Diffusion vision-language models (DVLMs) process their entire input at every denoising step. Since visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image. Visual token pruning methods partially relieve this burden by removing...
Donghyeon Cho, Joowon Kim, Seung-Ho Shin et al.· 0 citations
Rubric-based rewards enable effective reinforcement learning on non-verifiable tasks. However, because these rewards are typically defined as a weighted measure of rubric coverage, models are trained primarily to maximize a recall objective. As a result, RL-trained models produce responses that are more complete but al...
Hyun Ryu, Jong-Heon Kim, Yi-Qing Xie et al.· 0 citations
Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail generation. Sustained concurrency also concentrates context processing into fewer decode steps, increasing the KV workload per step. We characterize this \emph{KV concentr...
Sihwan Park, Sung-Yub Kim, Doohyuk Jang et al.· 0 citations
GRAFT (Gated Replacement of Answer-Failed groups with peer Trajectories), an off-policy-aware framework that replaces all-fail groups with informative peer groups and transfers both successful and unsuccessful peer responses with peer-computed advantages, while controlling cross-model mismatch through sequence-level co...
Doohyuk Jang, Y. Park, Gyouk Chu et al.· arXiv.org· 0 citations
This work proposes Judge co-adaptation from Zero data (J-Zero), a unified Challenger--Solver--Judge self-evolution framework that supports self-improvement across both verifiable and unverifiable domains and identifies Judge co-adaptation as the key driver of this sustained improvement.
Gyouk Chu, Myeongho Jeon, Teresa Yeo et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.