Cover Image

Reward Model Generalization for Compute-Aware Test-Time Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Song, Zeen, Qiang, Wenwen, Zhao, Siyu, Zheng, Changwen, Hua, Gang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction
by: Song, Ruike, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

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

Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective
by: Song, Zeen, et al.
Published: (2024)

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

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

Learning Invariant Causal Mechanism from Vision-Language Models
by: Song, Zeen, et al.
Published: (2024)

Neuromodulated Meta-Learning
by: Wang, Jingyao, et al.
Published: (2024)

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

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

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

On the Plasticity and Stability for Post-Training Large Language Models
by: Qiang, Wenwen, et al.
Published: (2026)

From Shallow to Deep: Pinning Semantic Intent via Causal GRPO
by: Zhou, Shuyi, et al.
Published: (2026)

On the Discriminability of Self-Supervised Representation Learning
by: Song, Zeen, et al.
Published: (2024)

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
by: Wang, Haozhe, et al.
Published: (2026)

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

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

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

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

Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
by: Zhang, Zheng, et al.
Published: (2025)

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference
by: Yu, Yue, et al.
Published: (2025)

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

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models
by: Yu, Song, et al.
Published: (2026)

M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
by: Wang, Junxiong, et al.
Published: (2025)

Exploration-Driven Optimization for Test-Time Large Language Model Reasoning
by: Li, Changhao, et al.
Published: (2026)

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance
by: Chen, Tianlang, et al.
Published: (2025)

PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model
by: Lin, Baijiong, et al.
Published: (2025)

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
by: Hong, Ilgee, et al.
Published: (2025)

Verifying Meta-Awareness via Predictive Rewards in Reasoning Models
by: Kim, Yoonjeon, et al.
Published: (2025)

Learning to Reason without External Rewards
by: Zhao, Xuandong, et al.
Published: (2025)