W-RAC decouples extraction from semantic planning via structured units and LLM grouping to match traditional retrieval performance at roughly 10x lower LLM token cost.
Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
OmniSelect is a training-free, modality-adaptive token pruning framework that dynamically selects Audio-Centric, Video-Centric, or Uniform compression regimes using AudioCLIP cross-modal relevance scores and then applies adaptive fine-grained pruning within temporal groups.
citing papers explorer
-
Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
W-RAC decouples extraction from semantic planning via structured units and LLM grouping to match traditional retrieval performance at roughly 10x lower LLM token cost.
-
OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models
OmniSelect is a training-free, modality-adaptive token pruning framework that dynamically selects Audio-Centric, Video-Centric, or Uniform compression regimes using AudioCLIP cross-modal relevance scores and then applies adaptive fine-grained pruning within temporal groups.