Found 130 document(s)
Page 3 of 9
-
Modern industrial ranking systems increasingly adopt generative recommendation (GR) paradigms, in which user behavior sequences and non-sequential (NS) features are tokenized and jointly modeled by Transformer-style back...
-
Simulating economic responses at society scale requires agents whose decisions reflect household circumstances. We introduce S$^2$-MAS, a society-scale multi-agent simulation framework built on 500 million synthetic hous...
-
Egocentric action transfer aims to decouple the semantic action from egocentric observations and reproduce them in new visual contexts, enabling scalable world simulation, embodied policy learning, and robotic data gener...
-
Effective manipulation requires a policy to capture not only about the current scene geometry, but also about how that geometry will evolve under interaction. Existing approaches either augment policies with geometric in...
-
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by letting the model active...
-
World-Action Models (WAMs) have emerged as a promising paradigm for embodied generalist policies by jointly modeling future world evolution and robot actions across diverse manipulation tasks. However, representing diver...
-
We study variance reduction for non-convex optimization when gradient evaluations return with a delay. The server can update the parameter while earlier evaluations remain unfinished. We first analyze an ordered recursiv...
-
Modeling lifetime user behavior sequences is essential for capturing long-range preferences in industrial recommendation, yet sequences containing up to 100K interactions make target-aware ranking prohibitively expensive...
-
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage become the dominant cost...
-
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not onl...
-
Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view observations remains...
-
Predicting molecular magnetic properties often requires costly electronic-structure calculations that account for spin-orbit coupling. Inspired by the spinor nature of the underlying electronic states, we introduce eSpin...
-
Large language models increasingly automate optimization modeling from natural language problems, producing written mathematics, solver code and a returned report. Verifying one optimization problem across these artifact...
-
Timbre similarity is a key evaluation target for generative speech systems, including voice conversion, speaker-cloning text-to-speech, and zero-shot speech models. When the generated voice does not match the target spea...
-
Autonomous agents powered by foundation models can reason, plan, and use tools, but their fixed weights and context limits hinder sustained learning from experience over long-term deployment. While external memory system...