Copertina

GRACE: Gradient-aligned Reasoning Data Curation for Efficient Post-training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Junjie, Wang, Ziao, Ma, NingXuan, Ma, Jianghong, Zhang, Xiaofeng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Uncovering Intrinsic Capabilities: A Paradigm for Data Curation in Vision-Language Models
di: Li, Junjie, et al.
Pubblicazione: (2025)

GiVE: Guiding Visual Encoder to Perceive Overlooked Information
di: Li, Junjie, et al.
Pubblicazione: (2024)

MLGIB: Multi-Label Graph Information Bottleneck for Expressive and Robust Message Passing
di: Wu, Chaokai, et al.
Pubblicazione: (2026)

Does Faithfulness Conflict with Plausibility? An Empirical Study in Explainable AI across NLP Tasks
di: Lu, Xiaolei, et al.
Pubblicazione: (2024)

GRACE: Discriminator-Guided Chain-of-Thought Reasoning
di: Khalifa, Muhammad, et al.
Pubblicazione: (2023)

On Data Synthesis and Post-training for Visual Abstract Reasoning
di: Zhu, Ke, et al.
Pubblicazione: (2025)

Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks
di: Zhang, Jingmao, et al.
Pubblicazione: (2025)

Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure
di: Zhang, Jingmao, et al.
Pubblicazione: (2025)

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
di: Wu, Chenghao, et al.
Pubblicazione: (2025)

IDVT: Interest-aware Denoising and View-guided Tuning for Social Recommendation
di: Yang, Dezhao, et al.
Pubblicazione: (2023)

CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
di: Wang, Shaobo, et al.
Pubblicazione: (2025)

DCA-Bench: A Benchmark for Dataset Curation Agents
di: Huang, Benhao, et al.
Pubblicazione: (2024)

DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization
di: Xie, Xuan, et al.
Pubblicazione: (2025)

What Matters in Data Curation for Multimodal Reasoning? Insights from the DCVLR Challenge
di: Shin, Yosub, et al.
Pubblicazione: (2026)

Layer-Aware Influence for Online Data Valuation Estimation
di: Yang, Ziao, et al.
Pubblicazione: (2025)

RADAR: Accelerating Large Language Model Inference With RL-Based Dynamic Draft Trees
di: Ma, Junjie, et al.
Pubblicazione: (2025)

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
di: Li, Ming, et al.
Pubblicazione: (2025)

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
di: Liu, Xiaoqun, et al.
Pubblicazione: (2024)

The Impact of Post-training on Data Contamination
di: Kocyigit, Muhammed Yusuf, et al.
Pubblicazione: (2026)

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
di: Zhang, Yuxiang, et al.
Pubblicazione: (2025)

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
di: Xuan, Richmond Sin Jing, et al.
Pubblicazione: (2026)

Efficient Post-training Quantization with FP8 Formats
di: Shen, Haihao, et al.
Pubblicazione: (2023)

Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model
di: Li, Yanhao, et al.
Pubblicazione: (2025)

Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models
di: Wu, Hui, et al.
Pubblicazione: (2026)

Post-training for Efficient Communication via Convention Formation
di: Hua, Yilun, et al.
Pubblicazione: (2025)

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning
di: Wu, Mingze, et al.
Pubblicazione: (2026)

Efficient Reasoning Models: A Survey
di: Feng, Sicheng, et al.
Pubblicazione: (2025)

CuraLight: Debate-Guided Data Curation for LLM-Centered Traffic Signal Control
di: Guo, Qing, et al.
Pubblicazione: (2026)

Neuro-Symbolic Data Generation for Math Reasoning
di: Li, Zenan, et al.
Pubblicazione: (2024)

Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning
di: Wan, Qian, et al.
Pubblicazione: (2026)

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View
di: Qi, Jianyu, et al.
Pubblicazione: (2025)

GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
di: Tang, Tianhao, et al.
Pubblicazione: (2026)

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
di: Liang, Zhenwen, et al.
Pubblicazione: (2025)

Efficient Reasoning with Balanced Thinking
di: Li, Yulin, et al.
Pubblicazione: (2026)

Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
di: Zhang, Yunjian, et al.
Pubblicazione: (2026)

Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation
di: Zhang, Xiyang, et al.
Pubblicazione: (2026)

DocMamba: Efficient Document Pre-training with State Space Model
di: Hu, Pengfei, et al.
Pubblicazione: (2024)

On-Policy Supervised Fine-Tuning for Efficient Reasoning
di: Zhao, Anhao, et al.
Pubblicazione: (2026)

Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimes
di: Seedat, Nabeel, et al.
Pubblicazione: (2023)

CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations
di: Li, Xiping, et al.
Pubblicazione: (2026)