2 citations · 8 across the 25 of their papers we have counts for
29 papers
LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery
Kai Li, Zigan Zhou, Zhenyang Li +7
Instance-level roof-to-footprint offset (RFO) prediction is central to extracting building footprints from off-nadir imagery. Query-based pipelines commonly use high-dimensional in…
ObliCity: A Benchmark and Baseline for Roof-to-Ground Projection Displacement Correction
Kai Li, Yupeng Deng, Ligao Deng +6
Oblique-view urban remote sensing imagery inevitably exhibits geometric projection displacements between building roofs and footprints, leading to significant distortions in spatia…
Latent Block-Diffusion Temporal Point Processes: A Semi-Autoregressive Framework for Asynchronous Event Sequence Generation
Shuai Zhang, Yancheng Chen, Chuan Zhou +5
Modeling and sampling from the underlying distribution of asynchronous event sequences are crucial in various real-world applications, including social networks, medical diagnosis,…
Discrete Token Modeling for Multi-Stem Music Source Separation with Language Models
Pengbo Lyu, Xiangyu Zhao, Chengwei Liu +4
We propose a generative framework for multi-track music source separation (MSS) that reformulates the task as conditional discrete token generation. Unlike conventional approaches…
From Failure to Mastery: Generating Hard Samples for Tool-use Agents
Bingguang Hao, Zengzhuang Xu, Yuntao Wen +11
The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of r…
Renormalization Group Guided Tensor Network Structure Search
Maolin Wang, Bowen Yu, Sheng Zhang +8
Tensor network structure search (TN-SS) aims to automatically discover optimal network topologies and rank configurations for efficient tensor decomposition in high-dimensional dat…
FunReason-MT Technical Report: Advanced Data Synthesis Solution for Real-world Multi-Turn Tool-use
Zengzhuang Xu, Bingguang Hao, Zechuan Wang +14
Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems.…
Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning
Xiao Han, Zimo Zhao, Wanyu Wang +4
Recent advancements in Large Language Models (LLMs) have emphasized the critical role of fine-tuning (FT) techniques in adapting LLMs to specific tasks, especially when retraining…
Empowering Denoising Sequential Recommendation with Large Language Model Embeddings
Tongzhou Wu, Yuhao Wang, Maolin Wang +2
Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as ac…
SPARK: Adaptive Low-Rank Knowledge Graph Modeling in Hybrid Geometric Spaces for Recommendation
Binhao Wang, Yutian Xiao, Maolin Wang +4
Knowledge Graphs (KGs) enhance recommender systems but face challenges from inherent noise, sparsity, and Euclidean geometry's inadequacy for complex relational structures, critica…
Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs
Yuhao Wang, Junwei Pan, Xinhang Li +6
Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large…
Reasoning through Exploration: A Reinforcement Learning Framework for Robust Function Calling
Bingguang Hao, Zengzhuang Xu, Maolin Wang +9
The effective training of Large Language Models (LLMs) for function calling faces a critical challenge: balancing exploration of complex reasoning paths with stable policy optimiza…
Put Teacher in Student's Shoes: Cross-Distillation for Ultra-compact Model Compression Framework
Maolin Wang, Jun Chu, Sicong Xie +4
In the era of mobile computing, deploying efficient Natural Language Processing (NLP) models in resource-restricted edge settings presents significant challenges, particularly in e…
Measure Domain's Gap: A Similar Domain Selection Principle for Multi-Domain Recommendation
Yi Wen, Yue Liu, Derong Xu +9
Multi-Domain Recommendation (MDR) achieves the desirable recommendation performance by effectively utilizing the transfer information across different domains. Despite the great su…
STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation
Maolin Wang, Sheng Zhang, Ruocheng Guo +6
Recent deep sequential recommendation models often struggle to effectively model key characteristics of user behaviors, particularly in handling sequence length variations and capt…
FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement
Bingguang Hao, ZengZhuang Xu, Maolin Wang +9
The integration of large language models (LLMs) with function calling has emerged as a crucial capability for enhancing their practical utility in real-world applications. However,…
Align-GRAG: Anchor and Rationale Guided Dual Alignment for Graph Retrieval-Augmented Generation
Derong Xu, Pengyue Jia, Xiaopeng Li +9
Despite the strong abilities, large language models (LLMs) still suffer from hallucinations and reliance on outdated knowledge, raising concerns in knowledge-intensive tasks. Graph…
Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression
Jingyu Peng, Maolin Wang, Nan Wang +7
Despite substantial advancements in aligning large language models (LLMs) with human values, current safety mechanisms remain susceptible to jailbreak attacks. We hypothesize that…
MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning
Maolin Wang, Xiangyu Zhao
There has been a significant increase in the deployment of neural network models, presenting substantial challenges in model adaptation and fine-tuning. Efficient adaptation is cru…
Stepwise Reasoning Error Disruption Attack of LLMs
Jingyu Peng, Maolin Wang, Xiangyu Zhao +6
Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks…
PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images
Kai Li, Yupeng Deng, Jingbo Chen +6
Extracting polygonal building footprints from off-nadir imagery is crucial for diverse applications. Current deep-learning-based extraction approaches predominantly rely on semanti…
Scalable Dynamic Embedding Size Search for Streaming Recommendation
Yunke Qu, Liang Qu, Tong Chen +3
Recommender systems typically represent users and items by learning their embeddings, which are usually set to uniform dimensions and dominate the model parameters. However, real-w…
GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems
Sheng Zhang, Maolin Wang, Wanyu Wang +6
Transformer-based models have gained significant traction in sequential recommender systems (SRSs) for their ability to capture user-item interactions effectively. However, these m…
The 2nd Workshop on Recommendation with Generative Models
Wenjie Wang, Yang Zhang, Xinyu Lin +7
The rise of generative models has driven significant advancements in recommender systems, leaving unique opportunities for enhancing users' personalized recommendations. This works…