Image de couverture de livre

From Shallow to Deep: Pinning Semantic Intent via Causal GRPO

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhou, Shuyi, Song, Zeen, Qiang, Wenwen, Sun, Jiyan, Zhou, Yao, Liu, Yinlong, Ma, Wei
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction
par: Song, Ruike, et autres
Publié: (2025)

Group Causal Policy Optimization for Post-Training Large Language Models
par: Gu, Ziyin, et autres
Publié: (2025)

Beyond All-to-All: Causal-Aligned Transformer with Dynamic Structure Learning for Multivariate Time Series Forecasting
par: Zhang, Xingyu, et autres
Publié: (2025)

Adaptive Uncertainty-Aware Tree Search for Robust Reasoning
par: Song, Zeen, et autres
Publié: (2026)

On the Generalization and Causal Explanation in Self-Supervised Learning
par: Qiang, Wenwen, et autres
Publié: (2024)

On the Out-of-Distribution Generalization of Self-Supervised Learning
par: Qiang, Wenwen, et autres
Publié: (2025)

Reward Model Generalization for Compute-Aware Test-Time Reasoning
par: Song, Zeen, et autres
Publié: (2025)

Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs
par: Wang, Jingyao, et autres
Publié: (2025)

Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs
par: Zhou, Yao, et autres
Publié: (2026)

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs
par: Zhang, Xingyu, et autres
Publié: (2026)

Hacking Task Confounder in Meta-Learning
par: Wang, Jingyao, et autres
Publié: (2023)

Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecasting
par: Zhang, Xingyu, et autres
Publié: (2024)

LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
par: Lai, Yao, et autres
Publié: (2026)

EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
par: Yu, Song, et autres
Publié: (2026)

From Intent to Evidence: A Categorical Approach for Structural Evaluation of Deep Research Agents
par: Liu, Shuoling, et autres
Publié: (2026)

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
par: Wang, Jingyao, et autres
Publié: (2026)

When Missing Becomes Structure: Intent-Preserving Policy Completion from Financial KOL Discourse
par: Liu, Yuncong, et autres
Publié: (2026)

dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models
par: Wan, Zhengyan, et autres
Publié: (2026)

Towards the Causal Complete Cause of Multi-Modal Representation Learning
par: Wang, Jingyao, et autres
Publié: (2024)

Tagged for Direction: Pinning Down Causal Edge Directions with Precision
par: Busch, Florian Peter, et autres
Publié: (2025)

Make Deep Networks Shallow Again
par: Bermeitinger, Bernhard, et autres
Publié: (2023)

How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning
par: Tian, Minghao, et autres
Publié: (2026)

Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
par: Wang, Liang, et autres
Publié: (2024)

Learning Polyhedral Conformal Sets for Robust Optimization
par: Chen, Shuyi, et autres
Publié: (2026)

Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
par: Zhang, Yanan, et autres
Publié: (2024)

Deep Minds and Shallow Probes
par: Lee, Su Hyeong, et autres
Publié: (2026)

Event-CausNet: Unlocking Causal Knowledge from Text with Large Language Models for Reliable Spatio-Temporal Forecasting
par: Niu, Luyao, et autres
Publié: (2025)

A Survey of Deep Causal Models and Their Industrial Applications
par: Li, Zongyu, et autres
Publié: (2022)

Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation
par: Liu, Wenzhang, et autres
Publié: (2025)

SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
par: Zheng, Zhi, et autres
Publié: (2025)

Drug Synergy Prediction via Residual Graph Isomorphism Networks and Attention Mechanisms
par: Song, Jiyan, et autres
Publié: (2026)

Lean Finder: Semantic Search for Mathlib That Understands User Intents
par: Lu, Jialin, et autres
Publié: (2025)

A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation
par: Song, Xinran, et autres
Publié: (2025)

AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
par: Yari, Amir Hossein, et autres
Publié: (2026)

Taming Extreme Tokens: Covariance-Aware GRPO with Gaussian-Kernel Advantage Reweighting
par: Wang, Cheng, et autres
Publié: (2026)

Advances in GRPO for Generation Models: A Survey
par: Liu, Zexiang, et autres
Publié: (2026)

Efficient Causal Structure Learning via Modular Subgraph Integration
par: Sun, Haixiang, et autres
Publié: (2026)

GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
par: Xu, Yanchen, et autres
Publié: (2025)

FedGRPO: Privately Optimizing Foundation Models with Group-Relative Rewards from Domain Client
par: Zhu, Gongxi, et autres
Publié: (2026)

Prepare Before You Act: Learning From Humans to Rearrange Initial States
par: Dai, Yinlong, et autres
Publié: (2025)