Daily Papers of 2026-09-23

  1. The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks 159 upvotes, #1 of 2026-09-23
  2. RULER: Instance-aware Rubric Rewards for SVG Generation 101 upvotes, #2 of 2026-09-23
  3. Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings 75 upvotes, #3 of 2026-09-23
  4. GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation 70 upvotes, #4 of 2026-09-23
  5. StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training 56 upvotes, #5 of 2026-09-23
  6. All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts 55 upvotes, #6 of 2026-09-23
  7. Bellman Policy Optimization 49 upvotes, #7 of 2026-09-23
  8. JEV-as-a-Judge: Accept When Confident, Escalate When Unsure 42 upvotes, #8 of 2026-09-23
  9. Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models 40 upvotes, #9 of 2026-09-23
  10. Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs 36 upvotes, #10 of 2026-09-23
  11. From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health 32 upvotes, #11 of 2026-09-23
  12. Lean Pool: An AI-Maintained Archive of Formalized Mathematics 27 upvotes, #12 of 2026-09-23
  13. Recursive self-improvement of AI research agents 27 upvotes, #12 of 2026-09-23
  14. Agensh: Scaling Organizational Intelligence to 1,024 Agents 27 upvotes, #12 of 2026-09-23
  15. Emergent Collusion in Long-Horizon LLM Agent Interaction 19 upvotes, #15 of 2026-09-23
  16. Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts 18 upvotes, #16 of 2026-09-23
  17. Embedding Physics Priors in Robot Learning: A Survey 18 upvotes, #16 of 2026-09-23
  18. LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay 17 upvotes, #18 of 2026-09-23
  19. ImIR: Image-Instruction Tuning for All-in-One Image Restoration 13 upvotes, #19 of 2026-09-23
  20. RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents 13 upvotes, #19 of 2026-09-23
  21. Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament 11 upvotes, #21 of 2026-09-23
  22. ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning 10 upvotes, #22 of 2026-09-23
  23. Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes 10 upvotes, #22 of 2026-09-23
  24. HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis 9 upvotes, #24 of 2026-09-23

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.