Jingcheng Li

Haozhan Shen, Peng Liu, Jingcheng Li et al. · cmu

Recently DeepSeek R1 has shown that reinforcement learning (RL) can substantially improve the reasoning capabilities of Large Language Models (LLMs) through a simple yet effective design. The core of R1 lies in its rule-based reward formulation, which leverages tasks with deterministic ground-truth answers to enable precise and stable reward computation. In the visual domain, we similarly observe that a wide range of visual understanding tasks are inherently equipped with well-defined ground-truth annotations. This property makes them naturally compatible with rule-based reward mechanisms. Motivated by this observation, we investigate the extension of R1-style reinforcement learning to Vision-Language Models (VLMs), aiming to enhance their visual reasoning capabilities. To this end, we develop VLM-R1, a dedicated framework designed to harness RL for improving VLMs' performance on general vision-language tasks. Using this framework, we further explore the feasibility of applying RL to visual domain. Experimental results indicate that the RL-based model not only delivers competitive performance on visual understanding tasks but also surpasses Supervised Fine-Tuning (SFT) in generalization ability. Furthermore, we conduct comprehensive ablation studies that uncover a series of noteworthy insights, including the presence of reward hacking in object detection, the emergence of the "OD aha moment", the impact of training data quality, and the scaling behavior of RL across different model sizes. Through these analyses, we aim to deepen the understanding of how reinforcement learning enhances the capabilities of vision-language models, and we hope our findings and open-source contributions will support continued progress in the vision-language RL community. Our code and model are available at https://github.com/om-ai-lab/VLM-R1

Junbo Shen, Qinze Yu, Shenyang Chen et al.

Signal peptide (SP) is a short peptide located in the N-terminus of proteins. It is essential to target and transfer transmembrane and secreted proteins to correct positions. Compared with traditional experimental methods to identify signal peptides, computational methods are faster and more efficient, which are more practical for analyzing thousands or even millions of protein sequences, especially for metagenomic data. Here we present Unbiased Organism-agnostic Signal Peptide Network (USPNet), a signal peptide classification and cleavage site prediction deep learning method that takes advantage of protein language models. We propose to apply label distribution-aware margin loss to handle data imbalance problems and use evolutionary information of protein to enrich representation and overcome species information dependence.

Qianqian Zhang, Jiajia Liao, Heting Ying et al. · cmu

Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial engineering overhead, lack of standardized components, and insufficient evaluation frameworks for fair comparison. We introduce Agent Graph-based Orchestration for Reasoning and Assessment (AGORA), a flexible and extensible framework that addresses these challenges through three key contributions: (1) a modular architecture with a graph-based workflow engine, efficient memory management, and clean component abstraction; (2) a comprehensive suite of reusable agent algorithms implementing state-of-the-art reasoning approaches; and (3) a rigorous evaluation framework enabling systematic comparison across multiple dimensions. Through extensive experiments on mathematical reasoning and multimodal tasks, we evaluate various agent algorithms across different LLMs, revealing important insights about their relative strengths and applicability. Our results demonstrate that while sophisticated reasoning approaches can enhance agent capabilities, simpler methods like Chain-of-Thought often exhibit robust performance with significantly lower computational overhead. AGORA not only simplifies language agent development but also establishes a foundation for reproducible agent research through standardized evaluation protocols.

Ye Qiao, Jingcheng Li, Haocheng Xu et al.

Neural Architecture Search (NAS) is a powerful technique for discovering high-performing CNN architectures, but most existing methods rely on costly training or extensive sampling. Zero-shot NAS offers a training-free alternative by using proxies to predict architecture performance. However, existing proxies are often suboptimal -- frequently outperformed by simple metrics like parameter count or FLOPs -- and they generalize poorly across different search spaces. Moreover, current model-based proxies struggle to adapt to new operators without access to ground-truth accuracy, limiting their transferability. We propose TG-NAS, a universal, model-based zero-cost (ZC) proxy that combines a Transformer-based operator embedding generator with a Graph Convolutional Network (GCN) to predict architecture performance. Unlike prior model-based predictors, TG-NAS requires no retraining and generalizes across arbitrary search spaces. It serves as a standalone ZC proxy with strong data efficiency, robustness, and cross-space consistency. Extensive evaluations across diverse NAS benchmarks demonstrate TG-NAS's superior rank correlation and generalizability compared to existing proxies. Additionally, it improves search efficiency by up to 300x and discovers architectures achieving 93.75% CIFAR-10 accuracy on NAS-Bench-201 and 74.9% ImageNet top-1 accuracy on the DARTS space, establishing TG-NAS as a promising foundation for efficient, generalizable NAS.

Jingcheng Li, Ye Qiao, Haocheng Xu et al.

Images captured under low-light scenarios often suffer from low quality. Previous CNN-based deep learning methods often involve using Retinex theory. Nevertheless, most of them cannot perform well in more complicated datasets like LOL-v2 while consuming too much computational resources. Besides, some of these methods require sophisticated training at different stages, making the procedure even more time-consuming and tedious. In this paper, we propose a more accurate, concise, and one-stage Retinex theory based framework, RSEND. RSEND first divides the low-light image into the illumination map and reflectance map, then captures the important details in the illumination map and performs light enhancement. After this step, it refines the enhanced gray-scale image and does element-wise matrix multiplication with the reflectance map. By denoising the output it has from the previous step, it obtains the final result. In all the steps, RSEND utilizes Squeeze and Excitation network to better capture the details. Comprehensive quantitative and qualitative experiments show that our Efficient Retinex model significantly outperforms other CNN-based models, achieving a PSNR improvement ranging from 0.44 dB to 4.2 dB in different datasets and even outperforms transformer-based models in the LOL-v2-real dataset.

Jingcheng Li, Lina Yao, Binghao Li et al.

Human Activity Recognition is an important task in many human-computer collaborative scenarios, whilst having various practical applications. Although uni-modal approaches have been extensively studied, they suffer from data quality and require modality-specific feature engineering, thus not being robust and effective enough for real-world deployment. By utilizing various sensors, Multi-modal Human Activity Recognition could utilize the complementary information to build models that can generalize well. While deep learning methods have shown promising results, their potential in extracting salient multi-modal spatial-temporal features and better fusing complementary information has not been fully explored. Also, reducing the complexity of the multi-modal approach for edge deployment is another problem yet to resolve. To resolve the issues, a knowledge distillation-based Multi-modal Mid-Fusion approach, DMFT, is proposed to conduct informative feature extraction and fusion to resolve the Multi-modal Human Activity Recognition task efficiently. DMFT first encodes the multi-modal input data into a unified representation. Then the DMFT teacher model applies an attentive multi-modal spatial-temporal transformer module that extracts the salient spatial-temporal features. A temporal mid-fusion module is also proposed to further fuse the temporal features. Then the knowledge distillation method is applied to transfer the learned representation from the teacher model to a simpler DMFT student model, which consists of a lite version of the multi-modal spatial-temporal transformer module, to produce the results. Evaluation of DMFT was conducted on two public multi-modal human activity recognition datasets with various state-of-the-art approaches. The experimental results demonstrate that the model achieves competitive performance in terms of effectiveness, scalability, and robustness.

Ziqi Xu, Jingcheng Li, Yanjun Pan et al.

Cooperative vehicle platooning significantly improves highway safety, fuel efficiency, and traffic flow. In this model, a set of vehicles move in line formation and coordinate acceleration, braking, and steering using a combination of physical sensing and vehicle-to-vehicle (V2V) messaging. The authenticity and integrity of the V2V messages are paramount to safety. For this reason, recent V2V and V2X standards support the integration of a PKI. However, a PKI cannot bind a vehicle's digital identity to the vehicle's physical state (location, velocity, etc.). As a result, a vehicle with valid cryptographic credentials can impact platoons from a remote location. In this paper, we seek to provide the missing link between the physical and the digital world in the context of vehicle platooning. We propose a new access control protocol we call Proof-of-Following (PoF) that verifies the following distance between a candidate and a verifier. The main idea is to draw security from the common, but constantly changing environment experienced by the closely traveling vehicles. We use the large-scale fading effect of ambient RF signals as a common source of randomness to construct a {\em PoF} primitive. The correlation of large-scale fading is an ideal candidate for the mobile outdoor environment because it exponentially decays with distance and time. We evaluate our PoF protocol on an experimental platoon of two vehicles in freeway, highway, and urban driving conditions. We demonstrate that the PoF withstands both the pre-recording and following attacks with overwhelming probability.