12 citations · 18 across the 16 of their papers we have counts for
18 papers
Pixel-wise Geo-registration of Drone and Satellite Images
Qingyang Liu, David G Shatwell, Parth Parag Kulkarni +1
Pixel-level cross-view geo-registration aims to align a query image (e.g., drone) to a geo-referenced satellite map so that every query pixel can be mapped to real-world GPS coordi…
OmniPresent: Generating Coherent Presentation Suites from Scientific Papers
Qianli Ma, Jipeng Xiao, Siyu Wang +7
Transforming static research papers into dynamic media such as posters, slides, and videos is essential for effective dissemination but remains a labor-intensive challenge. Existin…
Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
Shuochen Chang, Qingyang Liu, Shaobo Wang +8
Large language models achieve high reasoning performance via explicit chain-of-thought and reinforcement learning, but require long output sequences and extended inference time. La…
Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
Shuochen Chang, Tong Bai, Xiaofeng Zhang +5
Latent reasoning enables Large Language Models (LLMs) to perform multi-step inference within continuous hidden states, offering efficiency gains over explicit Chain-of-Thought (CoT…
Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners
Qingyang Liu, Bingjie Gao, Canmiao Fu +9
Recent unified models integrate multimodal understanding and generation within a single framework. However, an "understanding-generation gap" persists, where models can capture use…
The Missing Piece in Pre-trained Model Evaluation: Reward-Guided Decoding Unlocks Task-Oriented Behavior Without Parameter Updates
Shaobo Wang, Guo Chen, Ziyue Wang +5
With the rapid progress of large language models (LLMs), reliably evaluating the capabilities of pre-trained LLMs has become increasingly important. The challenge is that base pre-…
Reflection Generation for Composite Image Using Diffusion Model
Haonan Zhao, Qingyang Liu, Jiaxuan Chen +1
Image composition involves inserting a foreground object into the background while synthesizing environment-consistent effects such as shadows and reflections. Although shadow gene…
TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
Harold Haodong Chen, Disen Lan, Wen-Jie Shu +10
The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consi…
UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits
Keming Ye, Zhipeng Huang, Canmiao Fu +7
With the rapid advances of powerful multimodal models such as GPT-4o, Nano Banana, and Seedream 4.0 in Image Editing, the performance gap between closed-source and open-source mode…
DToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
Shuochen Chang, Xiaofeng Zhang, Qingyang Liu +1
Diffusion-based multimodal large language models (Diffusion MLLMs) have recently demonstrated impressive non-autoregressive generative capabilities across vision-and-language tasks…
HyperET: Efficient Training in Hyperbolic Space for Multi-modal Large Language Models
Zelin Peng, Zhengqin Xu, Qingyang Liu +2
Multi-modal large language models (MLLMs) have emerged as a transformative approach for aligning visual and textual understanding. They typically require extremely high computation…
RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
Bingjie Gao, Qianli Ma, Xiaoxue Wu +9
Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the gener…
The Telephone Game: Evaluating Semantic Drift in Unified Models
Sabbir Mollah, Rohit Gupta, Sirnam Swetha +3
Unified models (UMs) combine visual understanding (I2T) and generation (T2I) in a single framework. We focus on T2I and I2T, where cross-consistency---what a model understands, it…
AnimateScene: Camera-controllable Animation in Any Scene
Qingyang Liu, Bingjie Gao, Weiheng Huang +10
Recent advances in 3D scene reconstruction and 4D human animation have broadened adoption, but integrating the two remains difficult. Key challenges include placing humans at plaus…
Shadow Generation for Composite Image Using Diffusion model
Qingyang Liu, Junqi You, Jianting Wang +3
In the realm of image composition, generating realistic shadow for the inserted foreground remains a formidable challenge. Previous works have developed image-to-image translation…
DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
Qingyang Liu, Jianting Wang, Li Niu
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadow for the inserte…
Fast Object Placement Assessment
Li Niu, Qingyang Liu, Zhenchen Liu +1
Object placement assessment (OPA) aims to predict the rationality score of a composite image in terms of the placement (e.g., scale, location) of inserted foreground object. Howeve…
OPA: Object Placement Assessment Dataset
Liu Liu, Zhenchen Liu, Bo Zhang +4
Image composition aims to generate realistic composite image by inserting an object from one image into another background image, where the placement (e.g., location, size, occlusi…