Liqiang Nie

31

Papers

227

Total Citations

Papers (31)

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

FALCON: Resolving Visual Redundancy and Fragmentation in High-resolution Multimodal Large Language Models via Visual Registers

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data

Object-Shot Enhanced Grounding Network for Egocentric Video

GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression

Social Debiasing for Fair Multi-modal LLMs

Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning

NeurIPS 2025arXiv

Embodied Crowd Counting

Exploiting the Social-Like Prior in Transformer for Visual Reasoning

LLM vs Small Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model

DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring

Discriminative Probing and Tuning for Text-to-Image Generation

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

Revisiting Context Aggregation for Image Matting

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering

Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

Curriculum Coarse-to-Fine Selection for High-IPC Dataset Distillation

DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation

Language-Assisted Debiasing and Smoothing for Foundation Model-Based Semi-Supervised Learning

Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation

Less is More: Empowering GUI Agent with Context-Aware Simplification

Debiased Curriculum Adaptation for Safe Transfer Learning in Chest X-ray Classification