Daily Papers of 2026-04-22

  1. Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items 247 upvotes, #1 of 2026-04-22
  2. AgentSPEX: An Agent SPecification and EXecution Language 160 upvotes, #2 of 2026-04-22
  3. CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation 85 upvotes, #3 of 2026-04-22
  4. SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing 45 upvotes, #4 of 2026-04-22
  5. AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model 38 upvotes, #5 of 2026-04-22
  6. TEMPO: Scaling Test-time Training for Large Reasoning Models 33 upvotes, #6 of 2026-04-22
  7. ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning 28 upvotes, #7 of 2026-04-22
  8. PlayCoder: Making LLM-Generated GUI Code Playable 26 upvotes, #8 of 2026-04-22
  9. Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language 21 upvotes, #9 of 2026-04-22
  10. CityRAG: Stepping Into a City via Spatially-Grounded Video Generation 17 upvotes, #10 of 2026-04-22
  11. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation 15 upvotes, #11 of 2026-04-22
  12. SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks 14 upvotes, #12 of 2026-04-22
  13. Understanding and Enforcing Weight Disentanglement in Task Arithmetic 12 upvotes, #13 of 2026-04-22
  14. Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers 11 upvotes, #14 of 2026-04-22
  15. ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation 11 upvotes, #14 of 2026-04-22
  16. Target-Oriented Pretraining Data Selection via Neuron-Activated Graph 10 upvotes, #16 of 2026-04-22
  17. Speculative Decoding for Autoregressive Video Generation 10 upvotes, #16 of 2026-04-22
  18. UniMesh: Unifying 3D Mesh Understanding and Generation 10 upvotes, #16 of 2026-04-22
  19. Dual-View Training for Instruction-Following Information Retrieval 10 upvotes, #16 of 2026-04-22
  20. RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models 7 upvotes, #20 of 2026-04-22
  21. UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models 6 upvotes, #21 of 2026-04-22
  22. Accurate and scalable exchange-correlation with deep learning 4 upvotes, #22 of 2026-04-22
  23. Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints 4 upvotes, #22 of 2026-04-22
  24. MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge 4 upvotes, #22 of 2026-04-22
  25. HP-Edit: A Human-Preference Post-Training Framework for Image Editing 4 upvotes, #22 of 2026-04-22
  26. What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search 4 upvotes, #22 of 2026-04-22
  27. LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction 4 upvotes, #22 of 2026-04-22
  28. Predicting integers from continuous parameters 3 upvotes, #28 of 2026-04-22
  29. MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation 3 upvotes, #28 of 2026-04-22
  30. Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks 3 upvotes, #28 of 2026-04-22
  31. Mitigating Multimodal Hallucination via Phase-wise Self-reward 3 upvotes, #28 of 2026-04-22
  32. Micro Language Models Enable Instant Responses 3 upvotes, #28 of 2026-04-22
  33. Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs 2 upvotes, #33 of 2026-04-22
  34. Evaluation-driven Scaling for Scientific Discovery 2 upvotes, #33 of 2026-04-22
  35. Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs 1 upvotes, #35 of 2026-04-22
  36. The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus 1 upvotes, #35 of 2026-04-22
  37. SPRITE: From Static Mockups to Engine-Ready Game UI 1 upvotes, #35 of 2026-04-22

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.