FrameForge introduces a unified image generation framework that leverages pretrained video foundation models to capture dynamic temporal relationships between conditions and targets. It employs a Mixture of Temporal Experts (MoTE) to adaptively select temporal intervals and a Chain of Temporal Reasoning (CoTR) to model transformations through latent intermediate states, guided by a reasoning-bottleneck attention mask. Experiments on DreamBench, COCO2017, and GEdit-Bench demonstrate FrameForge’s superior performance in subject-driven generation, canny-to-image generation, and image editing compared to existing methods.
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.
arXiv:2607. 08763v1 Announce Type: cross Abstract: Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences.
arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
arXiv:2609.40129v1 Announce Type: new Abstract: Reasoning through video generation offers a promising path toward visual intelligence by modeling latent visual states and their dynamics. However, cur...
ProAR introduces a goal‑oriented reasoning framework for autoregressive video models, adding goal‑frame prediction via an asymmetric attention mask and future representation self‑alignment to guide intermediate states. These mechanisms combine sparse target supervision with dense step‑wise guidance, enabling coherent, goal‑directed generation while keeping computational costs modest. Experiments demonstrate consistent performance gains across visual reasoning benchmarks and training efficiency, achieving comparable results to fully trained baselines with only 25% of the training steps.
arXiv:2608.19583v2 Announce Type: replace-cross Abstract: Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet rel...
The paper introduces Temporal Activation Injection (TAI), a post‑processing technique that reinforces temporal representations in Video Large Language Models (VideoLLMs) at inference time. By measuring the temporal divergence vector τ_l— the layer‑wise difference caused by reversing video frame order— the authors find that temporal information peaks at intermediate layers and fades toward the output. TAI injects the peak divergence back into later layers, improving temporal reasoning on three VideoLLMs across four benchmarks without affecting non‑temporal performance.
arXiv:2508. 07683v2 Announce Type: replace-cross Abstract: Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries.
The paper introduces Temporal Specification Guidance (TSG), a training‑free inference framework that uses Temporal Logic specifications to guide text‑to‑video generation. TSG evaluates visual concept traces with differentiable quantitative semantics and adjusts the denoising direction via gradient‑derived attention biases, eliminating the need for external classifiers or backpropagation through the transformer. Experiments on 220 prompts across 11 temporal constraint categories show that TSG improves specification satisfaction by 9.5–20 percentage points over classifier‑free guidance with minimal memory overhead.
arXiv:2603. 08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning.
TAME introduces a Temporal-Aware Mixture-of-Experts framework for Text-Video Retrieval that enhances CLIP-based models by incorporating frame-level structure and temporal relations. It adds sparse Mixture-of-Experts layers with frame-consistent routing, Frame-Temporal tokens for global cross-frame aggregation, and a Cross-Temporal Interaction and Aggregation module to refine sentence-video similarities. Experiments on multiple TVR benchmarks show consistent performance gains, such as a 4.0 R@1 improvement on MSR‑VTT over CLIP4Clip.
arXiv:2608. 19583v1 Announce Type: cross Abstract: Recent studies suggest that video generation models can exhibit certain forms of zero-shot visual reasoning through generated frames.