1 citations · 1 across the 9 of their papers we have counts for
14 papers · 1 filter
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…
ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space
Minkyu Kim, Baekseung Kim, Junhoo Lee +2
Diffusion models achieve high-quality image generation but remain computationally expensive due to iterative denoising across many timesteps. Existing acceleration methods mainly r…
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--…
Completion Aware Guidance for World Action Models
Seungyeon Kim, Junhoo Lee, Baekseung Kim +2
World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, action-consistent predictions omit…
Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization
Yun Kim, Nojun Kwak
Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent methods use token entropy as an i…
Recursive Harness Distillation across Agents for Robot Manipulation
Seungyeon Kim, Junhoo Lee, Minkyu Kim +2
A central goal in robotics is to enable manipulation across changing tasks and environments. Vision-language-action (VLA) models provide broad manipulation capabilities but can str…
String: An Agentic OS Where Every App Is a Markdown File
Jookyung Song, Nojun Kwak, Simyung Chang
LLM agents have become a new class of software user, but every surface they work through was designed for someone else. Pages are built for human eyes, which can skim and ignore; t…
LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing Pages
Injun Baek, HyeongSeok Lee, Yearim Kim +2
Landing pages are goal-oriented web interfaces that must communicate a target-specific value proposition while organizing information flow, visual hierarchy, and calls to action (C…
When Saying No Makes Better Videos: Designing Dual Gatekeeping for Pedagogically Grounded AI Content Creation
Yearim Kim, Injun Baek, Nojun Kwak
To prevent the adoption of aesthetically polished but pedagogically flawed AI content, we study a video authoring pipeline featuring two layers of structured refusal. The first lay…
ACE: A Self-Correcting Agentic Canvas Editor for Multi-Slide Presentation Automation
JooYoung Jang, Taegyeong Lee, Jihyeon Park +1
Commercial design platforms increasingly edit documents through large language model (LLM) agents, but two practical problems block reliable deployment: legacy document formats exp…
VDPP: Video Depth Post-Processing for Speed and Scalability
Daewon Yoon, Injun Baek, Sangyu Han +2
Video depth estimation is essential for providing 3D scene structure in applications ranging from autonomous driving to mixed reality. Current end-to-end video depth models have es…
PedaCo-Gen: Scaffolding Pedagogical Agency in Human-AI Collaborative Video Authoring
Injun Baek, Yearim Kim, Nojun Kwak
While advancements in Text-to-Video (T2V) generative AI offer a promising path toward democratizing content creation, current models are often optimized for visual fidelity rather…