28 citations · 29 across the 9 of their papers we have counts for
10 papers
WorldBench: Culturally Grounded Benchmark for Multilingual Agents
Leonardo Ranaldi, Sherrie Shen, Jushi Kai +1
Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, a…
Information-Aware KV Cache Compression for Long Reasoning
Jushi Kai, Zhuiri Xiao, Alexandra Birch +1
Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages. Existing KV…
Towards Compressive and Scalable Recurrent Memory
Yunchong Song, Jushi Kai, Liming Lu +2
Transformers face a quadratic bottleneck in attention when scaling to long contexts. Recent approaches introduce recurrent memory to extend context beyond the current window, yet t…
Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models
Huanyu Wang, Jushi Kai, Haoli Bai +4
Vision-Language Models (VLMs) incur substantial computational overhead and inference latency due to the large number of vision tokens introduced by high-resolution image and video…
MLP Memory: A Retriever-Pretrained Memory for Large Language Models
Rubin Wei, Jiaqi Cao, Jiarui Wang +4
Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG) p…
FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
Jushi Kai, Yixuan Wang, Boyi Zeng +4
Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilli…
Leveraging Grammar Induction for Language Understanding and Generation
Jushi Kai, Shengyuan Hou, Yusheng Huang +1
Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream t…
ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning
Yihong Tang, Zhaokai Wang, Ao Qu +11
Citywalk, a recently popular form of urban travel, requires genuine personalization and understanding of fine-grained requests compared to traditional itinerary planning. In this p…
SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully
Jushi Kai, Tianhang Zhang, Hai Hu +1
Large language models (LLMs) demonstrate great performance in text generation. However, LLMs are still suffering from hallucinations. In this work, we propose an inference-time met…
Syntax-guided Localized Self-attention by Constituency Syntactic Distance
Shengyuan Hou, Jushi Kai, Haotian Xue +5
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of…