18 papers
ReGuide: From Test-Time Guidance to Self-Improving Diffusion Policies
Tzu-Hsiang Lin, Srinivas Shakkottai, Dileep Kalathil +1
Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into task failure. Existing metho…
Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
Xingyu Su, Jacob Helwig, Shubham Parashar +6
We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs). Rather than pretraining from scratch, prior work replaces the causal attention i…
Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction
Mahdi Farahbakhsh, Vishnu Teja Kunde, Dileep Kalathil +2
Diffusion models have been used as priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruc…
Learnability-Informed Fine-Tuning of Diffusion Language Models
Shubham Parashar, Atharv Chagi, Jacob Helwig +5
We aim to improve the reasoning capabilities of diffusion language models (DLMs). While SFT is a popular post-training recipe for autoregressive models, its use in DLMs faces chall…
Adaptive Outer-Loop Control of Quadrotors via Reinforcement Learning
Vishnu Saj, Sushil Vemuri, Dileep Kalathil +1
Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in overly conservative policies tha…
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Vishnu Teja Kunde, Fatemeh Doudi, Mahdi Farahbakhsh +3
Reinforcement learning (RL) has been effective for post-training autoregressive (AR) language models, but extending these methods to diffusion language models (DLMs) is challenging…