1 citations · 2 across the 5 of their papers we have counts for
5 papers
WnW: Waxing-and-Waning KV Cache for Long-Form Speech LLMs
Yiming Yao, Chenyang Lyu, Xuanfan Ni +4
Long-form audio inputs make the KV cache the dominant memory cost of speech LLMs. Prefill-only KV compression methods permanently discard audio KV positions once evicted, with no p…
Latent Causal Void: Explicit Missing-Context Reconstruction for Misinformation Detection
Hui Li, Zhongquan Jian, Jinsong Su +1
Automatic misinformation detection performs well when deception is visible in what an article explicitly states. However, some misinformation articles remain locally coherent and o…
RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection
Hui Li, Peien Ding, Jun Li +5
Multimodal fake news video detection is a crucial research direction for maintaining the credibility of online information. Existing studies primarily verify content authenticity b…
On the Information Redundancy in Non-Autoregressive Translation
Zhihao Wang, Longyue Wang, Jinsong Su +2
Token repetition is a typical form of multi-modal problem in fully non-autoregressive translation (NAT). In this work, we revisit the multi-modal problem in recently proposed NAT m…
Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models
Bingshuai Liu, Chenyang Lyu, Zijun Min +3
The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of…