4 citations · 5 across the 7 of their papers we have counts for
7 papers
LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation
Zan Wang, Yunhe Feng, Dong Nie +4
Referring surgical video instrument segmentation (RSVIS) aims at segmenting the instrument in a surgical video, given a textual description. Despite recent progress, current models…
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Hanzhi Zhang, Qiao Zhang, Qinglei Cao +4
Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores. Existing me…
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
Hanzhi Zhang, Heng Fan, Kewei Sha +2
Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention metho…
Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models
Hanzhi Zhang, Sumera Anjum, Heng Fan +3
Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for…
LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Shaohua Dong, Yunhe Feng, Qing Yang +2
High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently…
S3LLM: Large-Scale Scientific Software Understanding with LLMs using Source, Metadata, and Document
Kareem Shaik, Dali Wang, Weijian Zheng +4
The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emerge…
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Shaohua Dong, Yunhe Feng, Qing Yang +3
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approa…