Daily Papers of 2025-08-04

1. Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training 82 upvotes, #1 of 2025-08-04
2. Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models 61 upvotes, #2 of 2025-08-04
3. PixNerd: Pixel Neural Field Diffusion 49 upvotes, #3 of 2025-08-04
4. 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding 15 upvotes, #4 of 2025-08-04
5. Trainable Dynamic Mask Sparse Attention 14 upvotes, #5 of 2025-08-04
6. SWE-Exp: Experience-Driven Software Issue Resolution 12 upvotes, #6 of 2025-08-04
7. SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution 10 upvotes, #7 of 2025-08-04
8. MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks 9 upvotes, #8 of 2025-08-04
9. Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges 9 upvotes, #8 of 2025-08-04
10. Multimodal Referring Segmentation: A Survey 8 upvotes, #10 of 2025-08-04
11. Investigating Hallucination in Conversations for Low Resource Languages 6 upvotes, #11 of 2025-08-04
12. SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation 6 upvotes, #11 of 2025-08-04
13. IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation 5 upvotes, #13 of 2025-08-04
14. Multi-Agent Game Generation and Evaluation via Audio-Visual Recordings 3 upvotes, #14 of 2025-08-04

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.