Daily Papers of 2026-04-30

  1. GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents 114 upvotes, #1 of 2026-04-30
  2. RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments 74 upvotes, #2 of 2026-04-30
  3. ClawGym: A Scalable Framework for Building Effective Claw Agents 54 upvotes, #3 of 2026-04-30
  4. Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models 50 upvotes, #4 of 2026-04-30
  5. Large Language Models Explore by Latent Distilling 44 upvotes, #5 of 2026-04-30
  6. Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding 14 upvotes, #6 of 2026-04-30
  7. FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments 11 upvotes, #7 of 2026-04-30
  8. Agentic Fusion of Large Atomic and Language Models to Accelerate Superconductors Discovery 8 upvotes, #8 of 2026-04-30
  9. A Survey on LLM-based Conversational User Simulation 7 upvotes, #9 of 2026-04-30
  10. Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion 5 upvotes, #10 of 2026-04-30
  11. Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising 5 upvotes, #10 of 2026-04-30
  12. Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital 4 upvotes, #12 of 2026-04-30
  13. Sample Selection Using Multi-Task Autoencoders in Federated Learning with Non-IID Data 4 upvotes, #12 of 2026-04-30
  14. Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy 3 upvotes, #14 of 2026-04-30
  15. PSP: An Interpretable Per-Dimension Accent Benchmark for Indic Text-to-Speech 2 upvotes, #15 of 2026-04-30
  16. FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing 2 upvotes, #15 of 2026-04-30
  17. Probing Visual Planning in Image Editing Models 1 upvotes, #17 of 2026-04-30
  18. Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost 0 upvotes, #18 of 2026-04-30

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.