Daily Papers of 2026-01-30

  1. Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives 172 upvotes, #1 of 2026-01-30
  2. Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models 110 upvotes, #2 of 2026-01-30
  3. Scaling Embeddings Outperforms Scaling Experts in Language Models 97 upvotes, #3 of 2026-01-30
  4. DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation 68 upvotes, #4 of 2026-01-30
  5. MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods 57 upvotes, #5 of 2026-01-30
  6. OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models 48 upvotes, #6 of 2026-01-30
  7. ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation 42 upvotes, #7 of 2026-01-30
  8. Qwen3-ASR Technical Report 33 upvotes, #8 of 2026-01-30
  9. Shaping capabilities with token-level data filtering 25 upvotes, #9 of 2026-01-30
  10. Exploring Reasoning Reward Model for Agents 22 upvotes, #10 of 2026-01-30
  11. PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction 21 upvotes, #11 of 2026-01-30
  12. Discovering Hidden Gems in Model Repositories 21 upvotes, #11 of 2026-01-30
  13. EEG Foundation Models: Progresses, Benchmarking, and Open Problems 20 upvotes, #13 of 2026-01-30
  14. LoL: Longer than Longer, Scaling Video Generation to Hour 19 upvotes, #14 of 2026-01-30
  15. AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts 19 upvotes, #14 of 2026-01-30
  16. One-step Latent-free Image Generation with Pixel Mean Flows 17 upvotes, #16 of 2026-01-30
  17. Language-based Trial and Error Falls Behind in the Era of Experience 16 upvotes, #17 of 2026-01-30
  18. Self-Improving Pretraining: using post-trained models to pretrain better models 15 upvotes, #18 of 2026-01-30
  19. Latent Adversarial Regularization for Offline Preference Optimization 13 upvotes, #19 of 2026-01-30
  20. Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report 12 upvotes, #20 of 2026-01-30
  21. Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening 12 upvotes, #20 of 2026-01-30
  22. Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models 10 upvotes, #22 of 2026-01-30
  23. Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts 10 upvotes, #22 of 2026-01-30
  24. DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents 9 upvotes, #24 of 2026-01-30
  25. Beyond Imitation: Reinforcement Learning for Active Latent Planning 9 upvotes, #24 of 2026-01-30
  26. MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models 8 upvotes, #26 of 2026-01-30
  27. FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale 8 upvotes, #26 of 2026-01-30
  28. VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning 7 upvotes, #28 of 2026-01-30
  29. KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices 6 upvotes, #29 of 2026-01-30
  30. ECO: Quantized Training without Full-Precision Master Weights 6 upvotes, #29 of 2026-01-30
  31. JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion 6 upvotes, #29 of 2026-01-30
  32. MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources 5 upvotes, #32 of 2026-01-30
  33. FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning 4 upvotes, #33 of 2026-01-30
  34. BMAM: Brain-inspired Multi-Agent Memory Framework 4 upvotes, #33 of 2026-01-30
  35. Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation 4 upvotes, #33 of 2026-01-30
  36. Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units 4 upvotes, #33 of 2026-01-30
  37. Reinforcement Learning from Meta-Evaluation: Aligning Language Models Without Ground-Truth Labels 3 upvotes, #37 of 2026-01-30
  38. Flow-based Extremal Mathematical Structure Discovery 2 upvotes, #38 of 2026-01-30
  39. PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement 1 upvotes, #39 of 2026-01-30
  40. Segment Length Matters: A Study of Segment Lengths on Audio Fingerprinting Performance 1 upvotes, #39 of 2026-01-30
  41. Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis 1 upvotes, #39 of 2026-01-30
  42. STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation 0 upvotes, #42 of 2026-01-30
  43. WorldBench: Disambiguating Physics for Diagnostic Evaluation of World Models 1 upvotes, #42 of 2026-01-30
  44. Spotlighting Task-Relevant Features: Object-Centric Representations for Better Generalization in Robotic Manipulation 0 upvotes, #42 of 2026-01-30
  45. WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents 1 upvotes, #42 of 2026-01-30

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.