31 citations · 91 across the 22 of their papers we have counts for
23 papers
MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR
Yangyang Ren, Haodong Zhu, Sheng Xu +4
Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models but incurs substantial costs from rollouts and policy updates. On…
Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning
Haodong Zhu, Yangyang Ren, Yanjing Li +4
Reinforcement learning (RL) finetuning significantly enhances the reasoning capabilities of large language models (LLMs), yet its effectiveness critically depends on selecting prom…
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
Haoyu Huang, Boyu Liu, Linlin Yang +6
The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sign function). However, prevai…
GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning
Yixuan Luo, Feng Qiao, Zhexiao Xiong +2
Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Althoug…
Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
Haodong Zhu, Yangyang Ren, Yanjing Li +6
Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While r…
Context Over Compute Human-in-the-Loop Outperforms Iterative Chain-of-Thought Prompting in Interview Answer Quality
Kewen Zhu, Zixi Liu, Yanjing Li +1
Behavioral interview evaluation using large language models presents unique challenges that require structured assessment, realistic interviewer behavior simulation, and pedagogica…
Squeeze10-LLM: Squeezing LLMs' Weights by 10 Times via a Staged Mixed-Precision Quantization Method
Qingcheng Zhu, Yangyang Ren, Linlin Yang +6
Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and…
CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset
Zhiming Wang, Mingze Wang, Sheng Xu +2
Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of surface changes between multi-temporal remote sensing images, detailing the categor…
P4Q: Learning to Prompt for Quantization in Visual-language Models
Huixin Sun, Runqi Wang, Yanjing Li +4
Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms…
Representation Disparity-aware Distillation for 3D Object Detection
Yanjing Li, Sheng Xu, Mingbao Lin +3
In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors. We observe that off-the-shelf KD methods manifest their efficacy only when the teacher m…
DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
Yanjing Li, Sheng Xu, Xianbin Cao +4
Neural architecture search (NAS) proves to be among the effective approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by…
Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
Shengchao Liu, Weitao Du, Yanjing Li +10
Artificial intelligence for scientific discovery has recently generated significant interest within the machine learning and scientific communities, particularly in the domains of…
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
Yanjing Li, Sheng Xu, Mingbao Lin +4
Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices. Fully-binarized ViTs (Bi-ViT) th…
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
Sheng Xu, Yanjing Li, Mingbao Lin +4
The recent detection transformer (DETR) has advanced object detection, but its application on resource-constrained devices requires massive computation and memory resources. Quanti…
Implicit Diffusion Models for Continuous Super-Resolution
Sicheng Gao, Xuhui Liu, Bohan Zeng +6
Image super-resolution (SR) has attracted increasing attention due to its wide applications. However, current SR methods generally suffer from over-smoothing and artifacts, and mos…
Uncertainty-Aware Gradient Stabilization for Small Object Detection
Huixin Sun, Yanjing Li, Linlin Yang +2
Despite advances in generic object detection, there remains a performance gap in detecting small objects compared to normal-scale objects. We reveal that conventional object locali…
Resilient Binary Neural Network
Sheng Xu, Yanjing Li, Teli Ma +5
Binary neural networks (BNNs) have received ever-increasing popularity for their great capability of reducing storage burden as well as quickening inference time. However, there is…
Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
Yanjing Li, Sheng Xu, Baochang Zhang +3
The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems…
IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors
Sheng Xu, Yanjing Li, Bohan Zeng +5
Knowledge distillation (KD) has been proven to be useful for training compact object detection models. However, we observe that KD is often effective when the teacher model and stu…
Recurrent Bilinear Optimization for Binary Neural Networks
Sheng Xu, Yanjing Li, Tiancheng Wang +6
Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an esse…
TerViT: An Efficient Ternary Vision Transformer
Sheng Xu, Yanjing Li, Teli Ma +4
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-con…
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
Xiaolong Jiang, Peizhao Li, Yanjing Li +1
In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT). Given detection responses, we formulate the frame-by-frame dat…
Two-Stream Multi-Task Network for Fashion Recognition
Peizhao Li, Yanjing Li, Xiaolong Jiang +1
In this paper, we present a two-stream multi-task network for fashion recognition. This task is challenging as fashion clothing always contain multiple attributes, which need to be…