542 citations · 974 across the 10 of their papers we have counts for
11 papers
PipeSwift: Revisiting Pipeline Parallelism for Large-Scale Completion-Oriented Agentic LLM Serving
Shiju Wang, Fei Ren, Fangcheng Fu +4
LLM agents execute long-horizon workflows where each model response determines the progress of subsequent tool interactions and environment transitions. Unlike chatbot serving, whe…
When Entropy Is Not Enough: Reclaiming Lost Semantics in LLM Output Length Prediction
Feiyang Ren, Shengtao Wen, Lingbing Guo +6
Efficient LLM serving is often bottlenecked by the need to pad sequences to a fixed maximum length, and this wastes compute and degrades throughput. Output length prediction enable…
HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression
Yuxuan Yang, Feiyang Ren, Bowen Zeng +4
Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.g., Top- nucleus sampling) offer superior accuracy by dynamically fluctuating me…
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
Jun Zhang, Yicheng Ji, Feiyang Ren +7
Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token d…
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference
Bowen Zeng, Feiyang Ren, Jun Zhang +4
Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches…
ES-dLLM: Efficient Inference for Diffusion Large Language Models by Early-Skipping
Zijian Zhu, Fei Ren, Zhanhong Tan +1
Diffusion large language models (dLLMs) are emerging as a promising alternative to autoregressive models (ARMs) due to their ability to capture bidirectional context and the potent…
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
Xianya Fang, Feiyang Ren, Xiang Chen +4
Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this…
SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
Jiacheng Liu, Chang Zou, Yuanhuiyi Lyu +4
Diffusion models have revolutionized high-fidelity image and video synthesis, yet their computational demands remain prohibitive for real-time applications. These models face two f…
DELIA: Diversity-Enhanced Learning for Instruction Adaptation in Large Language Models
Yuanhao Zeng, Fei Ren, Xinpeng Zhou +2
Although instruction tuning is widely used to adjust behavior in Large Language Models (LLMs), extensive empirical evidence and research indicates that it is primarily a process wh…
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
Ye Jia, Yu Zhang, Ron J. Weiss +8
We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen d…
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
Yuxuan Wang, Daisy Stanton, Yu Zhang +7
In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The emb…