WildShadowRemover is a framework that adapts a pretrained video diffusion model for robust in-the-wild video shadow removal using LoRA fine-tuning. It augments the frozen VAE decoder with a detail injection module and introduces a shadow‑mask‑guided frequency‑decomposed modulation module to restore high‑frequency textures while suppressing shadow artifacts, with monocular depth priors providing geometry‑aware guidance. The authors also create WildShadow, a large‑scale paired video shadow removal dataset, and show that their method outperforms existing approaches in shadow removal quality, temporal consistency, and generalization across challenging real‑world scenarios.
By Jiamin Xu, Cong Wang, Zheng Dong, Chi Wang, Renshu Gu, Weiwei Xu, Gang Xu
arXiv:2608.22869v1 Announce Type: cross
Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long...
By Lars Osterberg, Maggie Wang, Mac Schwager
The paper introduces a Cross-Subject Perceived Speech Decoding (CPSD) framework that tackles the challenge of decoding perceived speech from non‑invasive brain recordings across different subjects. CPSD uses a two‑stage training process: first, contrastive learning pre‑trains a source model on multiple subjects to capture shared representations; second, personal specialization fine‑tunes the model for a target subject by extracting consistent components and further training on that subject’s data. A Positional Encoding‑based Spatial Attention (PESA) module is added to remap MEG/EEG data into a standardized reference space, improving cross‑subject consistency. Evaluations on three datasets (Armeni 2022, PKUEEG 2025, Broderick 2018) show that CPSD outperforms baseline methods by more than 6.8%, 15.4%, and 15.8% in Top‑10 accuracy, demonstrating its effectiveness, efficiency, and robustness.
By Aoke Zhang, Bo Wang, Xihong Wu, Heping Cheng, Jing Chen
Although Speech Large Language Models (SpeechLLMs) excel at speech understanding and generation, their capacity for fine-grained, temporally aligned outputs remains underexplored. Our work addresses t...
Dialogue games represent a challenging setting where complex cognitive skills are required to accomplish tasks while coordinating with other players. Considering that language represents an interface...
Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual...
We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require...
Mixture-of-Experts (MoE) scales language models by routing each input through a small set of independently parameterized experts. We show that copying this design into convolutional networks fails for...
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounde...
Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views are sparse or target v...
Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful beha...
Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Mo...
Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting it into text may involve different generation tasks. However, most prior work on data-to-text (...
Forecasting long-range influenza-like illness (ILI) matters for public health readiness. Publicly available surveillance datasets typically pair numeric epidemiological signals with textual informatio...
Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurring in professional photography: we aim to inver...
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While Thinking-with-Video...
In high-stakes healthcare applications, machine learning models are frequently trained on data from one patient population and deployed on another, creating a distribution shift that degrades both acc...
Personalized text generation for authors and literary writing is essential for applications such as adaptive writing assistants, creative support tools, and computational literary analysis. However, e...
Vision-Language Models (VLMs) perform well on diverse vision-language tasks, but transformer-based visual encoders split images into fixed-resolution sub-images, compromising object integrity in light...
Multimodal Large Language Models (MLLMs) are increasingly deployed as multi-step agents, where explicit reasoning supports task decomposition and tool coordination but also accumulates self-generated...