Daily Papers of 2025-11-06

1. Diffusion Language Models are Super Data Learners 110 upvotes, #1 of 2025-11-06
2. UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions 50 upvotes, #2 of 2025-11-06
3. LEGO-Eval: Towards Fine-Grained Evaluation on Synthesizing 3D Embodied Environments with Tool Augmentation 46 upvotes, #3 of 2025-11-06
4. CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents 20 upvotes, #4 of 2025-11-06
5. Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning 14 upvotes, #5 of 2025-11-06
6. Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects 13 upvotes, #6 of 2025-11-06
7. TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models 13 upvotes, #6 of 2025-11-06
8. LiveTradeBench: Seeking Real-World Alpha with Large Language Models 11 upvotes, #8 of 2025-11-06
9. MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity 7 upvotes, #9 of 2025-11-06
10. The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute 4 upvotes, #10 of 2025-11-06
11. Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation 3 upvotes, #11 of 2025-11-06
12. Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask 3 upvotes, #11 of 2025-11-06
13. Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper 1 upvotes, #13 of 2025-11-06

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.