Found 2,471 document(s)
Page 30 of 165
-
Retrieval-augmented generation over multi-viewpoint queries must preserve distinct answers and positions from the retrieved evidence while operating under a fixed context budget. We introduce LMVU, a lightweight ranker t...
-
One-step generative models enable fast text-guided image editing, yet they often introduce unintended changes to regions that should remain unchanged. Temporal aggregation stabilizes editing fields across noise levels, b...
-
Omni-modal assistants must remember not only what users say, but also what they show and convey. Existing long-term memory benchmarks are mostly text-and-image or report a single end-to-end score, so they cannot locate w...
-
The bulk-boundary correspondence establishes a fundamental connection between bulk band topology and the emergence of boundary states, underpinning topological phenomena across electronic, acoustic, photonic, and many ot...
-
Radar heart sounds capture cardiac mechanical activity without contact, while echocardiography characterizes ventricular and valvular function. Paired measurements connect these signals to structural heart disease, yet s...
-
Analogical reasoning is widely considered a fundamental component of human intelligence. Few benchmarks are designed to explicitly test far analogical reasoning - reasoning between domains that are superficially dissimil...
-
Vision-language-action (VLA) models enable robots to perform tasks specified through natural-language instructions, but their large weight footprint challenges deployment on memory-constrained onboard platforms. Ultra-lo...
-
World Action Models (WAMs) have shown strong potential for robot manipulation by jointly learning visual dynamics and executable actions. However, their video and action objectives do not explicitly constrain the 3D geom...
-
Why large language models trained via log-loss minimization over massive and diverse datasets exhibit broad capabilities and generalizable skills is not yet fully understood. Grau-Moya et al. (ICML 2024) offer a conceptu...
-
Generative recommenders replace the retrieve-then-rank cascade with a single model: beam search over semantic item identifiers performs retrieval, and the same likelihood performs ranking. We show that this shared score ...
-
Multimodal knowledge editing aims to update visually grounded facts in Multimodal Large Language Models (MLLMs) while preserving unrelated text and visual behaviors. However, standard answer-level metrics can hide eviden...
-
Evolutionary coding agents such as AlphaEvolve are one of the notable successes in using Large Language Models (LLMs) to build AI Scientists. These agents tackle open-ended scientific problems by iteratively improving an...
-
Multimodal ocean modeling remains challenging due to substantial heterogeneity in data structures, physical semantics, and spatiotemporal characteristics across satellite imagery, gridded oceanographic fields, and buoy o...
-
Unlike question answering, where a query specifies a perceptual target, open-ended detailed captioning must determine what evidence to acquire and how to integrate it into a coherent global description. We propose Observ...
-
Long-horizon robot manipulation requires a robot to remember task-relevant information beyond its short observation window. Existing memory-augmented policies typically retrieve relevant information from history and reas...