Filtering with Self-Attention and Storing with MLP: One-Layer Transformers Can Provably Acquire and Extract Knowledge
arxiv.orgยท6d
Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models
arxiv.orgยท5d
ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
arxiv.orgยท4d
TEFormer: Texture-Aware and Edge-Guided Transformer for Semantic Segmentation of Urban Remote Sensing Images
arxiv.orgยท6h
When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
arxiv.orgยท6d
Augmented Question-guided Retrieval (AQgR) of Indian Case Law with LLM, RAG, and Structured Summaries
arxiv.orgยท3d
A Markov Decision Process Framework for Early Maneuver Decisions in Satellite Collision Avoidance
arxiv.orgยท6h
Loading...Loading more...