arXiv:2601. 21444v2 Announce Type: replace-cross Abstract: The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs).
arXiv:2609.37001v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) enable high-quality video generation but suffer from substantial inference latency, primarily attributable to the compu...
arXiv:2602. 01801v2 Announce Type: replace-cross Abstract: Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines.
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.
arXiv:2610.01785v1 Announce Type: cross Abstract: Processing long videos with Vision-Language Models (VLMs) is bottlenecked by the quadratic cost of visual tokens, making long-form inference prohibit...
arXiv:2607. 14711v1 Announce Type: cross Abstract: We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time.
arXiv:2609.16722v1 Announce Type: new Abstract: Scaling Multimodal Large Language Models (MLLMs) to long-form video understanding is bottlenecked by the explosion of visual tokens, which saturates co...
Video DeltaNet (VDN) introduces a hybrid attention mechanism for livestream video generation, combining local Softmax attention with a bidirectional linear memory branch called Video Delta Attention (VDA). VDA updates memory once per frame, integrating spatial tokens, while separate output projections and learnable gates balance the two branches. Applied to MiniMax H3, VDN achieves a 14.5× speedup over the dense baseline, completing 14.3‑second, 768p video denoising in 6.70 seconds on eight NVIDIA B200 GPUs.
arXiv:2609.23601v1 Announce Type: new Abstract: Long-video understanding must capture transient visual evidence under strict token budgets, yet existing methods compress frames, append memory tokens,...
VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.
arXiv:2608. 19920v1 Announce Type: new Abstract: A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive hardware budgets.
The paper introduces Adaptive Visual Token Pruning (AVTP), a training‑free framework that dynamically selects pruning layers and ratios for large vision‑language models (LVLMs) when processing multiple image sequences. By analyzing visual attention distributions across different LVLM architectures, AVTP adapts token retention to image importance, enabling efficient inference without relying on attention‑based computations incompatible with FlashAttention. Experiments show significant speedups—up to 2× for Qwen3VL‑8B—while preserving or even improving accuracy on multi‑image benchmarks.
UniPrefill is a prefill‑acceleration framework that works with virtually any model architecture, directly speeding up token‑level computation. It is implemented as a continuous‑batching operator and extends vLLM’s scheduling to support prefill‑decode co‑processing and tensor parallelism. The method delivers up to a 2.1× speedup in Time‑to‑First‑Token, with gains growing as concurrent requests increase.