Daily Papers of 2026-01-12

  1. Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization 159 upvotes, #1 of 2026-01-12
  2. MMFormalizer: Multimodal Autoformalization in the Wild 102 upvotes, #2 of 2026-01-12
  3. CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature 51 upvotes, #3 of 2026-01-12
  4. The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning 48 upvotes, #4 of 2026-01-12
  5. Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking 45 upvotes, #5 of 2026-01-12
  6. Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards 39 upvotes, #6 of 2026-01-12
  7. EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis 35 upvotes, #7 of 2026-01-12
  8. AgentOCR: Reimagining Agent History via Optical Self-Compression 27 upvotes, #8 of 2026-01-12
  9. Can We Predict Before Executing Machine Learning Agents? 25 upvotes, #9 of 2026-01-12
  10. VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction 21 upvotes, #10 of 2026-01-12
  11. An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift 19 upvotes, #11 of 2026-01-12
  12. Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency 18 upvotes, #12 of 2026-01-12
  13. Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals 14 upvotes, #13 of 2026-01-12
  14. AnyDepth: Depth Estimation Made Easy 9 upvotes, #14 of 2026-01-12
  15. Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection 9 upvotes, #14 of 2026-01-12
  16. BizFinBench.v2: A Unified Dual-Mode Bilingual Benchmark for Expert-Level Financial Capability Alignment 9 upvotes, #14 of 2026-01-12
  17. SmartSearch: Process Reward-Guided Query Refinement for Search Agents 8 upvotes, #17 of 2026-01-12
  18. Orient Anything V2: Unifying Orientation and Rotation Understanding 8 upvotes, #17 of 2026-01-12
  19. Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning 5 upvotes, #19 of 2026-01-12
  20. DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation 5 upvotes, #19 of 2026-01-12
  21. Over-Searching in Search-Augmented Large Language Models 5 upvotes, #19 of 2026-01-12
  22. TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration 4 upvotes, #22 of 2026-01-12
  23. Legal Alignment for Safe and Ethical AI 3 upvotes, #23 of 2026-01-12
  24. GenCtrl -- A Formal Controllability Toolkit for Generative Models 3 upvotes, #23 of 2026-01-12
  25. TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents 3 upvotes, #23 of 2026-01-12
  26. IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck 2 upvotes, #26 of 2026-01-12
  27. Afri-MCQA: Multimodal Cultural Question Answering for African Languages 1 upvotes, #27 of 2026-01-12
  28. ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers 1 upvotes, #27 of 2026-01-12
  29. Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs 1 upvotes, #27 of 2026-01-12
  30. Distilling Feedback into Memory-as-a-Tool 1 upvotes, #27 of 2026-01-12
  31. The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models 1 upvotes, #31 of 2026-01-12

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.