Publications (19)
MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement
Weitao Jia, Jinghui Lu, Haiyang Yu +17
Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, s…
Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs
Kaixin Peng, Mengyang Zhao, Haiyang Yu +2
As the oldest mature writing system, Oracle Bone Script (OBS) has long posed significant challenges for archaeological decipherment due to its rarity, abstractness, and pictographi…
EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models
Haiyang Yu, Mengyang Zhao, Jinghui Lu +8
Video subtitles play a crucial role in short videos and movies, as they not only help models better understand video content but also support applications such as video translation…
From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation
Ke Niu, Haiyang Yu, Zhuofan Chen +4
Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent adv…
Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning
Jinghui Lu, Haiyang Yu, Siliang Xu +9
Recent advancements in reasoning have significantly enhanced the capabilities of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) across diverse tasks. How…
ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
Ke Niu, Haiyang Yu, Mengyang Zhao +6
Person re-identification (Re-ID) is a crucial task in computer vision, aiming to recognize individuals across non-overlapping camera views. While recent advanced vision-language mo…
OmniPT: Unleashing the Potential of Large Vision Language Models for Pedestrian Tracking and Understanding
Teng Fu, Mengyang Zhao, Ke Niu +2
LVLMs have been shown to perform excellently in image-level tasks such as VQA and caption. However, in many instance-level tasks, such as visual grounding and object detection, LVL…
EAFormer: Scene Text Segmentation with Edge-Aware Transformers
Haiyang Yu, Teng Fu, Bin Li +1
Scene text segmentation aims at cropping texts from scene images, which is usually used to help generative models edit or remove texts. The existing text segmentation methods tend…
Mismatched estimation of non-symmetric rank-one matrices corrupted by structured noise
Teng Fu, YuHao Liu, Jean Barbier +3
We study the performance of a Bayesian statistician who estimates a rank-one signal corrupted by non-symmetric rotationally invariant noise with a generic distribution of singular…
The Role of Rank in Mismatched Low-Rank Symmetric Matrix Estimation
Panpan Niu, Yuhao Liu, Teng Fu +3
We investigate the performance of a Bayesian statistician tasked with recovering a rank-\(k\) signal matrix \(\bS \bS^{\top} \in \mathbb{R}^{n \times n}\), corrupted by element-wis…
Capacity-achieving sparse superposition codes with spatially coupled VAMP decoder
Yuhao Liu, Teng Fu, Jie Fan +3
Sparse superposition (SS) codes provide an efficient communication scheme over the Gaussian channel, utilizing the vector approximate message passing (VAMP) decoder for rotational…
CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
Ke Niu, Zhuofan Chen, Haiyang Yu +5
Computer-Aided Design (CAD) plays a pivotal role in industrial manufacturing. Orthographic projection reasoning underpins the entire CAD workflow, encompassing design, manufacturin…
Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
Ke Niu, Haiyang Yu, Xuelin Qian +3
Existing person re-identification (Re-ID) methods principally deploy the ImageNet-1K dataset for model initialization, which inevitably results in sub-optimal situations due to the…
Sparse superposition codes with rotational invariant coding matrices for memoryless channels
YuHao Liu, Teng Fu, Jean Barbier +1
We recently showed in [1] the superiority of certain structured coding matrices ensembles (such as partial row-orthogonal) for sparse superposition codes when compared with purely…
IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning
Mengyang Zhao, Teng Fu, Haiyang Yu +2
Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language…
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
Yuchuan Wu, Minghan Zhuo, Teng Fu +3
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes sc…
CrowdTrack: A Benchmark for Difficult Multiple Pedestrian Tracking in Real Scenarios
Teng Fu, Yuwen Chen, Zhuofan Chen +3
Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category.…
DeNoising-MOT: Towards Multiple Object Tracking with Severe Occlusions
Teng Fu, Xiaocong Wang, Haiyang Yu +3
Multiple object tracking (MOT) tends to become more challenging when severe occlusions occur. In this paper, we analyze the limitations of traditional Convolutional Neural Network-…
Sparse superposition codes under VAMP decoding with generic rotational invariant coding matrices
TianQi Hou, YuHao Liu, Teng Fu +1
Sparse superposition codes were originally proposed as a capacity-achieving communication scheme over the gaussian channel, whose coding matrices were made of i.i.d. gaussian entri…