arXiv:2611.07551v1 Announce Type: new Abstract: Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further...
arXiv:2609.39563v1 Announce Type: new Abstract: Existing video language models encode sampled RGB frames independently, so a long video must either exhaust the token budget or drop the changes betwee...
MT‑WAM enhances the Fast‑WAM framework by adding complementary supervision for future 2‑D point trajectories and visual features while keeping the original training objectives. A lightweight dual‑stream branch and structured attention mask isolate motion‑specific processing, and motion‑stream tokens provide additional dynamics cues to the action expert. During inference, MT‑WAM skips future‑video prediction, using cached video and motion information to achieve higher success rates on LIBERO, LIBERO‑Plus, RoboTwin 2.0 Clean2Rand, and several real‑world tasks.
arXiv:2608. 02870v1 Announce Type: new Abstract: We introduce \ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training.
arXiv:2609.37250v1 Announce Type: cross Abstract: World-action models (WAMs) couple future visual-state prediction with action generation. By adapting video generators or image-editing models pretrai...
FlashAR is a lightweight post‑training adaptation framework that converts a pre‑trained raster‑scan autoregressive image model into a highly parallel generator using two‑way next‑token prediction. It preserves the original training objective by keeping the horizontal head for row‑wise prediction and adding a lightweight vertical head for column‑wise prediction, with a learnable fusion gate to combine the two predictions. A two‑stage adaptation pipeline—first initializing the vertical head from the pre‑trained model and then jointly fine‑tuning—yields up to a 22.9× speedup for 512×512 image generation while using only 0.05% of the original training data.
arXiv:2610.26903v1 Announce Type: new Abstract: Action-conditioned world models support planning and policy evaluation by predicting future states. However, learning an accurate one-step predictor ca...
arXiv:2610.06942v1 Announce Type: new Abstract: Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time serie...
SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
The paper introduces the Continuous Memory Machine (CMM), a recurrent neural network that uses separate matrix-valued short‑term and long‑term memory states. Short‑term memory tracks recent neural activity with neuron‑level models for rapid computation, while long‑term memory stores information for later use; both are jointly updated by a Transformer that allows bidirectional read‑write operations. Experiments on algorithmic, in‑context learning, and recurrent reasoning tasks show that CMM outperforms many baselines and generalizes better than previous memory‑augmented networks, while maintaining interpretable attention patterns from the Continuous Thought Machine.
LongVU‑TTT is a causal test‑time training method for long‑video multimodal large language models that inserts a convolutional resampler with fast‑weight updates between the vision encoder and the LLM. The fast weights adapt per video and contextualize frame features before compression, while a hybrid selector keeps explicit visual evidence for downstream reasoning. Experiments show that TTT‑Conv outperforms TTT‑MLP and bidirectional Mamba2 on MLVU, and beats attention‑ and fixed‑state recurrent resamplers on three benchmarks, achieving competitive results on five video‑understanding tasks after reducing 512 frames to 128 LLM frames.
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.