[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

[Seminar] Improving spatial reasoning of LLMs using Multi-modal transformer

[Seminar] Multi-Agent Cooperation via Tree Search and Language Models

[Seminar] Does Vision Models Use Monocular Depth Cues?

[Seminar] How to train a critic model?

[Seminar] Aligning Text-to-Motion Model at Event-Level with GPT-4Vision Reward

[Seminar] Cuboid Arrangement and Scene Assembly for Interior Design

[Seminar] CaPo: Cooperative Plan Optimization with LLMs

[Seminar] Simulating Human-like Daily Activities With Desire-Driven Autonomy

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

[Seminar] Unified Physics-Based Character Control Through Masked Motion Inpainting

[Seminar] Physics-based Scene Layout Generation from Human Motion

[Seminar] Unlock Lost Details in 3D Gaussian Splatting

[Seminar] Scene Representation on Code Space

[Seminar] A general and reliable trained model-based reinforcement learning method (DreamerV3)

[Seminar] Self-Composing Policies for Scalable Continual RL

[Seminar] 3D spatial memory system for VLM agents

[SIGGRAPH 2025] ForceGrip: Realistic and Intention-Aware Grasping for Virtual Hand Interaction

[Seminar] Advancing Large-Scale Dataset for Bimanual Hand-Object Interaction

[Seminar] PersonaBooth: Personalized Text-to-Motion Generation

[Seminar] Any to Motion Generation

[Seminar] Human-aware Indoor Scene Optimization via Deep Reinforcement Learning

[Seminar] LLM based Indoor Scene Synthesis

[Seminar] Generating Traffic Scenario Dataset via In Context Learning

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

[Seminar] Scaling Large Language Model-Based Multi Agent Network

[Seminar] Synergy of Reasoning and Acting in LLMs

[Seminar] Animatable Gaussians

[Seminar] Conformer: Convolution-augmented Transformer for Speech Recognition

[AI/XR/CG Research Trends] Feb. 2025.

[Seminar] Text-to-3D Scene Generation using 3D Gaussian Splatting (DreamScene)

[Seminar] A Teacher-Student Framework for Interactive Character Control

[Seminar] Human-like memory systems for AI agents

[IEEE VR] Shaping the Future of VR Hand Interactions: Lesson Learned from Modern Methods

[Seminar] Hand-centric Motion Refinement for 3D Hand-Object Interaction

[Seminar] LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model

[Seminar] Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting

[Seminar] Language Models Meet World Models

[Seminar] Text-to-3D Generation using SDS versus ISM

[AAAI-Oral] REVECA: Adaptive Planning and Trajectory-based Validation in Cooperative Language Agents

[Seminar] BAMM: Bidirectional Autoregressive Motion Model

[Seminar] Physically Interactable 3D Indoor Scene Synthesis

Embodied Multi-Agent Cooperation with Efficient Communication

[Seminar] How appearance and motion affect personality perception?

[Seminar] How to denoise motion using neural distance field

[Seminar] MoMask Generative Masked Modeling of 3D Human Motions

[Seminar] Training-free method using LLM for Video anomaly detection

[Seminar] Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation

[Seminar] Semantic-aware editing using CNS-edit

[Seminar] Physics-aware Hand-object Interaction Denoising

[Seminar] MotionGPT: Human Motion as a Foreign Language

[Seminar] Compositional 3D Scene Synthesis from Scene Graphs

[Seminar] HOLODECK: Language Guided Generation of 3D Embodied AI Environments

[Seminar] How can crowd animation be created driven by a large language model (LLM)?

[Seminar] ParCo: Part-Coordinating Text-to-Motion Synthesis

[PG] 3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization

[TOG] A Deep Solver For Arbitrary Marker Configuration in Optical Motion Capture

[Seminar] An Introduction to Retriever-Augmented Generation