6 papers
Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution
Minkyu Kim, Junhoo Lee, Seungyeon Kim +4
Vision-language-action (VLA) policies generate action sequences that reduce repeated inference, but deciding how much of each sequence to execute is critical to task success. Exist…
Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse
Junhoo Lee, Baekseung Kim, Seungyeon Kim +1
Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining normal behavior on clean sample…
Two Companion -Series Identities and Their Combinatorics
Haijun Li, Chenwei Wang
In this paper, we evaluate two companion -series recently suggested for investigation by Andrews and El Bachraoui in the concluding remarks of their work. From these evaluations…
ACRO: Actor-Critic Rollout Orchestration
Junhoo Lee, Seungyeon Kim, Baekseung Kim +4
Executing a vision-language-action (VLA) policy involves deciding when to continue an attempt and when to intervene to improve its chances of success. We introduce ACRO, an Actor--…
Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
Kyomin Hwang, Hyeonjin Kim, Seungyeon Kim +2
There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses r…
Unlocking the Potential of Diffusion Language Models through Template Infilling
Junhoo Lee, Seungyeon Kim, Nojun Kwak
Diffusion Language Models (DLMs) have emerged as a promising alternative to Autoregressive Language Models, yet their inference strategies remain limited to prefix-based prompting…