yiju, et al.
Publicado: (2026)

Reinforcement Learning on Pre-Training Data
por: Li, Siheng, et al.
Publicado: (2025)

Reframing Data Value for Large Language Models Through the Lens of Plausibility
por: Rammal, Mohamad Rida, et al.
Publicado: (2024)

Learning to Reason Efficiently with A* Post-Training
por: Opedal, Andreas, et al.
Publicado: (2026)

Data Efficacy for Language Model Training
por: Dai, Yalun, et al.
Publicado: (2025)

KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning
por: Xu, Hongling, et al.
Publicado: (2025)

Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale
por: Zhou, Fan, et al.
Publicado: (2024)

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage
por: Hu, Junhao, et al.
Publicado: (2026)

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
por: Chen, Peter, et al.
Publicado: (2025)

ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
por: Yang, Zonghan, et al.
Publicado: (2024)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
por: Du, Hongzhe, et al.
Publicado: (2025)

Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents
por: Li, Xirui, et al.
Publicado: (2026)

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data
por: Wang, Yejie, et al.
Publicado: (2024)

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
por: Li, Ming, et al.
Publicado: (2025)

Can Post-Training Transform LLMs into Causal Reasoners?
por: Chen, Junqi, et al.
Publicado: (2026)

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources
por: Nguyen, Huu, et al.
Publicado: (2025)

The Limits of Preference Data for Post-Training
por: Zhao, Eric, et al.
Publicado: (2025)

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
por: Jung, Jaehun, et al.
Publicado: (2025)

How to Synthesize Text Data without Model Collapse?
por: Zhu, Xuekai, et al.
Publicado: (2024)

Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?
por: Yin, Yutong, et al.
Publicado: (2025)

Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning
por: Li, Xiaochuan, et al.
Publicado: (2024)

Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language Models
por: Gu, Xiaojie, et al.
Publicado: (2026)