Author

Guang Lin

h-index 4 View on Semantic Scholar

We have 5 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Selective Tie Learning: Mitigating Spurious Correlations in Preference Optimization

Preference optimization can learn spurious correlations, and augmenting the preference data with ties (equally preferred responses) can reduce spurious reliance. However, ties differ in their corrective effect, making their selection for augmentation important. For log-linear policies, we derive each tie's influence on...

Christian Moya, Purav Matlia, E. Thornley et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control

It is shown that selective control under partial auditing reduces accepted errors while increasing correctness, and experiments with log linear and neural contextual bandits and with a language model support the analysis and show that selective control under partial auditing reduces accepted errors while increasing cor...

Christian Moya, E. Thornley, Guang Lin · 0 citations

#machine learning Preprint May 2026

Conformalized Quantum DeepONet Ensembles: Towards Scalable Operator Learning with Distribution-Free Guarantees

These results connect resource-aware scalability analysis with finite-sample uncertainty guarantees for quantum operator learning, and explore hybrid classical-quantum architectures and superposed execution to manage ensemble runtime and hardware requirements.

Purav Matlia, Christian Moya, Guang Lin · 0 citations

Preprint Aug 2026

GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation

This work proposes GraspMeanFlow, an SE(3)-equivariant MeanFlow framework for few-step 6-DoF grasp generation, and proves that a point-cloud-conditioned distribution transported by an equivariant average-velocity flow map remains invariant, so equivariance is retained under few-step sampling.

J. Kwon, Yikun Bai, Amirhossein Mollaali et al. · 0 citations

Preprint Aug 2026

CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories

Autonomous computer-use agents are increasingly applied to long-horizon tasks requiring coordinated application calls, persistent state tracking, and verifier-sensitive writes, yet they remain prone to procedural failures: misreading application state, tool semantics, or task progress. Procedural memory promises more c...

Zheyuan Deng, Bing-Hang Lu, Han-Qi Feng et al. · 0 citations