…Bridging Words and Colors for Conditional Image Grading (2026) What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment? (2026) Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try…
…AI-generated summary Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user…
…it feels very similar to dreamer, learning a latent dynamics model from pixels and using imagined futures for planning, but wams push the explicit coupling of dynamics and action generation, which could…
…AI-generated summary Large Vision-Language Models (LVLMs) often suffer from hallucinations , generating descriptions that include visual details absent from the input image. Recent preference alignment methods typically rely on supervision distilled…
…AI-generated summary Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human-like perception. For navigation…
…AI-generated summary Generalizable novel view synthesis aims to render unseen views from uncalibrated input images without requiring per-scene optimization. Recent feed-forward approach es based on 3D Gaussian Splatting have…
…AI-generated summary Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post…
…AI-generated summary Embodied intelligence requires high-fidelity simulation environments to support perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose…
…and Image for Unified Retrieval (2026) Think Harder and Don't Overlook Your Options: Revisiting Issue-Commit Linking with LLM-Assisted Retrieval (2026) Probing Privacy Leaks in LLM-based Code Generation via…
…AI-generated summary Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to…