Daily Papers of 2025-07-16

  1. EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes 48 upvotes, #1 of 2025-07-16
  2. Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models 43 upvotes, #2 of 2025-07-16
  3. Scaling Laws for Optimal Data Mixtures 32 upvotes, #3 of 2025-07-16
  4. AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs 13 upvotes, #4 of 2025-07-16
  5. OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique 13 upvotes, #4 of 2025-07-16
  6. Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers 11 upvotes, #6 of 2025-07-16
  7. Taming generative video models for zero-shot optical flow extraction 9 upvotes, #7 of 2025-07-16
  8. BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering 6 upvotes, #8 of 2025-07-16
  9. Token-based Audio Inpainting via Discrete Diffusion 4 upvotes, #9 of 2025-07-16
  10. UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks 4 upvotes, #9 of 2025-07-16
  11. LLMalMorph: On The Feasibility of Generating Variant Malware using Large-Language-Models 3 upvotes, #11 of 2025-07-16
  12. Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning 3 upvotes, #11 of 2025-07-16
  13. Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs 2 upvotes, #13 of 2025-07-16

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.