Copertina

Round-trip Reinforcement Learning: Self-Consistent Training for Better Chemical LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kong, Lecheng, Wang, Xiyuan, Chen, Yixin, Zhang, Muhan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

One for All: Towards Training One Graph Model for All Classification Tasks
di: Liu, Hao, et al.
Pubblicazione: (2023)

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction
di: Wang, Juntong, et al.
Pubblicazione: (2025)

Using Random Noise Equivariantly to Boost Graph Neural Networks Universally
di: Wang, Xiyuan, et al.
Pubblicazione: (2025)

TAGLAS: An atlas of text-attributed graph datasets in the era of large graph and language models
di: Feng, Jiarui, et al.
Pubblicazione: (2024)

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman
di: Feng, Jiarui, et al.
Pubblicazione: (2023)

GOFA: A Generative One-For-All Model for Joint Graph Language Modeling
di: Kong, Lecheng, et al.
Pubblicazione: (2024)

Graph as Point Set
di: Wang, Xiyuan, et al.
Pubblicazione: (2024)

Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
di: Wang, Xiyuan, et al.
Pubblicazione: (2023)

Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
di: Liu, Yewei, et al.
Pubblicazione: (2025)

On the Completeness of Invariant Geometric Deep Learning Models
di: Li, Zian, et al.
Pubblicazione: (2024)

Is Distance Matrix Enough for Geometric Deep Learning?
di: Li, Zian, et al.
Pubblicazione: (2023)

Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
di: Zhou, Cai, et al.
Pubblicazione: (2024)

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
di: Zhou, Junru, et al.
Pubblicazione: (2023)

Neural Common Neighbor with Completion for Link Prediction
di: Wang, Xiyuan, et al.
Pubblicazione: (2023)

RTMol: Rethinking Molecule-text Alignment in a Round-trip View
di: Chen, Letian, et al.
Pubblicazione: (2025)

Reconsidering the Performance of GAE in Link Prediction
di: Ma, Weishuo, et al.
Pubblicazione: (2024)

Do Graph Diffusion Models Accurately Capture and Generate Substructure Distributions?
di: Wang, Xiyuan, et al.
Pubblicazione: (2025)

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
di: Ma, Weishuo, et al.
Pubblicazione: (2025)

SPGNN: Recognizing Salient Subgraph Patterns via Enhanced Graph Convolution and Pooling
di: Dong, Zehao, et al.
Pubblicazione: (2024)

Efficient Neural Common Neighbor for Temporal Graph Link Prediction
di: Zhang, Xiaohui, et al.
Pubblicazione: (2024)

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors
di: Zhou, Junru, et al.
Pubblicazione: (2024)

Geometric Representation Condition Improves Equivariant Molecule Generation
di: Li, Zian, et al.
Pubblicazione: (2024)

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling
di: Kang, Shijia, et al.
Pubblicazione: (2025)

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
di: Liu, Taowen, et al.
Pubblicazione: (2025)

Toward Better Geometric Representations for Molecule Generative Models
di: Yan, Shaoheng, et al.
Pubblicazione: (2026)

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning
di: Zhang, Haozhen, et al.
Pubblicazione: (2025)

CktGNN: Circuit Graph Neural Network for Electronic Design Automation
di: Dong, Zehao, et al.
Pubblicazione: (2023)

Dynamic Mixture-of-Experts for Incremental Graph Learning
di: Kong, Lecheng, et al.
Pubblicazione: (2025)

Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2025)

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
di: Ma, Guozheng, et al.
Pubblicazione: (2023)

Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
di: Hu, Zijing, et al.
Pubblicazione: (2025)

Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation
di: Lee, Jaehyeok, et al.
Pubblicazione: (2024)

S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
di: Ma, Ruotian, et al.
Pubblicazione: (2025)

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning
di: Liu, Huanyu, et al.
Pubblicazione: (2025)

GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
di: Wang, Juntong, et al.
Pubblicazione: (2026)

On Lexical Invariance on Multisets and Graphs
di: Zhang, Muhan
Pubblicazione: (2024)

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model
di: Yang, Haotong, et al.
Pubblicazione: (2024)

Griffin: Towards a Graph-Centric Relational Database Foundation Model
di: Wang, Yanbo, et al.
Pubblicazione: (2025)

Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
di: Zhao, Ji, et al.
Pubblicazione: (2026)

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning
di: Luo, Zhi, et al.
Pubblicazione: (2024)