Researchers propose AlignVAR, a visual autoregressive framework for image super-resolution that addresses critical consistency problems in existing VAR models. The approach combines spatial consistency autoregression and hierarchical consistency constraints to achieve 10x faster inference with 50% fewer parameters than leading diffusion-based methods.
Researchers present Pointer-CAD, an LLM-based framework that addresses fundamental limitations in command sequence-based CAD generation by enabling explicit geometric entity selection through pointer mechanisms. The approach reduces quantization errors and supports complex operations like chamfering and filleting that prior methods cannot handle.
Researchers have introduced STAR (Separators for AutoRegressive pretraining), a method that extends Vision Mamba's input sequence length by 4x through strategic separator insertion between images. The STAR-B model achieved 83.5% accuracy on ImageNet-1k, demonstrating improved long-range dependency modeling in vision tasks.
Researchers have introduced VideoTemp-o3, a unified framework that addresses limitations in long-video understanding by combining temporal grounding and question-answering in a single agentic system. The approach uses a unified masking mechanism during training and reinforcement learning with dedicated reward signals to improve video segment localization and reduce hallucinations.
Segmind has released SegMoE, a mixture-of-experts (MoE) diffusion model designed to accelerate image generation while reducing computational overhead. The model applies MoE techniques traditionally used in large language models to the diffusion model architecture, enabling selective expert activation during inference.