Daily Papers of 2026-01-06

  1. K-EXAONE Technical Report 81 upvotes, #1 of 2026-01-06
  2. Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits 71 upvotes, #2 of 2026-01-06
  3. NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation 56 upvotes, #3 of 2026-01-06
  4. Recursive Language Models 55 upvotes, #4 of 2026-01-06
  5. DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer 49 upvotes, #5 of 2026-01-06
  6. VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation 32 upvotes, #6 of 2026-01-06
  7. InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams 31 upvotes, #7 of 2026-01-06
  8. GARDO: Reinforcing Diffusion Models without Reward Hacking 28 upvotes, #8 of 2026-01-06
  9. VINO: A Unified Visual Generator with Interleaved OmniModal Context 28 upvotes, #8 of 2026-01-06
  10. Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling 25 upvotes, #10 of 2026-01-06
  11. SimpleMem: Efficient Lifelong Memory for LLM Agents 25 upvotes, #10 of 2026-01-06
  12. SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving 21 upvotes, #12 of 2026-01-06
  13. Confidence Estimation for LLMs in Multi-turn Interactions 14 upvotes, #13 of 2026-01-06
  14. Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes 13 upvotes, #14 of 2026-01-06
  15. KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs 11 upvotes, #15 of 2026-01-06
  16. OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment 9 upvotes, #16 of 2026-01-06
  17. CPPO: Contrastive Perception for Vision Language Policy Optimization 6 upvotes, #17 of 2026-01-06
  18. COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs 6 upvotes, #17 of 2026-01-06
  19. Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion 4 upvotes, #19 of 2026-01-06
  20. DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies 4 upvotes, #19 of 2026-01-06
  21. IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset 2 upvotes, #21 of 2026-01-06
  22. Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery 1 upvotes, #22 of 2026-01-06
  23. Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents 1 upvotes, #22 of 2026-01-06
  24. Prithvi-Complimentary Adaptive Fusion Encoder (CAFE): unlocking full-potential for flood inundation mapping 1 upvotes, #22 of 2026-01-06
  25. M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models 2 upvotes, #25 of 2026-01-06

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.