Zobrazeno 1 - 10
of 4 851
pro vyhledávání: '"DONG, YUE"'
Personalized conversational information retrieval (CIR) combines conversational and personalizable elements to satisfy various users' complex information needs through multi-turn interaction based on their backgrounds. The key promise is that the per
Externí odkaz:
http://arxiv.org/abs/2407.16192
Large language models (LLMs) have fundamentally transformed artificial intelligence, catalyzing recent advancements while imposing substantial environmental and computational burdens. We introduce TRAWL (Tensor Reduced and Approximated Weights for La
Externí odkaz:
http://arxiv.org/abs/2406.17261
Query expansion has been employed for a long time to improve the accuracy of query retrievers. Earlier works relied on pseudo-relevance feedback (PRF) techniques, which augment a query with terms extracted from documents retrieved in a first stage. H
Externí odkaz:
http://arxiv.org/abs/2406.07136
Autor:
Cai., Zefan, Zhang, Yichi, Gao, Bofei, Liu, Yuliang, Liu, Tianyu, Lu, Keming, Xiong, Wayne, Dong, Yue, Chang, Baobao, Hu, Junjie, Xiao, Wen
In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information through Pyramida
Externí odkaz:
http://arxiv.org/abs/2406.02069
Autor:
Chakraborty, Trishna, Shayegani, Erfan, Cai, Zikui, Abu-Ghazaleh, Nael, Asif, M. Salman, Dong, Yue, Roy-Chowdhury, Amit K., Song, Chengyu
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinf
Externí odkaz:
http://arxiv.org/abs/2406.02575
Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation. Despite defenses against malicious short questions, th
Externí odkaz:
http://arxiv.org/abs/2405.15202
Multi-band gravitational-wave (GW) standard siren observations are poised to herald a new era in the study of cosmic evolution. These observations offer higher signal-to-noise ratios and improved localizations compared to those achieved with single-b
Externí odkaz:
http://arxiv.org/abs/2404.18188
State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations, we create diagnostic datasets with subject-relation queries and adapt
Externí odkaz:
http://arxiv.org/abs/2403.18167
Autor:
Shahgir, Haz Sameen, Sayeed, Khondker Salman, Bhattacharjee, Abhik, Ahmad, Wasi Uddin, Dong, Yue, Shahriyar, Rifat
The advent of Vision Language Models (VLM) has allowed researchers to investigate the visual understanding of a neural network using natural language. Beyond object classification and detection, VLMs are capable of visual comprehension and common-sen
Externí odkaz:
http://arxiv.org/abs/2403.15952
Publikováno v:
ACM SIGGRAPH 2024 Conference Proceedings
This paper presents a novel method for exerting fine-grained lighting control during text-driven diffusion-based image generation. While existing diffusion models already have the ability to generate images under any lighting condition, without addit
Externí odkaz:
http://arxiv.org/abs/2402.11929