collaborators

5 papers

cs.CV2026

MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation

Ruiyao Liu, Hui Shen, Ping Zhang +16

Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed vi…

cs.CL2026

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering

Xiangfeng Wang, Hangyu Guo, Yanlin Lai +11

While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the c…

cs.CL2026

R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging

Yanlin Lai, Mitt Huang, Hangyu Guo +11

Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts t…

cs.CL2026

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures

Yanghao Su, Wenbo Zhou, Tianwei Zhang +4

Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mai…

cs.LG2026

Reward Shaping to Mitigate Reward Hacking in RLHF

Jiayi Fu, Xuandong Zhao, Chengyuan Yao +3

Reinforcement learning from human feedback (RLHF) is widely used to align large language models (LLMs) with human preferences. However, RLHF remains vulnerable to \emph{reward hack…