arXiv:2607. 17625v1 Announce Type: cross Abstract: Modern video transformers typically ignore principles from primate vision and are rarely evaluated against neural data, limiting their biological interpretability.
arXiv:2609.40347v1 Announce Type: new Abstract: We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of r...
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
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:2609.06960v1 Announce Type: new Abstract: Invasive neural recordings provide high-fidelity measurements of brain activity, with signals such as intracranial EEG (iEEG) and intracortical spiking...
The paper introduces Growing Sparsity and Reduced Search (GSRS), a training‑free framework that accelerates Diffusion Transformers for video generation by progressively increasing sparsity and reusing early attention blocks to limit search space. GSRS uses Top‑p selection for adaptive sparsity and a precise evaluation scheme that computes exact attention weights with negligible overhead. Experiments on HunyuanVideo and Wan 2.1 show 1.55×–2.21× speedups while preserving generation quality comparable to full attention.
Neurons++ is a visual‑stream framework that reconstructs both static images and dynamic videos from fMRI data. It builds on the earlier Neurons model by extending from video‑only to image‑and‑video reconstruction and replacing parallel task conditioning with a serial, cortex‑inspired decoding pipeline. The approach first pre‑trains on image‑fMRI pairs for stable spatial‑semantic initialization, then fine‑tunes separately for image and video tasks, organizing fMRI representations into spatial, semantic, language‑level, and temporal cues, and achieves state‑of‑the‑art video reconstruction with competitive image results while enabling neural‑to‑visual interpretability and ROI‑guided semantic modulation.
arXiv:2608. 14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools to decompose internal representations into sparse and more interpretable features.
VETO (Video Efficient Token Optimization for Vision Language Models) is a plug‑in that reduces the quadratic cost of visual tokens in long‑video inference by applying dual‑axis compression: an intra‑frame compressor merges semantically similar tokens within each frame, and an inter‑frame compressor merges temporally redundant frames. By first compressing spatial dimensions, VETO lowers the cost of subsequent global temporal matching, surpassing single‑axis methods and achieving up to 45% faster inference on models such as LLaVA‑OneVision‑7B while maintaining or improving accuracy. The approach is universally applicable across LLaVA‑OneVision, InternVL‑2.5, and LongVA, preserving or enhancing zero‑shot accuracy even under extreme token budgets.
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:2609.36366v1 Announce Type: cross Abstract: Understanding how the brain parses actions and events from time-varying natural inputs is a central challenge in neuroscience. Recent work has used d...
Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learnable prompts at the input level. However, existing VP methods typically employ dense pixel-level prompts, which often suffer from redundant perturbations, limited generalization and energy inefficiency.
arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...