Oriel — AI & technology worth noticing, every day.

Trending

Discover what is gaining attention, alongside recent publications from your sources.

Source: Hugging Face Papers

  1. Harness^2: Recursive Agent Harnessing for an Open World — Hugging Face Papers · Rank 1 · 112 points · 1 comments · arxiv.org
  2. MOSS-Image Technical Report — Hugging Face Papers · Rank 2 · 59 points · 3 comments · arxiv.org
  3. Kronos: A Foundation Model for the Language of Financial Markets — Hugging Face Papers · Rank 3 · 60 points · 4 comments · arxiv.org
  4. The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction — Hugging Face Papers · Rank 4 · 28 points · 5 comments · arxiv.org
  5. TradingAgents: Multi-Agents LLM Financial Trading Framework — Hugging Face Papers · Rank 5 · 153 points · 6 comments · arxiv.org
  6. Has GPT-6-Astra Achieved Embodied Intelligence? — Hugging Face Papers · Rank 6 · 337 points · 2 comments · arxiv.org
  7. YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality — Hugging Face Papers · Rank 7 · 222 points · 3 comments · arxiv.org
  8. Unlimited OCR Works — Hugging Face Papers · Rank 8 · 95 points · 7 comments · arxiv.org
  9. Internal Safety Collapse in Frontier Large Language Models — Hugging Face Papers · Rank 9 · 31 points · 1 comments · arxiv.org
  10. Efficient Memory Management for Large Language Model Serving with PagedAttention — Hugging Face Papers · Rank 10 · 77 points · 1 comments · arxiv.org
  11. OpenDevin: An Open Platform for AI Software Developers as Generalist Agents — Hugging Face Papers · Rank 11 · 90 points · 7 comments · arxiv.org
  12. Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation — Hugging Face Papers · Rank 12 · 362 points · 3 comments · arxiv.org
  13. RSI-Anything: Unlocking Recursive Self-Improvement with World Models — Hugging Face Papers · Rank 13 · 54 points · 2 comments · arxiv.org
  14. StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions — Hugging Face Papers · Rank 14 · 20 points · 2 comments · arxiv.org
  15. Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation — Hugging Face Papers · Rank 15 · 7 points · 2 comments · arxiv.org
  16. DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses — Hugging Face Papers · Rank 16 · 14 points · 2 comments · arxiv.org
  17. nanoMuse: An Open-Source Personal Agent for Every Device You Own — Hugging Face Papers · Rank 17 · 116 points · 3 comments · arxiv.org
  18. Native and Compact Structured Latents for 3D Generation — Hugging Face Papers · Rank 18 · 9 points · 2 comments · arxiv.org
  19. OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use — Hugging Face Papers · Rank 19 · 319 points · 4 comments · arxiv.org
  20. Hybrid Reasoning Agents: 35–55% fewer tokens and up to 2.6× faster inference — Hugging Face Papers · Rank 20 · 38 points · 2 comments · arxiv.org
  21. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing — Hugging Face Papers · Rank 21 · 181 points · 2 comments · arxiv.org
  22. RAG-Anything: All-in-One RAG Framework — Hugging Face Papers · Rank 22 · 85 points · 6 comments · arxiv.org
  23. UniMate: One Unified Model to Animate Diverse Skeletons — Hugging Face Papers · Rank 23 · 23 points · 2 comments · arxiv.org
  24. Self-Evolving Agent Harness — Hugging Face Papers · Rank 24 · 199 points · 7 comments · arxiv.org
  25. Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory — Hugging Face Papers · Rank 25 · 74 points · 2 comments · arxiv.org
  26. Zep: A Temporal Knowledge Graph Architecture for Agent Memory — Hugging Face Papers · Rank 26 · 17 points · 0 comments · arxiv.org
  27. SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion — Hugging Face Papers · Rank 27 · 178 points · 19 comments · arxiv.org
  28. Player-1: Learning to Play from Synthetic Experience — Hugging Face Papers · Rank 28 · 344 points · 3 comments · arxiv.org
  29. ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration — Hugging Face Papers · Rank 29 · 155 points · 10 comments · arxiv.org
  30. PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training — Hugging Face Papers · Rank 30 · 26 points · 1 comments · arxiv.org
  31. PyTorch Distributed: Experiences on Accelerating Data Parallel Training — Hugging Face Papers · Rank 31 · 14 points · 0 comments · arxiv.org
  32. UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space — Hugging Face Papers · Rank 32 · 9 points · 2 comments · arxiv.org
  33. Very Large-Scale Multi-Agent Simulation in AgentScope — Hugging Face Papers · Rank 33 · 48 points · 2 comments · arxiv.org
  34. Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training — Hugging Face Papers · Rank 34 · 21 points · 1 comments · arxiv.org
  35. AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications — Hugging Face Papers · Rank 35 · 71 points · 4 comments · arxiv.org
  36. HuggingFace's Transformers: State-of-the-art Natural Language Processing — Hugging Face Papers · Rank 36 · 34 points · 7 comments · arxiv.org
  37. DLite: History-free Speculative Decoding for Agentic AI — Hugging Face Papers · Rank 37 · 20 points · 2 comments · arxiv.org
  38. PaperBanana: Automating Academic Illustration for AI Scientists — Hugging Face Papers · Rank 38 · 231 points · 13 comments · arxiv.org
  39. VisionHOPE: Visual Backbones as Self-Modifying Learning Systems — Hugging Face Papers · Rank 39 · 221 points · 2 comments · arxiv.org
  40. 3DCodeVerse: Exploring 3D Worlds as Code — Hugging Face Papers · Rank 40 · 114 points · 2 comments · arxiv.org
  41. Prime Agent: A Self-Improving RLM Harness — Hugging Face Papers · Rank 41 · 57 points · 2 comments · arxiv.org
  42. BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business — Hugging Face Papers · Rank 42 · 269 points · 3 comments · arxiv.org
  43. OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools — Hugging Face Papers · Rank 43 · 41 points · 4 comments · arxiv.org
  44. Matrix-Game: Interactive World Foundation Model — Hugging Face Papers · Rank 44 · 73 points · 2 comments · arxiv.org
  45. COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation — Hugging Face Papers · Rank 45 · 131 points · 3 comments · arxiv.org
  46. Agent-Reflex: Teaching Language Agents to Act Reflectively — Hugging Face Papers · Rank 46 · 214 points · 3 comments · arxiv.org
  47. A decoder-only foundation model for time-series forecasting — Hugging Face Papers · Rank 47 · 47 points · 1 comments · arxiv.org
  48. SkillOpt: Executive Strategy for Self-Evolving Agent Skills — Hugging Face Papers · Rank 48 · 268 points · 5 comments · arxiv.org
  49. VideoJev: System One Model for Video Understanding and Interaction — Hugging Face Papers · Rank 49 · 365 points · 3 comments · arxiv.org
  50. Fish Audio S2 Technical Report — Hugging Face Papers · Rank 50 · 41 points · 2 comments · arxiv.org