Daily Papers of 2025-12-23

  1. DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI 193 upvotes, #1 of 2025-12-23
  2. The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding 61 upvotes, #2 of 2025-12-23
  3. Region-Constraint In-Context Generation for Instructional Video Editing 48 upvotes, #3 of 2025-12-23
  4. QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation 31 upvotes, #4 of 2025-12-23
  5. WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion 29 upvotes, #5 of 2025-12-23
  6. Infinite-Homography as Robust Conditioning for Camera-Controlled Video Generation 27 upvotes, #6 of 2025-12-23
  7. LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry 25 upvotes, #7 of 2025-12-23
  8. Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction 23 upvotes, #8 of 2025-12-23
  9. Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs 19 upvotes, #9 of 2025-12-23
  10. Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching 19 upvotes, #9 of 2025-12-23
  11. UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models 17 upvotes, #11 of 2025-12-23
  12. StoryMem: Multi-shot Long Video Storytelling with Memory 17 upvotes, #11 of 2025-12-23
  13. LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding 15 upvotes, #13 of 2025-12-23
  14. GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators 15 upvotes, #13 of 2025-12-23
  15. MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive, and MCP-Augmented Environments 11 upvotes, #15 of 2025-12-23
  16. Over++: Generative Video Compositing for Layer Interaction Effects 11 upvotes, #15 of 2025-12-23
  17. CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion 10 upvotes, #17 of 2025-12-23
  18. MatSpray: Fusing 2D Material World Knowledge on 3D Geometry 8 upvotes, #18 of 2025-12-23
  19. Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital 8 upvotes, #18 of 2025-12-23
  20. Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface 7 upvotes, #20 of 2025-12-23
  21. Name That Part: 3D Part Segmentation and Naming 3 upvotes, #21 of 2025-12-23
  22. Understanding Syllogistic Reasoning in LLMs from Formal and Natural Language Perspectives 2 upvotes, #22 of 2025-12-23
  23. SecureCode v2.0: A Production-Grade Dataset for Training Security-Aware Code Generation Models 2 upvotes, #22 of 2025-12-23
  24. Brain-Grounded Axes for Reading and Steering LLM States 2 upvotes, #22 of 2025-12-23

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.