DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Checkby Ziheng Qiao, Houquan…
Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingby Mingjia Shi, Yuhao Zhou,…
EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generationby Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun…
What Makes In-context Learning Effective for Mathematical Reasoning: A Theoretical Analysisby Jiayu Liu, Zhenya Huang,…
DriveGazen: Event-Based Driving Status Recognition using Conventional Cameraby Xiaoyin YangFirst submitted to arxiv on: 16…
A Variable Occurrence-Centric Framework for Inconsistency Handling (Extended Version)by Yakoub SalhiFirst submitted to arxiv on:…
Explainable Procedural Mistake Detectionby Shane Storks, Itamar Bar-Yossef, Yayuan Li, Zheyuan Zhang, Jason J. Corso,…
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swappingby Hao Shao, Shulun Wang, Yang…
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsby Yuchen Fu, Zifeng…
RapidNet: Multi-Level Dilated Convolution Based Mobile Backboneby Mustafa Munir, Md Mostafijur Rahman, Radu MarculescuFirst submitted…