1 citations · 3 across the 12 of their papers we have counts for
15 papers
Learning Marginal Viewpoint Utility for Budgeted Evidence Selection in RAG
Yiyang Duan, Ziqi Yu, Tiantong Wu +2
Retrieval-augmented generation over multi-viewpoint queries must preserve distinct answers and positions from the retrieved evidence while operating under a fixed context budget. W…
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
Jingguang Li, Yebo Wu, Zuyi Guo +7
Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches…
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
Yebo Wu, Han Jin, Zhijiang Guo +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual cont…
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge
Yebo Wu, Jingguang Li, Chunlin Tian +3
Federated fine-tuning enables privacy-preserving LLM adaptation but faces a critical bottleneck: the disparity between LLMs' high memory demands and edge devices' limited capacity.…
TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings
Yebo Wu, Feng Liu, Ziwei Xie +4
Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task confli…
Floe: Federated Specialization for Real-Time LLM-SLM Inference
Chunlin Tian, Kahou Tam, Yebo Wu +4
Deploying large language models (LLMs) in real-time systems remains challenging due to their substantial computational demands and privacy concerns. We propose Floe, a hybrid feder…
Elastic Mixture of Rank-Wise Experts for Knowledge Reuse in Federated Fine-Tuning
Yebo Wu, Jingguang Li, Zhijiang Guo +1
Federated fine-tuning offers a promising solution for adapting Large Language Models (LLMs) to downstream tasks while safeguarding data privacy. However, its high computational and…
Memory-Efficient Federated Fine-Tuning of Large Language Models via Layer Pruning
Yebo Wu, Jingguang Li, Chunlin Tian +2
Federated fine-tuning enables privacy-preserving Large Language Model (LLM) adaptation, but its high memory cost limits participation from resource-constrained devices. We propose…
Learning Like Humans: Resource-Efficient Federated Fine-Tuning through Cognitive Developmental Stages
Yebo Wu, Jingguang Li, Zhijiang Guo +1
Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge d…
A Survey on Federated Fine-tuning of Large Language Models
Yebo Wu, Chunlin Tian, Jingguang Li +8
Large Language Models (LLMs) have demonstrated impressive success across various tasks. Integrating LLMs with Federated Learning (FL), a paradigm known as FedLLM, offers a promisin…
Breaking the Memory Wall for Heterogeneous Federated Learning via Model Splitting
Chunlin Tian, Li Li, Kahou Tam +2
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while preserving data privacy. Ever-increasing model complexity coupled with limited memory…
Heterogeneity-Aware Coordination for Federated Learning via Stitching Pre-trained blocks
Shichen Zhan, Yebo Wu, Chunlin Tian +2
Federated learning (FL) coordinates multiple devices to collaboratively train a shared model while preserving data privacy. However, large memory footprint and high energy consumpt…
Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing
Wu Yebo, Li Li, Tian Chunlin +4
In this paper, we propose SmartFreeze, a framework that effectively reduces the memory footprint by conducting the training in a progressive manner. Instead of updating the full mo…
Bridging Memory Gaps: Scaling Federated Learning for Heterogeneous Clients
Yebo Wu, Jingguang Li, Chunlin Tian +3
Federated Learning (FL) enables multiple clients to collaboratively train a shared model while preserving data privacy. However, the high memory demand during model training severe…
Breaking the Memory Wall for Heterogeneous Federated Learning via Progressive Training
Yebo Wu, Li Li, Chengzhong Xu
This paper presents ProFL, a new framework that effectively addresses the memory constraints in FL. Rather than updating the full model during local training, ProFL partitions the…