Daily Papers of 2026-09-11

  1. NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction 319 upvotes, #1 of 2026-09-11
  2. SenseNova-U1.5: Towards Native Unified Visual Intelligence 262 upvotes, #2 of 2026-09-11
  3. SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem 137 upvotes, #3 of 2026-09-11
  4. Mi-Ripple: Restoring Images Degraded by Iterative AI Editing 49 upvotes, #4 of 2026-09-11
  5. X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation 42 upvotes, #5 of 2026-09-11
  6. An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics 40 upvotes, #6 of 2026-09-11
  7. EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents 38 upvotes, #7 of 2026-09-11
  8. Memory as Plans: World-Action Modeling with Memory-Grounded Planning 37 upvotes, #8 of 2026-09-11
  9. FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation 34 upvotes, #9 of 2026-09-11
  10. Beyond Solver Verdicts: Generative Reward Models for Autoformalization 33 upvotes, #10 of 2026-09-11
  11. Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs 33 upvotes, #10 of 2026-09-11
  12. Negative Self-Distillation: Learning to Reason by Avoiding Flaws 33 upvotes, #10 of 2026-09-11
  13. Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning 31 upvotes, #13 of 2026-09-11
  14. World in World: Explore the World with World Models 31 upvotes, #13 of 2026-09-11
  15. TempCloze: Can Video-LLMs Identify the Missing Middle? 30 upvotes, #15 of 2026-09-11
  16. HyQuant: Hybrid-Precision Quantization for LLM Attention 28 upvotes, #16 of 2026-09-11
  17. Studying Image Tokenizers as Visual Languages in Unified Multimodal Models 28 upvotes, #16 of 2026-09-11
  18. MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes 28 upvotes, #16 of 2026-09-11
  19. Generative Late-Interaction Embeddings For Visual Document Retrieval 26 upvotes, #19 of 2026-09-11
  20. Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2 25 upvotes, #20 of 2026-09-11
  21. DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat 25 upvotes, #20 of 2026-09-11
  22. CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation 24 upvotes, #22 of 2026-09-11
  23. ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation 23 upvotes, #23 of 2026-09-11
  24. IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications 23 upvotes, #23 of 2026-09-11
  25. UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration 22 upvotes, #25 of 2026-09-11
  26. Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking 20 upvotes, #26 of 2026-09-11

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.