Daily Papers of 2025-11-05

  1. VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation 97 upvotes, #1 of 2025-11-05
  2. Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization 90 upvotes, #2 of 2025-11-05
  3. When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought 53 upvotes, #3 of 2025-11-05
  4. Step-Audio-EditX Technical Report 27 upvotes, #4 of 2025-11-05
  5. When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs 24 upvotes, #5 of 2025-11-05
  6. The Collaboration Gap 21 upvotes, #6 of 2025-11-05
  7. Brain-IT: Image Reconstruction from fMRI via Brain-Interaction Transformer 12 upvotes, #7 of 2025-11-05
  8. Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVR 11 upvotes, #8 of 2025-11-05
  9. Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models 9 upvotes, #9 of 2025-11-05
  10. CodeClash: Benchmarking Goal-Oriented Software Engineering 8 upvotes, #10 of 2025-11-05
  11. LTD-Bench: Evaluating Large Language Models by Letting Them Draw 8 upvotes, #10 of 2025-11-05
  12. TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System 8 upvotes, #10 of 2025-11-05
  13. RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies 5 upvotes, #13 of 2025-11-05
  14. iFlyBot-VLA Technical Report 5 upvotes, #13 of 2025-11-05
  15. Forget BIT, It is All about TOKEN: Towards Semantic Information Theory for LLMs 3 upvotes, #15 of 2025-11-05
  16. ChartM^3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension 3 upvotes, #15 of 2025-11-05
  17. RiddleBench: A New Generative Reasoning Benchmark for LLMs 2 upvotes, #17 of 2025-11-05
  18. BRAINS: A Retrieval-Augmented System for Alzheimer's Detection and Monitoring 2 upvotes, #17 of 2025-11-05
  19. D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation 1 upvotes, #19 of 2025-11-05
  20. Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation 1 upvotes, #19 of 2025-11-05
  21. Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning 1 upvotes, #19 of 2025-11-05
  22. TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data 1 upvotes, #19 of 2025-11-05
  23. LiveSecBench: A Dynamic and Culturally-Relevant AI Safety Benchmark for LLMs in Chinese Context 1 upvotes, #19 of 2025-11-05
  24. AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda 1 upvotes, #19 of 2025-11-05
  25. VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models 1 upvotes, #19 of 2025-11-05

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.