Pharo offers a sophisticated completion engine based on semantic heuristics, which coordinates specific fetchers within a lazy architecture. These heuristics ca...
Distributed AI systems face critical memory management challenges across computation, communication, and deployment layers. RRAM based in memory computing suffe...
The Experiment: Probing the Black Box For years, we have treated large language models LLMs as black boxes. When a model says, “I am currently thinking about c...
We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's c...
Recently, Quantum Visual Fields (QVFs) have shown promising improvements in model compactness and convergence speed for learning the provided 2D or 3D signals. ...
Nighttime color constancy remains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-A...
Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer se...
We prove tight lower bounds for online multicalibration, establishing an information-theoretic separation from marginal calibration. In the general setting wher...
Functional grasping with dexterous robotic hands is a key capability for enabling tool use and complex manipulation, yet progress has been constrained by two pe...
Referring Expression Segmentation (RES) and Comprehension (REC) respectively segment and detect the object described by an expression, while Referring Expressio...
As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferenc...
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constr...
Large language models suffer from 'hallucinations'-logical inconsistencies induced by semantic noise. We propose that current architectures operate in a 'Metric...
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view s...
Humans can effortlessly anticipate how objects might move or change through interaction--imagining a cup being lifted, a knife slicing, or a lid being closed. W...
We used machine learning and artificial intelligence: 1) to measure levels of peace in countries from news and social media and 2) to develop on-line tools that...
Agents capable of reasoning and planning in the real world require the ability of predicting the consequences of their actions. While world models possess this ...
I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machin...
One-shot prediction enables rapid adaptation of pretrained foundation models to new tasks using only one labeled example, but lacks principled uncertainty quant...
We present textsc{MineNPC-Task}, a user-authored benchmark and evaluation harness for testing memory-aware, mixed-initiative LLM agents in open-world Minecraft....
Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools...
Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, aging, and diseases. One key application is Brain Age Predicti...
MoE3D is a mixture-of-experts module designed to sharpen depth boundaries and mitigate flying-point artifacts (highlighted in red) of existing feed-forward 3D r...
Pervasive AI increasingly depends on on-device learning systems that deliver low-latency and energy-efficient computation under strict resource constraints. Liq...
