📰 Daily AI Digest

Open Source AI Platform - AI Chat with advanced features that works with every LLM

During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods.

Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic datasets. Furthermore, to evaluate the real-world performance of inverse rendering without ground truth, we propose a novel VLM-based assessment protocol measuring semantic, spatial, and temporal consistency. Combined with our toolkit, our forward renderer enables users to edit styles of AAA games from G-buffers using text prompts.

Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it.

Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of driving systems. However, adapting such models for driving tasks currently faces a critical dilemma between spatial perception and semantic reasoning. To overcome this, we propose UniDriveVLA, a Unified Driving Vision-Language-Action model based on Mixture-of-Transformers that addresses the perception-reasoning conflict via expert decoupling.