Ruipeng Zhang

Ruipeng Zhang, Zhihao Li, Haozhang Yuan et al.

Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans, thereby addressing the hallucination issue. Despite its success, this paradigm has yet to specifically target the perceptual bottleneck in attended regions or address insufficient Visual Robustness against image degradation. Furthermore, existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning. To address these challenges, we propose Perceptual Processing Direct Preference Optimization (P$^2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs, thereby directly addressing the identified visual bottlenecks while inherently avoiding the issues of vision-agnostic and off-policy data. It introduces: (1) an on-policy preference pairs construction method targeting Focus-and-Enhance perception and Visual Robustness, and (2) a well-designed Calibration Loss to precisely align visual signals with the causal generation of text. Experimental results demonstrate that with a comparable amount of training data and cost, P$^2$-DPO outperforms strong baselines that rely on costly human feedback on benchmarks. Furthermore, evaluations on Attention Region Fidelity (ARF) and image degradation scenarios validate the effectiveness of P$^2$-DPO in addressing perceptual bottleneck in attended regions and improving Visual Robustness against degraded inputs.

Haolin Li, Shuyang Jiang, Ruipeng Zhang et al.

While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, existing approaches typically distill chain-of-thought reasoning traces from large proprietary models via supervised fine-tuning, then conduct reinforcement learning (RL). These methods exhibit limited improvement on underrepresented domains like rare diseases while incurring substantial costs from generating complex reasoning chains. To efficiently enhance medical reasoning, we propose MedSSR, a Medical Knowledge-enhanced data Synthesis and Semi-supervised Reinforcement learning framework. Our framework first employs rare disease knowledge to synthesize distribution-controllable reasoning questions. We then utilize the policy model itself to generate high-quality pseudo-labels. This enables a two-stage, intrinsic-to-extrinsic training paradigm: self-supervised RL on the pseudo-labeled synthetic data, followed by supervised RL on the human-annotated real data. MedSSR scales model training efficiently without relying on costly trace distillation. Extensive experiments on Qwen and Llama demonstrate that our method outperforms existing methods across ten medical benchmarks, achieving up to +5.93% gain on rare-disease tasks. Our code is available at https://github.com/tdlhl/MedSSR.

Ruipeng Zhang, Chenning Yu, Jingkai Chen et al.

Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments. For the more challenging problem of planning in dynamic environments, such as multi-arm assembly tasks and human-robot interaction, motion planners need to consider the trajectories of the dynamic obstacles and reason about temporal-spatial interactions in very large state spaces. We propose a GNN-based approach that uses temporal encoding and imitation learning with data aggregation for learning both the embeddings and the edge prioritization policies. Experiments show that the proposed methods can significantly accelerate online planning over state-of-the-art complete dynamic planning algorithms. The learned models can often reduce costly collision checking operations by more than 1000x, and thus accelerating planning by up to 95%, while achieving high success rates on hard instances as well.

Tianjie Dai, Ruipeng Zhang, Feng Hong et al.

Vision-Language Pre-training (VLP) that utilizes the multi-modal information to promote the training efficiency and effectiveness, has achieved great success in vision recognition of natural domains and shown promise in medical imaging diagnosis for the Chest X-Rays (CXRs). However, current works mainly pay attention to the exploration on single dataset of CXRs, which locks the potential of this powerful paradigm on larger hybrid of multi-source CXRs datasets. We identify that although blending samples from the diverse sources offers the advantages to improve the model generalization, it is still challenging to maintain the consistent superiority for the task of each source due to the existing heterogeneity among sources. To handle this dilemma, we design a Conquer-and-Divide pre-training framework, termed as UniChest, aiming to make full use of the collaboration benefit of multiple sources of CXRs while reducing the negative influence of the source heterogeneity. Specially, the ``Conquer" stage in UniChest encourages the model to sufficiently capture multi-source common patterns, and the ``Divide" stage helps squeeze personalized patterns into different small experts (query networks). We conduct thorough experiments on many benchmarks, e.g., ChestX-ray14, CheXpert, Vindr-CXR, Shenzhen, Open-I and SIIM-ACR Pneumothorax, verifying the effectiveness of UniChest over a range of baselines, and release our codes and pre-training models at https://github.com/Elfenreigen/UniChest.

Binjie Qin, Haohao Mao, Ruipeng Zhang et al.

Video decomposition is very important to extract moving foreground objects from complex backgrounds in computer vision, machine learning, and medical imaging, e.g., extracting moving contrast-filled vessels from the complex and noisy backgrounds of X-ray coronary angiography (XCA). However, the challenges caused by dynamic backgrounds, overlapping heterogeneous environments and complex noises still exist in video decomposition. To solve these problems, this study is the first to introduce a flexible visual working memory model in video decomposition tasks to provide interpretable and high-performance hierarchical deep architecture, integrating the transformative representations between sensory and control layers from the perspective of visual and cognitive neuroscience. Specifically, robust PCA unrolling networks acting as a structure-regularized sensor layer decompose XCA into sparse/low-rank structured representations to separate moving contrast-filled vessels from noisy and complex backgrounds. Then, patch recurrent convolutional LSTM networks with a backprojection module embody unstructured random representations of the control layer in working memory, recurrently projecting spatiotemporally decomposed nonlocal patches into orthogonal subspaces for heterogeneous vessel retrieval and interference suppression. This video decomposition deep architecture effectively restores the heterogeneous profiles of intensity and the geometries of moving objects against the complex background interferences. Experiments show that the proposed method significantly outperforms state-of-the-art methods in accurate moving contrast-filled vessel extraction with excellent flexibility and computational efficiency.

Ruipeng Zhang, Ya-Chien Chang, Sicun Gao

The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt methods have also been shown to struggle with performance-critical control problems in practice, where non-MaxEnt algorithms can successfully learn. In this work, we analyze how the trade-off between robustness and optimality affects the performance of MaxEnt algorithms in complex control tasks: while entropy maximization enhances exploration and robustness, it can also mislead policy optimization, leading to failure in tasks that require precise, low-entropy policies. Through experiments on a variety of control problems, we concretely demonstrate this misleading effect. Our analysis leads to better understanding of how to balance reward design and entropy maximization in challenging control problems.

Tao Wang, Ruipeng Zhang, Sicun Gao

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show that the more critical factor is the enhanced value estimation accuracy from more value update steps in each iteration. To demonstrate, we show that by simply increasing the number of value update steps per iteration, vanilla policy gradient itself can achieve performance comparable to or better than PPO in all the standard continuous control benchmark environments. Importantly, this simple change to vanilla policy gradient is significantly more robust to hyperparameter choices, opening up the possibility that RL algorithms may still become more effective and easier to use.

Ruipeng Zhang, Hongzhan Yu, Ya-Chien Chang et al.

Quadruped locomotion provides a natural setting for understanding when model-free learning can outperform model-based control design, by exploiting data patterns to bypass the difficulty of optimizing over discrete contacts and the combinatorial explosion of mode changes. We give a principled analysis of why imitation learning with quadrupeds can be inherently effective in a small data regime, based on the structure of its limit cycles, Poincaré return maps, and local numerical properties of neural networks. The understanding motivates a new imitation learning method that regulates the alignment between variations in a latent space and those over the output actions. Hardware experiments confirm that a few seconds of demonstration is sufficient to train various locomotion policies from scratch entirely offline with reasonable robustness.

Kendall Schmidt, Benjamin Bearce, Ken Chang et al.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location.

Qinwei Xu, Ruipeng Zhang, Ya Zhang et al.

Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from multiple source domains in order to generalize to unseen target domains. This paper introduces a novel Fourier-based perspective for domain generalization. The main assumption is that the Fourier phase information contains high-level semantics and is not easily affected by domain shifts. To force the model to capture phase information, we develop a novel Fourier-based data augmentation strategy called amplitude mix which linearly interpolates between the amplitude spectrums of two images. A dual-formed consistency loss called co-teacher regularization is further introduced between the predictions induced from original and augmented images. Extensive experiments on three benchmarks have demonstrated that the proposed method is able to achieve state-of-the-arts performance for domain generalization.