Daily Papers of 2026-01-08

  1. Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting 95 upvotes, #1 of 2026-01-08
  2. Evolving Programmatic Skill Networks 75 upvotes, #2 of 2026-01-08
  3. Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning 40 upvotes, #3 of 2026-01-08
  4. Benchmark^2: Systematic Evaluation of LLM Benchmarks 33 upvotes, #4 of 2026-01-08
  5. ROI-Reasoning: Rational Optimization for Inference via Pre-Computation Meta-Cognition 22 upvotes, #5 of 2026-01-08
  6. Klear: Unified Multi-Task Audio-Video Joint Generation 13 upvotes, #6 of 2026-01-08
  7. Choreographing a World of Dynamic Objects 12 upvotes, #7 of 2026-01-08
  8. Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks 11 upvotes, #8 of 2026-01-08
  9. Agentic Rubrics as Contextual Verifiers for SWE Agents 10 upvotes, #9 of 2026-01-08
  10. E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models 8 upvotes, #10 of 2026-01-08
  11. MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics 7 upvotes, #11 of 2026-01-08
  12. ThinkRL-Edit: Thinking in Reinforcement Learning for Reasoning-Centric Image Editing 6 upvotes, #12 of 2026-01-08
  13. Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts 5 upvotes, #13 of 2026-01-08
  14. EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering for Enhanced Alignment and Reasoning 5 upvotes, #13 of 2026-01-08
  15. RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models 5 upvotes, #13 of 2026-01-08
  16. RGS-SLAM: Robust Gaussian Splatting SLAM with One-Shot Dense Initialization 3 upvotes, #16 of 2026-01-08
  17. Pearmut: Human Evaluation of Translation Made Trivial 2 upvotes, #17 of 2026-01-08
  18. MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents 2 upvotes, #17 of 2026-01-08
  19. ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation 2 upvotes, #17 of 2026-01-08
  20. Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction 1 upvotes, #20 of 2026-01-08

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.