8 papers
DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning
Chi-Min Chan, Ehsan Hajiramezanali, Xiner Li +6
In scientific reasoning tasks, the veracity of the reasoning process is as critical as the final outcome. While Process Reward Models (PRMs) offer a solution to the coarse-grained…
Object-Aware 4D Human Motion Generation
Shurui Gui, Deep Anil Patel, Xiner Li +1
Recent advances in video diffusion models have enabled the generation of high-quality videos. However, these videos still suffer from unrealistic deformations, semantic violations,…
Language Models for Controllable DNA Sequence Design
Xingyu Su, Xiner Li, Yuchao Lin +3
We consider controllable DNA sequence design, where sequences are generated by conditioning on specific biological properties. While language models (LMs) such as GPT and BERT have…
Dynamic Search for Inference-Time Alignment in Diffusion Models
Xiner Li, Masatoshi Uehara, Xingyu Su +5
Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in…
Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation
Keqiang Yan, Xiner Li, Hongyi Ling +8
We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior…
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
Masatoshi Uehara, Xingyu Su, Yulai Zhao +5
To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-gui…