arXiv:2601. 01095v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored.
As generative multimedia evolves from static image synthesis to complex, interleaved visual narratives, a foundational bottleneck has emerged: the judgment crisis. While human perception naturally synthesizes the temporal and logical flow of a story, automated evaluation systems remain largely "blind" to sequential continuity, often failing to distinguish between a coherent narrative and a semantically shuffled or contradictory sequence.
arXiv:2608.29621v1 Announce Type: cross Abstract: Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt con...
Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumulates self-generated...
arXiv:2608.28633v1 Announce Type: cross Abstract: Generative AI systems increasingly mediate cultural adaptation, but their cultural decisions are often hidden inside prompts, transient model plans,...
arXiv:2408.11827v2 Announce Type: replace Abstract: Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies...
arXiv:2604. 14888v3 Announce Type: replace-cross Abstract: Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear.
arXiv:2608.22963v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool...
arXiv:2609.02000v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess fina...
The paper investigates how listeners decide to preserve or revise their understanding when a speaker refers to a scene they cannot see. It introduces a data‑driven framework for turn‑by‑turn preserve/revise decisions and compares four theory‑driven revision strategies. The study finds that a mismatch‑driven policy destabilizes grounding, while an uncertainty‑sensitive policy balances preservation and revision, leading to coherent understanding that aligns with conceptual pact theory.
Vision-language models (VLMs) are increasingly evaluated on complex image and video understanding tasks, yet conventional metrics primarily assess final-answer quality and reveal little about how diff...
arXiv:2606. 27598v1 Announce Type: cross Abstract: Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail.