TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL

• URL: http://arxiv.org/abs/2606.28016v2
• Date: Thu, 02 Jul 2026 07:14:50 GMT
• Title: TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
• Abstract summary: Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context.<n>A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions.<n>We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimize temporal decomposition and step-conditioned execution for temporally plausible AR video generation.
• Score: 72.7712729541565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation makes temporal instruction following ambiguous. A single global prompt does not specify which sub-event should be realized in each chunk, while naively switching to step-wise prompts often leads to delayed reactions, blended step semantics, and error propagation across prompt transitions. These failures are difficult to address with supervised fine-tuning or distillation alone: SFT suffers from exposure bias, while rollout-based distillation still optimizes low-level denoising or teacher-distribution matching rather than directly enforcing action ordering and prompt-transition correctness. We address these challenges with TempAct, a planner--executor reinforcement learning framework that jointly optimizes temporal decomposition and step-conditioned execution for temporally plausible AR video generation. TempAct uses an LLM planner to explore span-aware step prompts that are executable by the video model, and trains an AR diffusion executor to follow these prompts under its own generated histories. Its key mechanism is hierarchical group exploration: candidate plans form planning groups, and each plan induces an execution group of multiple continuations from a shared visual context, enabling plan-level credit assignment for long-horizon temporal outcomes and executor-level credit assignment for prompt-switch behavior. We further design hierarchical rewards that combine plan-quality and full-video temporal feedback for the planner with local transition-level step-following rewards, aesthetic regularization, and KL constraints for the executor. Experiments on Self-Forcing and LongLive show that TempAct improves temporal consistency while preserving overall visual quality.

Related papers

• HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning [51.95194664412812]
  Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks.<n>We propose Hierarchical Planning and Information Folding (HIPIF) for long-horizon LLM agent learning.<n>HIPIF trains the agent end-to-end to organize long-horizon execution around explicit subgoals while folding completed subgoal histories to reduce long-context interference.
  arXiv  Detail & Related papers  (2026-06-09T07:35:14Z)
• STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models [81.32710031596591]
  Video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames.<n>Existing methods built on vision-language models (LVLMs) often address this challenge by externalizing reasoning through chain-of-thought (CoT)<n>We propose STORMS, a two-stage framework that teaches LVLMs to reason through bounded continuous latent trajectories instead of explicit textual CoT.
  arXiv  Detail & Related papers  (2026-05-25T16:33:00Z)
• Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning [13.499744113926505]
  DRAPE is a prompt-learning framework that synthesizes continuous instance-specific soft prompts for MCIT.<n>DRAPE achieves state-of-the-art performance among representative prompt-based and LoRA-based continual-learning baselines.
  arXiv  Detail & Related papers  (2026-05-11T15:59:06Z)
• Long-Horizon Manipulation via Trace-Conditioned VLA Planning [55.80061850746898]
  LoHo-Manip is a framework that scales short-horizon VLA execution to long-horizon instruction following via a dedicated task-management VLM.<n>LoHo-Manip predicts a progress-aware remaining plan that combines a subtask sequence with an explicit done + remaining split as lightweight language memory.<n>The executor VLA is adapted to condition on the rendered trace, thereby turning long-horizon decision-making into repeated local control.
  arXiv  Detail & Related papers  (2026-04-23T17:59:04Z)
• StreamVLA: Breaking the Reason-Act Cycle via Completion-State Gating [8.031311182554981]
  Long-horizon robotic manipulation requires bridging the gap between high-level planning and low-level control.<n>Current Vision-Language-Action models often entangle these processes, performing redundant multimodal reasoning at every timestep.<n>We present StreamVLA, a dual-system architecture that unifies textual task decomposition, visual goal imagination, and continuous action generation within a single parameter-efficient backbone.
  arXiv  Detail & Related papers  (2026-02-01T08:51:17Z)
• Open-Vocabulary Spatio-Temporal Scene Graph for Robot Perception and Teleoperation Planning [55.90805559207812]
  In dynamic remote scenes, transmission latency during bidirectional communication creates gaps between remote perceived states and operator intent.<n>We present a representation that enriches open-vocabulary perception with temporal dynamics and lightweight latency annotations.<n>We show that our method achieves 74 percent node accuracy on the Replica benchmark, outperforming Concept.Graph.
  arXiv  Detail & Related papers  (2025-09-27T04:31:24Z)
• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos [32.71627274876863]
  We address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual observations.<n>Previous work has mainly relied on text-level supervision to bridge the gap between observed states and unobserved actions, but it struggles with capturing intricate temporal relationships among actions.<n>We propose the Masked Temporal Interpolation Diffusion Diffusion model that introduces a latent space temporal temporal module within the diffusion model.
  arXiv  Detail & Related papers  (2025-07-04T08:54:59Z)
• Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks [12.239868705130178]
  We propose a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL) Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options.
  arXiv  Detail & Related papers  (2024-10-03T11:10:37Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.