2026-07-07（周二） 收录 10 篇论文：PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space；InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization；Auto: The AGI Compiler…
3D reconstruction and generation are commonly tackled by separate paradigms: pixel-based regression for reconstruction, and latent diffusion for generation. Recent works attempt to unify them in laten...
Unified models for robot manipulation aim to equip one policy with both the semantic priors of pretrained VLMs and the physical dynamics learned through future prediction. In practice, existing design...
Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded. We present Auto, a compiler that records live agent behavior, measures which ...
Dense spatial perception is essential for physical intelligence, where visual systems are expected to recover structured, metric, and actionable representations from pixel observations. Modern visual ...
Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing toke...
Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less understood. Analyzing roug...
Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we identify verification, the ability to determine th...
We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents as part of the envir...
Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensio...
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outputs for external rec...