The proposed BootDiffLights framework is a novel framework that employs a conditional diffusion model to provide an implicit credit-assignment mechanism and achieves superior performance compared to state-of-the-art baselines.
Reinforcement learning can align visual generators with reward signals beyond their pretraining objectives, but existing score-function methods typically introduce stochasticity by perturbing the reverse denoising trajectory, leading to costly rollout-based optimization. We instead ask whether stochastic exploration ca...
Qiuhong Shen, Yiding Yang, Yu-Xin Zhang et al.· 0 citations
Network decision-making tasks, including adaptive bitrate streaming, load balancing, and congestion control, require policies to process heterogeneous states and actions while balancing near- and long-term consequences. Existing solutions generalize poorly across network tasks, require substantial task-specific redesig...
Ling-Feng Peng, Xiao-Hui Xie, Yang Bao et al.· 0 citations
This paper introduces Effective Congestion (EC), a deadline-aware metric family that quantifies interface congestion by packet urgency and proactively filters non-viable traffic, coupled with a Uniform Path Grouping (UPG) distribution heuristic promoting robust load-balancing; the resulting policies are embedded into M...
V. N. Vitale, Mohammad Solki, A. Tulino et al.· 0 citations
Online reinforcement learning (RL) fine-tunes diffusion models with black-box rewards, but reverse-process methods such as Flow-GRPO are limited in efficiency by poor credit assignment, while forward-process methods such as DiffusionNFT are efficient yet unstable without carefully tuned exponential-moving-average (EMA)...
Zheng-Lin Wan, Jia-Yu Chen, Zhengfeiyang Zhang et al.· 0 citations
This work reformulates the transition-level log-likelihood in Flow-GRPO into a token-wise representation natively aligned with DiT patch architectures, constructing spatially fine-grained importance sampling ratios and introduces a continuous spatial credit map derived from reward gradients.
The method, $\lambda$-Controlled GRPO, calibrates importance-ratio behavior from this predicted law rather than from noisy empirical statistics, and allocates gradient effort across denoising steps according to their predicted cost, and keeps late-step path variance within its intended budget.
Yu-Feng Wang, Parivesh Priye, Meeshawn Marathe et al.· 0 citations
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.