LLM Digest

Story

arxiv_cs_lg · Nov 10, 2026 · paper

Source brief

C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference

arxiv.orgNov 10, 2026
original source linked

In brief

Visual Question Answering (VQA) imposes substantial computational overhead on vision-language models (VLMs), motivating model-agnostic input reduction methods that can be readily applied across diverse VLMs, including in black-box settings. Simply enforcing a visual-token cap red

Continues in

Diffusion Language — open the evidence trace →

Feed lens

evaluation

Read the original at arxiv.org →Open in live feed Read that day’s brief

C$^2$-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference

Earlier in this thread 4 items

EffComp: Efficient Prompt Compression via Hybrid Reinforcement & Supervised Learning

MatMoE: Matryoshka Mixture-of-Experts with Dynamic Mixed-Precision Quantization for Efficient Inference

Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models

D3Tree: Learning to Prune Block-Diffusion Draft Trees for Efficient Verification