11 citations · 20 across the 8 of their papers we have counts for
9 papers
POP: Online Structural Pruning Enables Efficient Inference of Large Foundation Models
Yi Chen, Wonjin Shin, Shuhong Liu +6
Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during inference, overlooking spars…
Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals
Moritz Vandenhirtz, Kaveh Hassani, Shervin Ghasemlou +5
Sequential recommender systems rank relevant items by modeling a user's interaction history and computing the inner product between the resulting user representation and stored ite…
DynSplit-KV: Dynamic Semantic Splitting for KVCache Compression in Efficient Long-Context LLM Inference
Jiancai Ye, Jun Liu, Qingchen Li +5
Although Key-Value (KV) Cache is essential for efficient large language models (LLMs) inference, its growing memory footprint in long-context scenarios poses a significant bottlene…
DTN: Deep Multiple Task-specific Feature Interactions Network for Multi-Task Recommendation
Yaowen Bi, Yuteng Lian, Jie Cui +14
Neural-based multi-task learning (MTL) has been successfully applied to many recommendation applications. However, these MTL models (e.g., MMoE, PLE) did not consider feature inter…
Adaptive loose optimization for robust question answering
Jie Ma, Pinghui Wang, Zewei Wang +4
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (…
Benchmarking LF-MMI, CTC and RNN-T Criteria for Streaming ASR
Xiaohui Zhang, Frank Zhang, Chunxi Liu +8
In this work, to measure the accuracy and efficiency for a latency-controlled streaming automatic speech recognition (ASR) application, we perform comprehensive evaluations on thre…
Efficient Dynamic WFST Decoding for Personalized Language Models
Jun Liu, Jiedan Zhu, Vishal Kathuria +1
We propose a two-layer cache mechanism to speed up dynamic WFST decoding with personalized language models. The first layer is a public cache that stores most of the static part of…
Training ASR models by Generation of Contextual Information
Kritika Singh, Dmytro Okhonko, Jun Liu +8
Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales,…
Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
Tianxing He, Jun Liu, Kyunghyun Cho +4
In this work, we study how the finetuning stage in the pretrain-finetune framework changes the behavior of a pretrained neural language generator. We focus on the transformer encod…