most citedProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

2 citations · 4 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Variable-Length Generative Protein Design via Generalized Poisson Flow

Chaoran Cheng, Zhanghan Ni, Yanru Qu +4

The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- an…

cs.LG2026

Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning

Bangji Yang, Hongbo Ma, Jiajun Fan +1

Large Language Models employing Chain-of-Thought reasoning achieve strong performance but suffer from excessive token consumption that inflates inference costs. Existing efficiency…

cs.LG2025

Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards

Jiajun Fan, Roger Ren, Jingyuan Li +6

The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inferen…

cs.LG2025

Fine-tuning Flow Matching Generative Models with Intermediate Feedback

Jiajun Fan, Chaoran Cheng, Shuaike Shen +2

Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuo…

cs.LG2025

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Jiajun Fan, Tong Wei, Chaoran Cheng +2

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence…

cs.LG2025

ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning

Ziwen Wang, Jiajun Fan, Ruihan Guo +3

Protein generative models have shown remarkable promise in protein design, yet their success rates remain constrained by reliance on curated sequence-structure datasets and by misa…