Daily Papers of 2025-11-03

  1. ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning 78 upvotes, #1 of 2025-11-03
  2. OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows 70 upvotes, #2 of 2025-11-03
  3. INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats 66 upvotes, #3 of 2025-11-03
  4. Continuous Autoregressive Language Models 61 upvotes, #4 of 2025-11-03
  5. π_RL: Online RL Fine-tuning for Flow-based Vision-Language-Action Models 59 upvotes, #5 of 2025-11-03
  6. Defeating the Training-Inference Mismatch via FP16 27 upvotes, #6 of 2025-11-03
  7. Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning 27 upvotes, #6 of 2025-11-03
  8. Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals 21 upvotes, #8 of 2025-11-03
  9. Revisiting Multimodal Positional Encoding in Vision-Language Models 19 upvotes, #9 of 2025-11-03
  10. HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration 19 upvotes, #9 of 2025-11-03
  11. SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens 15 upvotes, #11 of 2025-11-03
  12. Value Drifts: Tracing Value Alignment During LLM Post-Training 12 upvotes, #12 of 2025-11-03
  13. Visual Backdoor Attacks on MLLM Embodied Decision Making via Contrastive Trigger Learning 12 upvotes, #12 of 2025-11-03
  14. Higher-order Linear Attention 11 upvotes, #14 of 2025-11-03
  15. Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model 8 upvotes, #15 of 2025-11-03
  16. The Denario project: Deep knowledge AI agents for scientific discovery 6 upvotes, #16 of 2025-11-03
  17. A Survey on Efficient Vision-Language-Action Models 5 upvotes, #17 of 2025-11-03
  18. Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning 4 upvotes, #18 of 2025-11-03
  19. Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning 3 upvotes, #19 of 2025-11-03
  20. MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data 2 upvotes, #20 of 2025-11-03
  21. Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification 1 upvotes, #21 of 2025-11-03
  22. Monopoly Deal: A Benchmark Environment for Bounded One-Sided Response Games 1 upvotes, #21 of 2025-11-03
  23. Mask-to-Height: A YOLOv11-Based Architecture for Joint Building Instance Segmentation and Height Classification from Satellite Imagery 1 upvotes, #21 of 2025-11-03

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.