Copertina

On the Plasticity and Stability for Post-Training Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Qiang, Wenwen, Gu, Ziyin, Zhou, Jiahuan, Hu, Jie, Wang, Jingyao, Zheng, Changwen, Xiong, Hui
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Group Causal Policy Optimization for Post-Training Large Language Models
di: Gu, Ziyin, et al.
Pubblicazione: (2025)

CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models
di: Guo, Huijie, et al.
Pubblicazione: (2026)

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
di: Wang, Jingyao, et al.
Pubblicazione: (2026)

Rethinking Multi-Modal Learning from Gradient Uncertainty
di: Guo, Peizheng, et al.
Pubblicazione: (2025)

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
di: Wang, Jingyao, et al.
Pubblicazione: (2025)

Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning
di: Zhang, Jianqi, et al.
Pubblicazione: (2026)

On the Universality of Self-Supervised Learning
di: Qiang, Wenwen, et al.
Pubblicazione: (2024)

Rethinking Meta-Learning from a Learning Lens
di: Wang, Jingyao, et al.
Pubblicazione: (2024)

Towards Task Sampler Learning for Meta-Learning
di: Wang, Jingyao, et al.
Pubblicazione: (2023)

On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
di: Qiang, Wenwen, et al.
Pubblicazione: (2025)

On the Generalization and Causal Explanation in Self-Supervised Learning
di: Qiang, Wenwen, et al.
Pubblicazione: (2024)

Towards the Causal Complete Cause of Multi-Modal Representation Learning
di: Wang, Jingyao, et al.
Pubblicazione: (2024)

Neuromodulated Meta-Learning
di: Wang, Jingyao, et al.
Pubblicazione: (2024)

On the Out-of-Distribution Generalization of Self-Supervised Learning
di: Qiang, Wenwen, et al.
Pubblicazione: (2025)

Spatio-Temporal Fuzzy-oriented Multi-Modal Meta-Learning for Fine-grained Emotion Recognition
di: Wang, Jingyao, et al.
Pubblicazione: (2024)

Hacking Task Confounder in Meta-Learning
di: Wang, Jingyao, et al.
Pubblicazione: (2023)

AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design Anywhere
di: Wang, Jingyao, et al.
Pubblicazione: (2023)

Understanding Token-level Topological Structures in Transformer-based Time Series Forecasting
di: Zhang, Jianqi, et al.
Pubblicazione: (2024)

Exploring Transferability of Self-Supervised Learning by Task Conflict Calibration
di: Guo, Huijie, et al.
Pubblicazione: (2025)

A Generalized Learning Framework for Self-Supervised Contrastive Learning
di: Si, Lingyu, et al.
Pubblicazione: (2025)

Reward Model Generalization for Compute-Aware Test-Time Reasoning
di: Song, Zeen, et al.
Pubblicazione: (2025)

Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
di: Song, Fei, et al.
Pubblicazione: (2025)

PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
di: Guo, Peizheng, et al.
Pubblicazione: (2026)

Adaptive Uncertainty-Aware Tree Search for Robust Reasoning
di: Song, Zeen, et al.
Pubblicazione: (2026)

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs
di: Guo, Peizheng, et al.
Pubblicazione: (2025)

Enhancing Time Series Forecasting via Logic-Inspired Regularization
di: Zhang, Jianqi, et al.
Pubblicazione: (2025)

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs
di: Zhang, Xingyu, et al.
Pubblicazione: (2026)

Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
di: Zhang, Xingyu, et al.
Pubblicazione: (2025)

Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentation
di: Wang, Jingyao, et al.
Pubblicazione: (2025)

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
di: Zhang, Kaichen, et al.
Pubblicazione: (2025)

On the Evolution of Federated Post-Training Large Language Models: A Model Accessibility View
di: Guo, Tao, et al.
Pubblicazione: (2025)

GWT: Scalable Optimizer State Compression for Large Language Model Training
di: Wen, Ziqing, et al.
Pubblicazione: (2025)

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting
di: Zhang, Xingyu, et al.
Pubblicazione: (2024)

Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma
di: Wang, Ruiyu, et al.
Pubblicazione: (2025)

Scaling Laws for Post Training Quantized Large Language Models
di: Xu, Zifei, et al.
Pubblicazione: (2024)

Post Training Quantization of Large Language Models with Microscaling Formats
di: Sharify, Sayeh, et al.
Pubblicazione: (2024)

S-GRPO: Unified Post-Training for Large Vision-Language Models
di: Yan, Yuming, et al.
Pubblicazione: (2026)

Efficient Post-Training Pruning of Large Language Models with Statistical Correction
di: Yu, Peiqi, et al.
Pubblicazione: (2026)

AdaGC: Improving Training Stability for Large Language Model Pretraining
di: Wang, Guoxia, et al.
Pubblicazione: (2025)

Interventional Imbalanced Multi-Modal Representation Learning via $β$-Generalization Front-Door Criterion
di: Li, Yi, et al.
Pubblicazione: (2024)