Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributionsby Quan Liu, Zhenhong Zhou, Longzhu He,…
SSRFlow: Semantic-aware Fusion with Spatial Temporal Re-embedding for Real-world Scene Flowby Zhiyang Lu, Qinghan Chen,…
Evidential Graph Contrastive Alignment for Source-Free Blending-Target Domain Adaptationby Juepeng Zheng, Yibin Wen, Jinxiao Zhang,…
On Effects of Steering Latent Representation for Large Language Model Unlearningby Dang Huu-Tien, Trung-Tin Pham,…
OWL2Vec4OA: Tailoring Knowledge Graph Embeddings for Ontology Alignmentby Sevinj Teymurova, Ernesto Jiménez-Ruiz, Tillman Weyde, Jiaoyan…
HateSieve: A Contrastive Learning Framework for Detecting and Segmenting Hateful Content in Multimodal Memesby Xuanyu…
Generating novel experimental hypotheses from language models: A case study on cross-dative generalizationby Kanishka Misra,…
VITA: Towards Open-Source Interactive Omni Multimodal LLMby Chaoyou Fu, Haojia Lin, Zuwei Long, Yunhang Shen,…
Large Language Model based Agent Framework for Electric Vehicle Charging Behavior Simulationby Junkang Feng, Chenggang…
Strong and weak alignment of large language models with human valuesby Mehdi Khamassi, Marceau Nahon,…