PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

• URL: http://arxiv.org/abs/2603.25730v1
• Date: Thu, 26 Mar 2026 17:59:05 GMT
• Title: PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
• Abstract summary: PackForcing generates coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU.<n>It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal (5s to 120s) operating effectively either zero-shot or trained on merely 5-second clips.
• Score: 46.18482046594169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that efficiently manages the generation history through a novel three-partition KV-cache strategy. Specifically, we categorize the historical context into three distinct types: (1) Sink tokens, which preserve early anchor frames at full resolution to maintain global semantics; (2) Mid tokens, which achieve a massive spatiotemporal compression (32x token reduction) via a dual-branch network fusing progressive 3D convolutions with low-resolution VAE re-encoding; and (3) Recent tokens, kept at full resolution to ensure local temporal coherence. To strictly bound the memory footprint without sacrificing quality, we introduce a dynamic top-$k$ context selection mechanism for the mid tokens, coupled with a continuous Temporal RoPE Adjustment that seamlessly re-aligns position gaps caused by dropped tokens with negligible overhead. Empowered by this principled hierarchical context compression, PackForcing can generate coherent 2-minute, 832x480 videos at 16 FPS on a single H200 GPU. It achieves a bounded KV cache of just 4 GB and enables a remarkable 24x temporal extrapolation (5s to 120s), operating effectively either zero-shot or trained on merely 5-second clips. Extensive results on VBench demonstrate state-of-the-art temporal consistency (26.07) and dynamic degree (56.25), proving that short-video supervision is sufficient for high-quality, long-video synthesis. https://github.com/ShandaAI/PackForcing

Related papers

• TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment [51.33418612284208]
  We propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation.<n>Gated Recall with Attention-Diversity Balancing selects long-range memory frames using a gated score.<n>TAME lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution.
  arXiv  Detail & Related papers  (2026-06-11T08:16:08Z)
• Small Vision-Language Models are Smart Compressors for Long Video Understanding [73.65465038390771]
  Long-form video understanding relies on intent-driven efficiency rather than greedily padded context.<n>We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding.<n>Tests show Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency.
  arXiv  Detail & Related papers  (2026-04-09T11:40:25Z)
• KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study [0.0]
  We present a comprehensive study of KV-cache compression for self-forcing video generation on a Wan2.1-based Self-Forcing stack.<n>Our study covers 33 quantization and cache-policy variants, 610 prompt-level observations, and 63 benchmark-level summaries.<n>We jointly evaluate peak VRAM, runtime, realized compression ratio, VBench imaging quality, BF16-referenced fidelity (SSIM, LPIPS, PSNR), and terminal drift.
  arXiv  Detail & Related papers  (2026-03-29T01:35:16Z)
• Generative Video Compression with One-Dimensional Latent Representation [59.29493435530304]
  We introduce Generative Video Compression with One-Dimensional (1D) Latent Representation (GVC1D)<n>GVC1D encodes the video data into extreme compact 1D latent tokens conditioned on both short- and long-term contexts.<n> Experimental results indicate that GVC1D attains superior compression efficiency, surpassing previous video compression methods.
  arXiv  Detail & Related papers  (2026-03-16T14:02:17Z)
• OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer [14.628152488797356]
  OVGGT is a training-free framework that bounds both memory and compute to a fixed budget regardless of sequence length.<n>We show that OVGGT processes arbitrarily long videos within a constant VRAM envelope while achieving state-of-the-art 3D geometric accuracy.
  arXiv  Detail & Related papers  (2026-03-06T06:44:17Z)
• TeCoNeRV: Leveraging Temporal Coherence for Compressible Neural Representations for Videos [51.99176811574457]
  Implicit Neural Representations (INRs) have recently demonstrated impressive performance for video compression.<n>However, scaling to high-resolution videos while maintaining encoding efficiency remains a significant challenge.<n>We address these fundamental limitations through three key contributions.<n>We are the first hypernetwork approach to demonstrate results at 480p, 720p and 1080p on UVG, HEVC and MCL-JCV.
  arXiv  Detail & Related papers  (2026-02-18T18:59:55Z)
• Towards Holistic Modeling for Video Frame Interpolation with Auto-regressive Diffusion Transformers [95.68243351895107]
  We propose a holistic, video-centric paradigm named textbfLocal textbfDiffusion textbfForcing for textbfVideo textbfFrame textbfInterpolation (LDF-VFI)<n>Our framework is built upon an auto-regressive diffusion transformer that models the entire video sequence to ensure long-range temporal coherence.<n>LDF-VFI achieves state-of-the-art performance on challenging long-sequence benchmarks, demonstrating superior per
  arXiv  Detail & Related papers  (2026-01-21T12:58:52Z)
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache [61.57938553036056]
  We introduce PackCache, a training-free KV-cache management method that compacts the KV cache through three coordinated mechanisms.<n>In terms of efficiency, PackCache accelerates end-to-end generation by 1.7-2.2x on 48-frame long sequences.
  arXiv  Detail & Related papers  (2026-01-07T19:51:06Z)
• Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity [59.80405282381126]
  Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability.<n>We propose a training-free framework termed Sparse VideoGen (SVG) that leverages the inherent sparsity in 3D Full Attention to boost inference efficiency.<n>SVG achieves up to 2.28x and 2.33x end-to-end speedup on CogVideoX-v1.5 and HunyuanVideo, respectively, while preserving generation quality.
  arXiv  Detail & Related papers  (2025-02-03T19:29:16Z)

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.