Copertina

VeriGate: Verifier-Gated Step-Level Supervision for GRPO

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Agrawal, Aakriti, Liu, Minghui, Huang, Furong
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

GATES: Self-Distillation under Privileged Context with Consensus Gating
di: Stein, Alex, et al.
Pubblicazione: (2026)

Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2024)

GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
di: Wang, Jingyi, et al.
Pubblicazione: (2026)

EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
di: Agrawal, Aakriti, et al.
Pubblicazione: (2025)

PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
di: Panaitescu-Liess, Michael-Andrei, et al.
Pubblicazione: (2025)

GatedFWA: Linear Flash Windowed Attention with Gated Associative Memory
di: Liu, Jiaxu, et al.
Pubblicazione: (2025)

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
di: Ho, Sy-Tuyen, et al.
Pubblicazione: (2026)

FineGates: LLMs Finetuning with Compression using Stochastic Gates
di: Svirsky, Jonathan, et al.
Pubblicazione: (2024)

MAGIC: Multi-Step Advantage-Gated Causal Influence for Multi-agent Reinforcement Learning
di: Yu, Haohan, et al.
Pubblicazione: (2026)

Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification
di: Mroueh, Youssef
Pubblicazione: (2025)

SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms
di: Genet, Rémi, et al.
Pubblicazione: (2025)

Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
di: Nguyen, Huy, et al.
Pubblicazione: (2024)

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
di: Jia, Zeyu, et al.
Pubblicazione: (2025)

ArcGate: Adaptive Arctangent Gated Activation
di: Bhattacharya, Avik, et al.
Pubblicazione: (2026)

VeriThinker: Learning to Verify Makes Reasoning Model Efficient
di: Chen, Zigeng, et al.
Pubblicazione: (2025)

Gaussian Process-Gated Hierarchical Mixtures of Experts
di: Liu, Yuhao, et al.
Pubblicazione: (2023)

Uncertainty-Gated Generative Modeling
di: Gu, Xingrui, et al.
Pubblicazione: (2026)

Differential Gated Self-Attention
di: Lygizou, Elpiniki Maria, et al.
Pubblicazione: (2025)

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
di: Huang, Runhui, et al.
Pubblicazione: (2026)

WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning
di: Mundada, Gagan, et al.
Pubblicazione: (2026)

Expanded Gating Ranges Improve Activation Functions
di: Huang, Allen Hao
Pubblicazione: (2024)

Spectral Gating Networks
di: Zhang, Jusheng, et al.
Pubblicazione: (2026)

Gated-SwinRMT: Unifying Swin Windowed Attention with Retentive Manhattan Decay via Input-Dependent Gating
di: Maity, Dipan, et al.
Pubblicazione: (2026)

Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models
di: Lee, Seungjae, et al.
Pubblicazione: (2025)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
di: Ding, Mucong, et al.
Pubblicazione: (2024)

Masked Gated Linear Unit
di: Tajima, Yukito, et al.
Pubblicazione: (2025)

LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
di: Lai, Yao, et al.
Pubblicazione: (2026)

Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Function
di: Song, Qiuchen, et al.
Pubblicazione: (2025)

Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
di: Hu, Yuelin, et al.
Pubblicazione: (2026)

Light Differentiable Logic Gate Networks
di: Rüttgers, Lukas, et al.
Pubblicazione: (2025)

Gated Graph Attention Networks with Learnable Temperature
di: Ma, Zhongtian, et al.
Pubblicazione: (2026)

Remember to Forget: Gated Adaptive Positional Encoding
di: Ali, Riccardo, et al.
Pubblicazione: (2026)

Recurrent Deep Differentiable Logic Gate Networks
di: Bührer, Simon, et al.
Pubblicazione: (2025)

Convergence Rates for Softmax Gating Mixture of Experts
di: Nguyen, Huy, et al.
Pubblicazione: (2025)

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO
di: Ren, Yiming, et al.
Pubblicazione: (2026)

WAVES: Benchmarking the Robustness of Image Watermarks
di: An, Bang, et al.
Pubblicazione: (2024)

VeriContest: A Competitive-Programming Benchmark for Verifiable Code Generation
di: Xie, Zichen, et al.
Pubblicazione: (2026)

Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate
di: Zheng, Liangwei Nathan, et al.
Pubblicazione: (2025)

VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
di: Bai, Yifan, et al.
Pubblicazione: (2026)