arXiv:2604.17422v2 Announce Type: replace Abstract: Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive cost of processing dens...
arXiv:2608.28699v1 Announce Type: new Abstract: Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine...
VideoLVR introduces a method for multimodal large language models to maintain visual grounding during chain-of-thought reasoning by constructing latent visual evidence from local video regions at relevant moments. It uses a visual token prediction objective that unifies visual evidence reconstruction and text generation, allowing models to interleave text tokens with latent visual states. The approach is further extended with reinforcement learning, treating visual tokens as actions and optimizing policies with final-answer rewards, thereby improving video understanding without expanding the multimodal context.
VaME (Variational Multimodal Embeddings) introduces a framework that treats latent reasoning as a learnable distribution over trajectories, enabling autoregressive exploration in latent space guided by answer reconstruction. By augmenting embedding-token readout with a latent-fused embedding and optimizing over stochastic variational trajectories via reinforcement learning with a Semantic Decoding Reward, VaME achieves superior performance on the MMEB-V2 benchmark and reasoning-intensive tasks like MRMR. The method also delivers at least a 4.25× inference speedup compared to deterministic latent autoregressive baselines.
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.
DocHop is a new benchmark that tests multimodal large language models on integrated chart‑context reasoning within document‑style images. The benchmark presents narrative text that imposes multi‑step compositional constraints, while charts supply the data needed to answer questions grounded in semantic reference labels. It contains 2,074 examples across six task categories, generated via a stochastic logic‑first pipeline that controls reasoning depth and visual density, and shows a large performance gap between humans (over 90% accuracy) and the best models (62.83%).
arXiv:2605.22144v2 Announce Type: replace Abstract: Existing approaches for digital short-drama production typically rely on one-shot LLM generated scripts and loosely coupled pipelines, which fail t...
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:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
arXiv:2605.16638v2 Announce Type: replace Abstract: Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this pa...
The paper introduces ViMoD, a lightweight framework that dynamically manages visual memory for multimodal large language models. ViMoD uses Deformable Aggregation of Region-wise Tokens (DART) to create content‑adaptive coarse representations linked to recoverable fine tokens, and Temporal Routing for Adaptive Contextual Evidence (TRACE) to anticipate and adjust evidence needs during reasoning. On the Qwen3‑VL‑4B model, ViMoD achieves superior performance across eight reasoning benchmarks with only a 20% visual token budget and minimal additional parameters.
arXiv:2608. 15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments.