Daily Papers of 2026-02-27

  1. The Trinity of Consistency as a Defining Principle for General World Models 194 upvotes, #1 of 2026-02-27
  2. From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models 148 upvotes, #2 of 2026-02-27
  3. MobilityBench: A Benchmark for Evaluating Route-Planning Agents in Real-World Mobility Scenarios 104 upvotes, #3 of 2026-02-27
  4. OmniGAIA: Towards Native Omni-Modal AI Agents 51 upvotes, #4 of 2026-02-27
  5. Imagination Helps Visual Reasoning, But Not Yet in Latent Space 39 upvotes, #5 of 2026-02-27
  6. Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization 35 upvotes, #6 of 2026-02-27
  7. AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning 27 upvotes, #7 of 2026-02-27
  8. Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization 22 upvotes, #8 of 2026-02-27
  9. MediX-R1: Open Ended Medical Reinforcement Learning 22 upvotes, #8 of 2026-02-27
  10. VGG-T^3: Offline Feed-Forward 3D Reconstruction at Scale 13 upvotes, #10 of 2026-02-27
  11. Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling 12 upvotes, #11 of 2026-02-27
  12. General Agent Evaluation 11 upvotes, #12 of 2026-02-27
  13. EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents 11 upvotes, #12 of 2026-02-27
  14. AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games 9 upvotes, #14 of 2026-02-27
  15. veScale-FSDP: Flexible and High-Performance FSDP at Scale 7 upvotes, #15 of 2026-02-27
  16. Causal Motion Diffusion Models for Autoregressive Motion Generation 7 upvotes, #15 of 2026-02-27
  17. GeoWorld: Geometric World Models 7 upvotes, #15 of 2026-02-27
  18. Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation? 6 upvotes, #18 of 2026-02-27
  19. Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning 5 upvotes, #19 of 2026-02-27
  20. What Makes a Good Query? Measuring the Impact of Human-Confusing Linguistic Features on LLM Performance 3 upvotes, #20 of 2026-02-27
  21. DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain 3 upvotes, #20 of 2026-02-27
  22. No One Size Fits All: QueryBandits for Hallucination Mitigation 2 upvotes, #22 of 2026-02-27
  23. MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation 2 upvotes, #22 of 2026-02-27
  24. Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving 2 upvotes, #22 of 2026-02-27
  25. MEG-to-MEG Transfer Learning and Cross-Task Speech/Silence Detection with Limited Data 1 upvotes, #25 of 2026-02-27
  26. Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models 1 upvotes, #25 of 2026-02-27
  27. DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation 1 upvotes, #25 of 2026-02-27
  28. Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns 0 upvotes, #28 of 2026-02-27

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.