Large Language Model
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm.
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
This dual approach bridges the semantic gap between visual and textual data, thereby improving the model's ability to process and interpret information from multiple images effectively.
Preference Learning Algorithms Do Not Learn Preference Rankings
Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited.
VLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
Compositionality is still a challenging problem.
SSDM: Scalable Speech Dysfluency Modeling
However, there are three challenges.
What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation
We select a representative subset consisting of 22 datasets and propose it as the MESS benchmark.
Transfer Q: Principled Decoding for LLM Alignment
Aligning foundation models is essential for their safe and trustworthy deployment.