Daily Papers of 2026-03-10

  1. Lost in Stories: Consistency Bugs in Long Story Generation by LLMs 87 upvotes, #1 of 2026-03-10
  2. Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence 81 upvotes, #2 of 2026-03-10
  3. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory 56 upvotes, #3 of 2026-03-10
  4. How Far Can Unsupervised RLVR Scale LLM Training? 52 upvotes, #4 of 2026-03-10
  5. Believe Your Model: Distribution-Guided Confidence Calibration 39 upvotes, #5 of 2026-03-10
  6. CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing 36 upvotes, #6 of 2026-03-10
  7. CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation 36 upvotes, #6 of 2026-03-10
  8. HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising 31 upvotes, #8 of 2026-03-10
  9. \$OneMillion-Bench: How Far are Language Agents from Human Experts? 26 upvotes, #9 of 2026-03-10
  10. NLE: Non-autoregressive LLM-based ASR by Transcript Editing 21 upvotes, #10 of 2026-03-10
  11. AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery 16 upvotes, #11 of 2026-03-10
  12. Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces 15 upvotes, #12 of 2026-03-10
  13. Scale Space Diffusion 15 upvotes, #12 of 2026-03-10
  14. Training-free Latent Inter-Frame Pruning with Attention Recovery 14 upvotes, #14 of 2026-03-10
  15. PIRA-Bench: A Transition from Reactive GUI Agents to GUI-based Proactive Intent Recommendation Agents 14 upvotes, #14 of 2026-03-10
  16. Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training 13 upvotes, #16 of 2026-03-10
  17. TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward 13 upvotes, #16 of 2026-03-10
  18. Agentic Critical Training 13 upvotes, #16 of 2026-03-10
  19. Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness 11 upvotes, #19 of 2026-03-10
  20. From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning 10 upvotes, #20 of 2026-03-10
  21. PureCC: Pure Learning for Text-to-Image Concept Customization 9 upvotes, #21 of 2026-03-10
  22. Building AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned 6 upvotes, #22 of 2026-03-10
  23. CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization 6 upvotes, #22 of 2026-03-10
  24. Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models 5 upvotes, #24 of 2026-03-10
  25. Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems 5 upvotes, #24 of 2026-03-10
  26. FVG-PT: Adaptive Foreground View-Guided Prompt Tuning for Vision-Language Models 5 upvotes, #24 of 2026-03-10
  27. Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity 4 upvotes, #27 of 2026-03-10
  28. NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving 4 upvotes, #27 of 2026-03-10
  29. CAST: Modeling Visual State Transitions for Consistent Video Retrieval 4 upvotes, #27 of 2026-03-10
  30. HydroShear: Hydroelastic Shear Simulation for Tactile Sim-to-Real Reinforcement Learning 3 upvotes, #30 of 2026-03-10
  31. Agentic Planning with Reasoning for Image Styling via Offline RL 3 upvotes, #30 of 2026-03-10
  32. HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing 3 upvotes, #30 of 2026-03-10
  33. Skip to the Good Part: Representation Structure & Inference-Time Layer Skipping in Diffusion vs. Autoregressive LLMs 3 upvotes, #30 of 2026-03-10
  34. OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning 3 upvotes, #30 of 2026-03-10
  35. Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation 2 upvotes, #35 of 2026-03-10
  36. ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer 2 upvotes, #35 of 2026-03-10
  37. LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models 2 upvotes, #35 of 2026-03-10
  38. Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts 2 upvotes, #35 of 2026-03-10
  39. Autophoresis of a Janus particle near a planar wall: a lubrication limit 1 upvotes, #39 of 2026-03-10
  40. Free Lunch for Pass@k? Low Cost Diverse Sampling for Diffusion Language Models 1 upvotes, #39 of 2026-03-10
  41. TAPFormer: Robust Arbitrary Point Tracking via Transient Asynchronous Fusion of Frames and Events 1 upvotes, #39 of 2026-03-10
  42. Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction: A GeoAI-Based Analysis of Multimodal Urban Mobility 1 upvotes, #39 of 2026-03-10
  43. MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering 1 upvotes, #39 of 2026-03-10
  44. Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation 1 upvotes, #39 of 2026-03-10
  45. PresentBench: A Fine-Grained Rubric-Based Benchmark for Slide Generation 1 upvotes, #39 of 2026-03-10
  46. Variational Flow Maps: Make Some Noise for One-Step Conditional Generation 1 upvotes, #39 of 2026-03-10
  47. SlowBA: An efficiency backdoor attack towards VLM-based GUI agents 1 upvotes, #39 of 2026-03-10
  48. SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation 0 upvotes, #48 of 2026-03-10
  49. MWM: Mobile World Models for Action-Conditioned Consistent Prediction 0 upvotes, #48 of 2026-03-10

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.