Daily Papers of 2026-04-16

  1. Seedance 2.0: Advancing Video Generation for World Complexity 151 upvotes, #1 of 2026-04-16
  2. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time 100 upvotes, #2 of 2026-04-16
  3. OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models 62 upvotes, #3 of 2026-04-16
  4. SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments 62 upvotes, #3 of 2026-04-16
  5. Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents 29 upvotes, #5 of 2026-04-16
  6. From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space 28 upvotes, #6 of 2026-04-16
  7. Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure 24 upvotes, #7 of 2026-04-16
  8. Exploration and Exploitation Errors Are Measurable for Language Model Agents 24 upvotes, #7 of 2026-04-16
  9. Target Policy Optimization 22 upvotes, #9 of 2026-04-16
  10. SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering 20 upvotes, #10 of 2026-04-16
  11. Geometric Context Transformer for Streaming 3D Reconstruction 17 upvotes, #11 of 2026-04-16
  12. Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself 15 upvotes, #12 of 2026-04-16
  13. LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling 14 upvotes, #13 of 2026-04-16
  14. Anthropogenic Regional Adaptation in Multimodal Vision-Language Model 13 upvotes, #14 of 2026-04-16
  15. TIP: Token Importance in On-Policy Distillation 13 upvotes, #14 of 2026-04-16
  16. TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration 13 upvotes, #14 of 2026-04-16
  17. ROSE: An Intent-Centered Evaluation Metric for NL2SQL 11 upvotes, #17 of 2026-04-16
  18. Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision 10 upvotes, #18 of 2026-04-16
  19. UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding 10 upvotes, #18 of 2026-04-16
  20. SkVM: Compiling Skills for Efficient Execution Everywhere 9 upvotes, #20 of 2026-04-16
  21. ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video 9 upvotes, #20 of 2026-04-16
  22. Narrative-Driven Paper-to-Slide Generation via ArcDeck 7 upvotes, #22 of 2026-04-16
  23. HDR Video Generation via Latent Alignment with Logarithmic Encoding 6 upvotes, #23 of 2026-04-16
  24. MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments 6 upvotes, #23 of 2026-04-16
  25. UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization 6 upvotes, #23 of 2026-04-16
  26. Self-Sovereign Agent 5 upvotes, #26 of 2026-04-16
  27. What do Language Models Learn and When? The Implicit Curriculum Hypothesis 4 upvotes, #27 of 2026-04-16
  28. Mobile GUI Agents under Real-world Threats: Are We There Yet? 3 upvotes, #28 of 2026-04-16
  29. Do AI Coding Agents Log Like Humans? An Empirical Study 3 upvotes, #28 of 2026-04-16
  30. ROSE: Retrieval-Oriented Segmentation Enhancement 3 upvotes, #28 of 2026-04-16
  31. InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis 2 upvotes, #31 of 2026-04-16
  32. A Temporally Augmented Graph Attention Network for Affordance Classification 1 upvotes, #32 of 2026-04-16

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.