Recent advances in multimodal foundation models and agent systems have driven GUI agents from single-platform task execution toward cross-platform interaction. However, building mu...
We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder subtasks. We model them hierarc...
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt th...
Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Recent syllabic tokenization met...
Research dissemination, turning a paper into a poster, a talk video, and a blog post, is still a manual last mile. Prior automation treats each artifact in isolation that each re-e...
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises ...
Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must groun...
Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong rea...
Geometry-conditioned 3D scene generation enables the creation of 3D environments from user-provided geometry, offering direct control over scene structure and object layout. To gen...
Vision-Language-Action (VLA) models acquire broad embodied capabilities through large-scale pretraining, yet their generalization remains far more fragile than that of LLMs and VLM...
Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learni...
Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising framework for...
Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to...
Concept erasure aims to remove a target concept from a representation while preserving the other information encoded in it. This is difficult because representations encode many co...
A key challenge in Arabic NLP is the scarcity of dialectal data relative to Modern Standard Arabic (MSA), causing LLMs to overproduce MSA and struggle with dialectally accurate gen...
The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc. While Diffusio...
Multimodal large language models (MLLMs) generate responses autoregressively, integrating visual and linguistic information in an evolving context. Prior work on interpretability h...
Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder...
LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed sa...
Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success signific...
Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the land...
We introduce Vidu S1, a real-time interactive video generation model supporting voice control of digital characters. Users can control video generation content at any moment throug...
Semi-supervised semantic segmentation (SSSS) has long turned on one question, which pseudo-labels to trust, and answered it with ever more careful confidence filtering. Foundation ...
Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, nativ...