강형엽 IIIXR LAB

[Seminar] Neural Robot Dynamics

[Seminar] Can a robot place objects precisely in unseen real-world environments?

[ICLR2026] Event-T2M: Event-level Conditioning for Complex Text-to-Motion Synthesis

[Seminar] Spatial Mental Modeling for VLMs

[Seminar] What if we use Chain-of-Thought to roll out a world model?

[Seminar] LLM-Designed Policies for Generalizable Game Agents

[IIIXR Lab's Research Interest] Jan. 2026.

[Seminar] From Text to Boxes: Diffusion Transformers for Open Vocabulary Natural Scene Layout Gen.

[Seminar] How to Reconstruct Complex 3D Meshes Using Diffusion Models

[Seminar] Guided Diffusion for Physics-based Character Look-ahead Control

[Seminar] Can a VLA perform ARPG-style combat?

[Seminar] Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts

[Seminar] Policy Contrastive Imitation Learning

[WACV2026-Oral] BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis,

[Seminar] 3D geometry estimation from multi-view images

[Seminar] Hierarchical and Interpretable Reinforcement Learning Using SkillTree

[Seminar] Can Vision-Language Models Learn from Context?

[Seminar] What if the world model and VLA met?

[Seminar] Towards Transferring Sketch Storyboards into 3D Animation

[Seminar] Attention is all you need for rendering

[Seminar] Language-Driven Sequential Sketch Generation

[IIIXR Lab's Research Interest] Oct. 2025.

[Seminar] Synergizing Reasoning and Acting in Task Solving Problem

[SIGGRAPH Asia 2025] How Does a Virtual Agent Decide Where to Look? Symbolic Cognitive Reasoning

[Seminar] Understanding 3D Scene Using Hierarchical Feature Gaussian Splatting

Title: CoT-VLA: A New Method for Visual Reasoning

[Seminar] GO-Skill: One Skill Library to Learn Many Tasks

[Seminar] Learning to Route LLMs with Preference Data

[Seminar] Global-Local Tree Search in VLMs for 3D Indoor Scene Generation

[Seminar] Using Pretrained Language Models for History Compression in RL