35 citations · 97 across the 16 of their papers we have counts for
16 papers
ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models
Zhongyuan Wu, Jingyuan Wang, Zexuan Cheng +5
Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate div…
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Song Bai, Lidong Bing +52
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale…
Train a Unified Multimodal Data Quality Classifier with Synthetic Data
Weizhi Wang, Rongmei Lin, Shiyang Li +7
The Multimodal Large Language Models (MLLMs) are continually pre-trained on a mixture of image-text caption data and interleaved document data, while the high-quality data filterin…
Direct Multi-Token Decoding
Xuan Luo, Weizhi Wang, Xifeng Yan
Decoder-only transformers have become the standard architecture for large language models (LLMs) due to their strong performance. Recent studies suggest that, in pre-trained LLMs,…
Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources
Weizhi Wang, Yu Tian, Linjie Yang +2
The reproduction of state-of-the-art multimodal LLM pre-training faces barriers at every stage of the pipeline, including high-quality data filtering, multimodal data mixture strat…
Adaptive Layer-skipping in Pre-trained LLMs
Xuan Luo, Weizhi Wang, Xifeng Yan
Various layer-skipping methods have been proposed to accelerate token generation in large language models (LLMs). However, limited attention has been paid to a fundamental question…
Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
Weizhi Wang, Khalil Mrini, Linjie Yang +4
We propose a novel framework for filtering image-text data by leveraging fine-tuned Multimodal Language Models (MLMs). Our approach outperforms predominant filtering methods (e.g.,…
GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks
Xinlu Zhang, Yujie Lu, Weizhi Wang +7
Automatically evaluating vision-language tasks is challenging, especially when it comes to reflecting human judgments due to limitations in accounting for fine-grained details. Alt…
Augmenting Language Models with Long-Term Memory
Weizhi Wang, Li Dong, Hao Cheng +4
Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs.…
STEPS: A Benchmark for Order Reasoning in Sequential Tasks
Weizhi Wang, Hong Wang, Xifeng Yan
Various human activities can be abstracted into a sequence of actions in natural text, i.e. cooking, repairing, manufacturing, etc. Such action sequences heavily depend on the exec…
Bot or Human? Detecting ChatGPT Imposters with A Single Question
Hong Wang, Xuan Luo, Weizhi Wang +1
Large language models (LLMs) like GPT-4 have recently demonstrated impressive capabilities in natural language understanding and generation. However, there is a concern that they c…
Non-Parametric Domain Adaptation for End-to-End Speech Translation
Yichao Du, Weizhi Wang, Zhirui Zhang +4
End-to-End Speech Translation (E2E-ST) has received increasing attention due to the potential of its less error propagation, lower latency, and fewer parameters. However, the effec…
Visually-Augmented Language Modeling
Weizhi Wang, Li Dong, Hao Cheng +5
Human language is grounded on multimodal knowledge including visual knowledge like colors, sizes, and shapes. However, current large-scale pre-trained language models rely on text-…
Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement
Yichao Du, Zhirui Zhang, Weizhi Wang +3
End-to-end speech-to-text translation (E2E-ST) is becoming increasingly popular due to the potential of its less error propagation, lower latency, and fewer parameters. Given the t…
Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables
Weizhi Wang, Zhirui Zhang, Yichao Du +3
Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usual…
Task-Oriented Dialogue System as Natural Language Generation
Weizhi Wang, Zhirui Zhang, Junliang Guo +3
In this paper, we propose to formulate the task-oriented dialogue system as the purely natural language generation task, so as to fully leverage the large-scale pre-trained models…