Daily Papers of 2026-02-26

  1. MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models 54 upvotes, #1 of 2026-02-26
  2. HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation 53 upvotes, #2 of 2026-02-26
  3. SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model 52 upvotes, #3 of 2026-02-26
  4. DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation 38 upvotes, #4 of 2026-02-26
  5. DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference 37 upvotes, #5 of 2026-02-26
  6. Solaris: Building a Multiplayer Video World Model in Minecraft 27 upvotes, #6 of 2026-02-26
  7. ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning 23 upvotes, #7 of 2026-02-26
  8. Image Generation with a Sphere Encoder 15 upvotes, #8 of 2026-02-26
  9. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL 15 upvotes, #8 of 2026-02-26
  10. JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation 14 upvotes, #10 of 2026-02-26
  11. World Guidance: World Modeling in Condition Space for Action Generation 14 upvotes, #10 of 2026-02-26
  12. From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors 12 upvotes, #12 of 2026-02-26
  13. VecGlypher: Unified Vector Glyph Generation with Language Models 11 upvotes, #13 of 2026-02-26
  14. Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images 6 upvotes, #14 of 2026-02-26
  15. NanoKnow: How to Know What Your Language Model Knows 6 upvotes, #14 of 2026-02-26
  16. SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models 4 upvotes, #16 of 2026-02-26
  17. Dropping Anchor and Spherical Harmonics for Sparse-view Gaussian Splatting 4 upvotes, #16 of 2026-02-26
  18. Revisiting Text Ranking in Deep Research 4 upvotes, #16 of 2026-02-26
  19. The Design Space of Tri-Modal Masked Diffusion Models 3 upvotes, #19 of 2026-02-26
  20. Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions 2 upvotes, #20 of 2026-02-26
  21. JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments 2 upvotes, #20 of 2026-02-26
  22. ISO-Bench: Can Coding Agents Optimize Real-World Inference Workloads? 2 upvotes, #20 of 2026-02-26
  23. UniVBench: Towards Unified Evaluation for Video Foundation Models 2 upvotes, #20 of 2026-02-26
  24. Intent Laundering: AI Safety Datasets Are Not What They Seem 1 upvotes, #24 of 2026-02-26
  25. DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction 1 upvotes, #24 of 2026-02-26
  26. Yor-Sarc: A gold-standard dataset for sarcasm detection in a low-resource African language 1 upvotes, #24 of 2026-02-26
  27. MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment 1 upvotes, #24 of 2026-02-26
  28. The Truthfulness Spectrum Hypothesis 1 upvotes, #24 of 2026-02-26
  29. Functional Continuous Decomposition 1 upvotes, #24 of 2026-02-26
  30. Small Language Models for Privacy-Preserving Clinical Information Extraction in Low-Resource Languages 1 upvotes, #24 of 2026-02-26
  31. NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors 1 upvotes, #24 of 2026-02-26

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.