Daily Papers of 2026-02-02

  1. PaperBanana: Automating Academic Illustration for AI Scientists 160 upvotes, #1 of 2026-02-02
  2. Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text 89 upvotes, #2 of 2026-02-02
  3. ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas 58 upvotes, #3 of 2026-02-02
  4. Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation 55 upvotes, #4 of 2026-02-02
  5. THINKSAFE: Self-Generated Safety Alignment for Reasoning Models 38 upvotes, #5 of 2026-02-02
  6. ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought 34 upvotes, #6 of 2026-02-02
  7. TTCS: Test-Time Curriculum Synthesis for Self-Evolving 33 upvotes, #7 of 2026-02-02
  8. Causal World Modeling for Robot Control 29 upvotes, #8 of 2026-02-02
  9. Do Reasoning Models Enhance Embedding Models? 24 upvotes, #9 of 2026-02-02
  10. MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning 20 upvotes, #10 of 2026-02-02
  11. Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling 20 upvotes, #10 of 2026-02-02
  12. FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation 20 upvotes, #10 of 2026-02-02
  13. PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing 19 upvotes, #13 of 2026-02-02
  14. DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment 15 upvotes, #14 of 2026-02-02
  15. DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation 15 upvotes, #14 of 2026-02-02
  16. DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning 12 upvotes, #16 of 2026-02-02
  17. SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization 12 upvotes, #16 of 2026-02-02
  18. DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding 10 upvotes, #18 of 2026-02-02
  19. Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification 9 upvotes, #19 of 2026-02-02
  20. NativeTok: Native Visual Tokenization for Improved Image Generation 9 upvotes, #19 of 2026-02-02
  21. RM -RF: Reward Model for Run-Free Unit Test Evaluation 8 upvotes, #21 of 2026-02-02
  22. Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors 8 upvotes, #21 of 2026-02-02
  23. TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance 8 upvotes, #21 of 2026-02-02
  24. Latent Chain-of-Thought as Planning: Decoupling Reasoning from Verbalization 7 upvotes, #24 of 2026-02-02
  25. Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience 7 upvotes, #24 of 2026-02-02
  26. Scaling Multiagent Systems with Process Rewards 7 upvotes, #24 of 2026-02-02
  27. RAPTOR: Ridge-Adaptive Logistic Probes 7 upvotes, #24 of 2026-02-02
  28. Continual GUI Agents 4 upvotes, #28 of 2026-02-02
  29. Revisiting Diffusion Model Predictions Through Dimensionality 4 upvotes, #28 of 2026-02-02
  30. LMK > CLS: Landmark Pooling for Dense Embeddings 4 upvotes, #28 of 2026-02-02
  31. Real-Time Aligned Reward Model beyond Semantics 4 upvotes, #28 of 2026-02-02
  32. Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving 3 upvotes, #32 of 2026-02-02
  33. ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding 3 upvotes, #32 of 2026-02-02
  34. Memorization Dynamics in Knowledge Distillation for Language Models 2 upvotes, #34 of 2026-02-02
  35. KAPSO: A Knowledge-grounded framework for Autonomous Program Synthesis and Optimization 2 upvotes, #34 of 2026-02-02
  36. SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding 2 upvotes, #34 of 2026-02-02
  37. Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis 2 upvotes, #34 of 2026-02-02
  38. Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data 2 upvotes, #34 of 2026-02-02
  39. Visual Personalization Turing Test 2 upvotes, #34 of 2026-02-02
  40. Value-Based Pre-Training with Downstream Feedback 1 upvotes, #40 of 2026-02-02
  41. Machine Learning for Energy-Performance-aware Scheduling 1 upvotes, #40 of 2026-02-02

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.