Songhua Liu lists you as their PhD advisor. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeStudents and postdocs1
Works10 from public data
- C4D: 4D Made from 3D Through Dual Correspondences9
This work introduces C4D, a framework that leverages temporal Correspondences to extend existing 3D reconstruction formulation to 4D, and trains a dynamic-aware point tracker that provides additional mobility information, facilitating the estimation of motion masks to separate moving elements from the static background, thus offering more reliable guidance for dynamic scenes.
- 8
- MetaISP: Efficient RAW-to-sRGB Mappings with Merely 1M Parameters7
The proposed MetaISP is a streamlined model that achieves superior reconstruction quality by adaptively modulating its parameters and architecture in response to diverse inputs by predicting dynamic weights for each input image and combining these weights with multiple learnable basis matrices to construct the correction matrices.
- 5
- Invisible Safety Threat: Malicious Finetuning for LLM via Steganography4
This paper finetuned the model to understand and apply a steganographic technique, and produces steganographic malicious outputs in response to hidden malicious prompts, while the user interface displays only a fully benign cover interaction.
- Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior3
RePro is proposed, a logit-based provenance framework that fuses teacher-forced likelihood features with logit-ranking signals and consistently attains strong performance and transfers well across refiners, suggesting that it exploits refiner-agnostic distribution shifts rather than rewrite-style artifacts.
- Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers2
This paper proposes a novel controllable diffusion framework tailored for linear attention backbones like SANA, which achieves state-of-the-art controllable generation performance based on linear-attention models, surpassing existing methods in terms of fidelity and controllability.
- 2
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.