Peng Li

15

Papers

52

Total Citations

1

Affiliations

Affiliations

Institute for AI Industry Research (AIR), Tsinghua University, China

Papers (15)

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion

Adversarial Robust Memory-Based Continual Learner

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models

Position: Towards Unified Alignment Between Agents, Humans, and Environment

Amend to Alignment: Decoupled Prompt Tuning for Mitigating Spurious Correlation in Vision-Language Models

High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Sampling

Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

How Do Multimodal Large Language Models Handle Complex Multimodal Reasoning? Placing Them in An Extensible Escape Game

Variable Importance in High-Dimensional Settings Requires Grouping

Semi-supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach

Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation