Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #7783

multimodal large language models

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

RESEARCH · 1 SOURCE · arXiv cs.AI

SpecLook: speculate-and-verify framework speeds up and scores agentic MLLMs

arXiv:2611.23483v1 introduces SpecLook, a training‑free three‑level speculate‑and‑verify framework for agentic multimodal LLMs that has a small model draft the agent's next visual observation (a "glimpse"), re‑answer from it, and only invokes the agent's tool loop when needed; SpecLook also produces per‑answer reliability scores without labels. Experiments on V*, HR‑Bench and POPE report that SpecLook outperforms all baselines and achieves major speedups (SpecLook: 87.2% and 86.2% mean accuracy with 7.7x and 4.7x speedups vs. DeepEyes‑7B and Thyme‑RL; SpecLook‑Fast: 9.9x and 6.3x speedups).

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Evidence order shifts multimodal LLM judgments (cross-modal evidence noncommutativity)

A new arXiv paper (arXiv:2609.26986v1) studies how the order of conflicting perceptual (image or speech) and textual evidence affects multimodal large language models. Using a paired-comparison design that fixes instructions and content but swaps source positions, the authors find that placing an image or recording after conflicting text consistently shifts model answers toward the perceptual content, a phenomenon they term cross-modal evidence noncommutativity.

7.0