MOTIVATION
Self-supervised pre-training models for molecular data have demonstrated notable results across many downstream tasks. The inherent multimodal properties of molecules have also motivated efforts to capture information from different modalities. However, current multimodal molecular pre-training models usuall...
Kang-Jie Zheng, Jun-Wei Yang, Siyu Long et al.· Bioinformatics· 0 citations
The Dual Consistency training framework, which incorporates a novel Temporal Geodesic Matching (TGM) scheduler, enables DCFold to achieve a 15x acceleration in inference while maintaining predictive fidelity.
Zhe Zhang, Yuanning Feng, Yuxuan Song et al.· arXiv.org· 3 citations
The evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly wh...
Ya-Wen Ouyang, Xin-Bo Zhang, Zi-Yuan Ma et al.· 0 citations
Direct On-Policy Distillation (Direct-OPD) is proposed, which transfers the teacher's RL-induced policy shift instead of running sparse-reward RL on the target model and consistently leverages weaker teachers to improve stronger target models.
Shiyuan Feng, Huan Gao, Haohan Chi et al.· arXiv.org· 8 citations· ⚡1
This work proposes the first Bayesian flow formulation for protein backbone orientations by recasting orientation modeling as an equivalent hyperspherical generation problem with antipodal symmetry and delivers consistently exceptional performance in both peptide and antibody design tasks.
Han-Lin Wu, Yuxuan Song, Zhe Zhang et al.· Neural Information Processin...· 0 citations
Subspace-Aligned Rewiring (SAR) shows that extracting reasoning-effective updates from parameter geometry can serve as a training-free mechanism to improve reasoning and multi-domain performance.
Zhilong Zhang, Hongli Yu, Huan Gao et al.· 0 citations
Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh, systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student.
Huan Gao, Haohan Chi, Yong Yan et al.· 12 citations· ⚡6
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
