29 citations · 77 across the 17 of their papers we have counts for
19 papers
CoCo-IR: Contextual Composed Image Retrieval
Shengcao Cao, Tanmaya Shekhar Dabral, Zhongli Ding +6
Current instruction-based image retrieval systems are powerful but limited to single-turn interactions, failing to capture the iterative nature of complex, real-world visual search…
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
Dayuan Zhao, Shengcao Cao, Yu-Xiong Wang +1
Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +355
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
DCNNAnaCal: Physics-Informed Machine Learning for Accurate and Precise Weak Lensing Shear Estimation
Shurui Lin, Xiangchong Li, Ji Li +3
Traditional weak gravitational lensing shear estimators are carefully calibrated but struggle to fully capture realistic galaxy morphologies, point-spread-function (PSF) effects, b…
OSGym: Scalable OS Infra for Computer Use Agents
Zengyi Qin, Jinyuan Chen, Yunze Man +25
Training computer use agents requires full-featured OS sandboxes with GUI environments, which consume substantial hardware resources as the number of sandboxes scales. Stochastic e…
Refer to Any Segmentation Mask Group With Vision-Language Prompts
Shengcao Cao, Zijun Wei, Jason Kuen +6
Recent image segmentation models have advanced to segment images into high-quality masks for visual entities, and yet they cannot provide comprehensive semantic understanding for c…
Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning
Yuxiang Lu, Shengcao Cao, Yu-Xiong Wang
Vision Foundation Models (VFMs) have demonstrated outstanding performance on numerous downstream tasks. However, due to their inherent representation biases originating from differ…
Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision
Shengcao Cao, Liang-Yan Gui, Yu-Xiong Wang
Current large multimodal models (LMMs) face challenges in grounding, which requires the model to relate language components to visual entities. Contrary to the common practice that…
TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding
Zhihao Zhang, Shengcao Cao, Yu-Xiong Wang
The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge fr…
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Shengcao Cao, Jiuxiang Gu, Jason Kuen +7
Open-world entity segmentation, as an emerging computer vision task, aims at segmenting entities in images without being restricted by pre-defined classes, offering impressive gene…
HASSOD: Hierarchical Adaptive Self-Supervised Object Detection
Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui +1
The human visual perception system demonstrates exceptional capabilities in learning without explicit supervision and understanding the part-to-whole composition of objects. Drawin…
Aligning Large Multimodal Models with Factually Augmented RLHF
Zhiqing Sun, Sheng Shen, Shengcao Cao +9
Large Multimodal Models (LMM) are built across modalities and the misalignment between two modalities can result in "hallucination", generating textual outputs that are not grounde…
Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation
Shengcao Cao, Mengtian Li, James Hays +3
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. Wh…
Contrastive Mean Teacher for Domain Adaptive Object Detectors
Shengcao Cao, Dhiraj Joshi, Liang-Yan Gui +1
Object detectors often suffer from the domain gap between training (source domain) and real-world applications (target domain). Mean-teacher self-training is a powerful paradigm in…
Neighborhood-Aware Neural Architecture Search
Xiaofang Wang, Shengcao Cao, Mengtian Li +1
Existing neural architecture search (NAS) methods often return an architecture with good search performance but generalizes poorly to the test setting. To achieve better generaliza…
Efficient Model Performance Estimation via Feature Histories
Shengcao Cao, Xiaofang Wang, Kris Kitani
An important step in the task of neural network design, such as hyper-parameter optimization (HPO) or neural architecture search (NAS), is the evaluation of a candidate model's per…
Rethinking Transformer-based Set Prediction for Object Detection
Zhiqing Sun, Shengcao Cao, Yiming Yang +1
DETR is a recently proposed Transformer-based method which views object detection as a set prediction problem and achieves state-of-the-art performance but demands extra-long train…
Lossless Image Compression through Super-Resolution
Sheng Cao, Chao-Yuan Wu, Philipp Krähenbühl
We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless su…
Learnable Embedding Space for Efficient Neural Architecture Compression
Shengcao Cao, Xiaofang Wang, Kris M. Kitani
We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compr…