AnchorPrune: Cutting Costs in Vision-Language Models
AnchorPrune introduces a new way to optimize large vision-language models, preserving performance while reducing inference costs by focusing on relevance-anchored contextual expansion.
Read the full articleYou might also wanna read
DatBench: A New Framework for More Faithful and Efficient Vision-Language Model Evaluation
Empirical evaluation serves as the primary compass guiding research progress in foundation models. Despite a large body of work focused on t
arxiv.org·6mo ago
PromptEmbedder: A Dual-LLM Framework for Efficient, Architecture-Agnostic Text Embedding
Large Language Models (LLMs) have demonstrated remarkable efficacy in text embedding, yet current adaptation methods like LoRA face signific
arxiv.org·1mo agoBreaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
Article URL: Comments URL: Points: 11 # Comments: 1
FlashAttention-T: Towards Tensorized Attention
Article URL: Comments URL: Points: 9 # Comments: 0
ELSA3D: Structured Text-3D Reasoning
ELSA3D revolutionizes unified 3D models with elastic semantic anchoring, achieving SOTA performance in 3D generation and captioning while ha
Ouro: Looped Language Models That Build Reasoning into Pre-Training Through Latent Space Iteration
Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-tr
arxiv.org·6mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.