TeHOR: Text-Guided 3D Human and Object Reconstruction with Textures
arXiv:2602.19679v1 Announce Type: cross Abstract: Joint reconstruction of 3D human and object from a single image is an active research…
DesignAsCode: Bridging Structural Editability and Visual Fidelity in Graphic Design Generation
arXiv:2602.17690v2 Announce Type: replace-cross Abstract: Graphic design generation demands a delicate balance between high visual fidelity and fine-grained structural editability.…
On the Dynamics of Observation and Semantics
arXiv:2602.18494v1 Announce Type: new Abstract: A dominant paradigm in visual intelligence treats semantics as a static property of latent representations,…
Verifying Chain-of-Thought Reasoning via Its Computational Graph
arXiv:2510.09312v2 Announce Type: replace-cross Abstract: Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box),…
Author Correction: Mask-prior-guided denoising diffusion improves inverse protein folding
Nature Machine Intelligence, Published online: 24 February 2026; doi:10.1038/s42256-026-01209-9 Author Correction: Mask-prior-guided denoising diffusion improves inverse protein folding
AI and the long game
Nature Machine Intelligence, Published online: 24 February 2026; doi:10.1038/s42256-026-01203-1 Almost 10 years ago, AlphaGo defeated one of the world’s best…
Anatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks
arXiv:2602.15997v2 Announce Type: replace-cross Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across…
Simplifying Outcomes of Language Model Component Analyses with ELIA
arXiv:2602.18262v1 Announce Type: cross Abstract: While mechanistic interpretability has developed powerful tools to analyze the internal workings of Large Language…
PRISM: Parallel Reward Integration with Symmetry for MORL
arXiv:2602.18277v1 Announce Type: cross Abstract: This work studies heterogeneous Multi-Objective Reinforcement Learning (MORL), where objectives can differ sharply in temporal…
Wink: Recovering from Misbehaviors in Coding Agents
arXiv:2602.17037v2 Announce Type: replace-cross Abstract: Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the…