Daily Papers of 2025-07-18

  1. A Survey of Context Engineering for Large Language Models 194 upvotes, #1 of 2025-07-18
  2. VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning 68 upvotes, #2 of 2025-07-18
  3. π^3: Scalable Permutation-Equivariant Visual Geometry Learning 54 upvotes, #3 of 2025-07-18
  4. Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models 48 upvotes, #4 of 2025-07-18
  5. The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner 46 upvotes, #5 of 2025-07-18
  6. AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning 37 upvotes, #6 of 2025-07-18
  7. RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization 35 upvotes, #7 of 2025-07-18
  8. MindJourney: Test-Time Scaling with World Models for Spatial Reasoning 25 upvotes, #8 of 2025-07-18
  9. Voxtral 24 upvotes, #9 of 2025-07-18
  10. FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers 19 upvotes, #10 of 2025-07-18
  11. AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research 16 upvotes, #11 of 2025-07-18
  12. Teach Old SAEs New Domain Tricks with Boosting 11 upvotes, #12 of 2025-07-18
  13. FLEXITOKENS: Flexible Tokenization for Evolving Language Models 8 upvotes, #13 of 2025-07-18
  14. Einstein Fields: A Neural Perspective To Computational General Relativity 6 upvotes, #14 of 2025-07-18
  15. TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation 5 upvotes, #15 of 2025-07-18
  16. Automating Steering for Safe Multimodal Large Language Models 3 upvotes, #16 of 2025-07-18

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.