norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers59 minutes ago
ResearchDaily Papers

AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

The paper introduces AV-GRPO, a diffusion reinforcement learning framework for joint audio-video generation, addressing issues like modality fidelity and cross-modal synchronization. It includes three modules to decouple learning signals and improve reward attribution, along with a dataset called 5DAV for systematic training.

Open original
SIGNAL FROM THE SOURCE
1
source votes
Tracking sinceSeptember 25, 20261 source votes
Momentum—More observations needed
Discussion—Read comments ↗
PublishedSeptember 24, 2026Zhiyu Xu, Weilong Yan, Yufei Shi
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

1 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This approach addresses challenges in joint audio-video generation by decoupling modality-specific learning signals and improving synchronization through specialized modules and a controlled training dataset.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

OmniEdu: Open Foundation Models for Learning and Teaching

OmniEdu is an open family of foundation models designed for K-12 education, focusing on problem solving, curriculum understanding, diagnostic reasoning, and instructional support. The models are trained on a diverse dataset of educational resources and evaluated on multiple benchmarks, showing strong performance in educational tasks.

6 days agoDaily Papers

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

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.

3 days agoDaily Papers

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

The 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.

4 days agoDaily Papers

HappyWorld-Bench: Evaluating the Reliability of World Models Under Interaction

HappyWorld-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.

4 days agoDaily Papers

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

This 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.

4 days agoDaily Papers

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

The 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.

yesterday