9 papers
Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library
Abu Hanif Muhammad Syarubany, Jaehyun Jang, Hwanhee Kim +3
Recent humanoid soccer systems make motion tracking the substrate and derive locomotion from it, typically by steering a motion-reference anchor toward the ball. This yields strong…
Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation
Abu Hanif Muhammad Syarubany, Jaehyun Jang, Siwoo Lim +2
Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language. Sa2VA combines a multimodal large language mo…
EquivDP3: A SIM(3)-Invariant Point-Cloud Encoder for Data-Efficient Humanoid Loco-Manipulation
Abu Hanif Muhammad Syarubany, Chang D. Yoo
Visuomotor policies for humanoid loco-manipulation must generalize across object poses and lighting from only a handful of demonstrations. 3D Diffusion Policy (DP3) conditions a di…
Budgeted Cache Repair for Cross-Context KV-Cache Reuse
Haeyong Kang, Chang D. Yoo
Cross-context KV-cache reuse predicts a shared segment's keys and values under a new prefix instead of recomputing them, and has been reported to do so without quality loss. We fin…
When to Evict, Not What to Keep: Draft-Guided Eviction for Training-Free KV-Cache Compression
Haeyong Kang, Chang D. Yoo
Training-free KV-cache compression methods such as SnapKV, H2O, and PyramidKV evict tokens at the end of prefill, aiming to preserve the attention mass that future queries are expe…
Mixtures of SubExperts for Large Language Continual Learning
Haeyong Kang, Hee Suk Yoon, Dahua Feng +1
Enabling lifelong learning in LLMs demands resolving the stability-plasticity dilemma (i.e., models must incorporate new knowledge without overwriting prior representations) while…
PentaRAG: Large-Scale Intelligent Knowledge Retrieval for Enterprise LLM Applications
Abu Hanif Muhammad Syarubany, Chang Dong Yoo
Enterprise deployments of large-language model (LLM) demand continuously changing document collections with sub-second latency and predictable GPU cost requirements that classical…
Soft-TransFormers for Continual Learning
Haeyong Kang, Chang D. Yoo
Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-TransFormers (Soft-TF), a continual learning framework that adapts a frozen pre-trained Transfo…
Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection
Sunghun Kang, Junbum Cha, Jonghwan Mun +2
Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend ta…