The paper introduces GAE, a geometry-native latent space for 3D-consistent world generation. It proposes reparameterizing a geometry foundation model's features into a compact latent space that enables joint decoding of appearance, depth, cameras, and point maps, improving visual quality and 3D coherence compared to traditional methods.
This source has not updated recently. Its observation time is shown above.
The chart will appear after repeat observations. The current metric comes from the source.
21 source votesReal observations only. History before source connection is not reconstructed.
This approach could improve 3D generation tasks by providing a shared latent space that better captures geometric consistency, potentially leading to more realistic and coherent 3D environments.
The paper introduces Taste-Bench, a benchmark for evaluating an agent's 'taste' in making long-horizon decisions. It measures the ability to choose the better path in decision forks without knowing future outcomes, revealing that current models perform poorly and that taste can be improved through distillation.
4 days agoDaily PapersThe paper explores the linearity in Large Language Models (LLMs) by showing that combining inputs from different text streams leads to a superposition of next-token distributions. It suggests that this linearity is an inherent property of the Transformer architecture and can be restored through fine-tuning, allowing for generating two coherent continuations from one forward pass.
2 days agoDaily PapersThe paper introduces Document Retrieval-Aware Chunking (D-RAC), a method for efficiently processing enterprise documents by normalizing them into PDF and converting them into retrieval-optimized Markdown using a multimodal LLM. This approach preserves document structure, reduces token costs, and improves chunking efficiency compared to traditional methods.
5 days agoDaily PapersHappyWorld-Bench is a comprehensive benchmark for evaluating the reliability of generated worlds under interaction, exploring their consistency and responsiveness. It includes three tracks—video, spatial, and embodied world models—with 1,138 video prompts, 300 spatial scenes, and 254 embodied test cases. The benchmark uses human A/B comparisons and automated metrics to assess behavioral correctness and model performance across 14 video, 9 spatial, and 8 embodied systems.
5 days agoDaily PapersThis paper introduces an all-in-one multilingual scene text recognition system that uses a script-aware Mixture-of-Experts (MoE) architecture. The system, called ScriptMoE, outperforms existing methods on multilingual text recognition tasks by leveraging a large synthetic dataset and a lightweight architecture that shares a visual encoder while using script-specific experts for decoding.
5 days agoDaily PapersThe paper introduces onPanda, an interactive tool for efficiently annotating alignment data for large language models (LLMs) and agents. It uses token-level correction, allowing annotators to replace problematic tokens in model outputs, which reduces annotation time and preserves the model's natural output distribution.
5 days ago