Tianlang Chen

Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute

RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance

Improving Diffusion Language Model Reasoning through Joint Search in Generation Order and Token Space

Exchangeability in Neural Networks and its Application to Dynamic Pruning

RelGNN: Composite Message Passing for Relational Deep Learning