Researchers introduced EditHero, described as the first benchmark for long-horizon, part-level 3D editing, with natural-language instructions and target images covering both geometry and texture, acco…
PlaceReasoner-Beta, a verifier-guided multi-agent framework from the authors of arXiv:2609.21263v1, reformulates VLSI macro placement as a closed-loop reasoning problem using a vision-language model p…
Researchers introduced Retriever, a programming framework for closed-loop robot agents that supports modules running on independent clocks from milliseconds to seconds, and demonstrated Retriever-0, a…
ConceptSMILE, a model-agnostic auditing framework, assesses the reliability of concept-based AI explanations by extending SMILE's perturbation-based logic. In a case study on retinal fundus images, Me…
An AI agent underwent a memory surgery that reduced its memory capacity from 91% to 30%, but preserved core knowledge and task performance. Post-surgery, the agent retained its ability to describe ima…
Researchers introduced Smooth Maximum Mean Discrepancy (SMMD) to improve numerical prediction accuracy in large language models by aligning predicted numeric distributions with targets using distance-…
Researchers introduced Efficient Continual Alignment (ECA), a new exemplar-free incremental learning approach for open-ended image-to-text generation that adapts alignment modules within pre-trained v…
Researchers have identified that vision-language models (VLMs) often locate relevant text in images but fail to utilize it for answering questions, a phenomenon called "localization-without-utilizatio…
Researchers introduced ToolGate, a lightweight external controller that predicts whether to execute or skip tool calls proposed by vision-language agents, addressing the pre-call control problem where…
Researchers have developed GAP3D, a diffusion-based method that aligns vision-language model latents directly to patch-level image embeddings, enabling frozen generative models to use VLMs as prompt e…
Researchers have developed Concept-Aware Fault Detection (CAFD), a learning-based method that improves fault detection in deep neural networks by integrating model-based, distance-based, and a novel c…
A developer released Cursed Browser, a tool that uses a vision-language model to read a webpage's HTML and hallucinate what the page looks like, rendering a unique visual interpretation with each load…