Coupled Variational Reinforcement Learning for Language Model General Reasoning
Paper • 2512.12576 • Published • 3
wenxueru
Aunderline
AI & ML interests
None yet
Organizations
None yet
authored a
paper 3 months ago
submitted a
paper to Daily Papers 3 months ago
authored 10
papers 10 months ago
Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
Paper • 2408.16326 • Published • 1
Scalable Oversight for Superhuman AI via Recursive Self-Critiquing
Paper • 2502.04675 • Published • 1
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
Paper • 2502.17173 • Published
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigation
Paper • 2406.12221 • Published
Rethinking Reward Model Evaluation: Are We Barking up the Wrong Tree?
Paper • 2410.05584 • Published
Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval
Paper • 2308.10191 • Published
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
Paper • 2503.03122 • Published • 1
End-to-End Entity Detection with Proposer and Regressor
Paper • 2210.10260 • Published
Type-supervised sequence labeling based on the heterogeneous star graph for named entity recognition
Paper • 2210.10240 • Published
Transferable Post-training via Inverse Value Learning
Paper • 2410.21027 • Published