Key papers

• Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (2026)
  Tommaso Cerruti et al.
  2.00
• CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation (2026)
  Zhongyuan Peng et al.
  1.94
• On the Optimal Reasoning Length for RL-Trained Language Models (2026)
  Daisuke Nohara et al.
  1.94
• SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer (2026)
  Haoyi Zhu et al.
  1.94
• Code as Agent Harness (2026)
  Xuying Ning et al.
  1.94
• Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency (2026)
  Anis Radianis
  1.94
• ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment (2026)
  Qiuyu Tian et al.
  1.94
• Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning (2026)
  NVIDIA et al.
  1.94
• When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents (2026)
  Aman Mehta
  1.94
• Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs (2026)
  Kareem Elozeiri et al.
  1.94
• Steered LLM Activations are Non-Surjective (2026)
  Aayush Mishra et al.
  1.83
• Compiler-First State Space Duality and Portable O(1) Autoregressive Caching for Inference (2026)
  Cosmo Santoni
  1.78
• DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models (2025)
  Sunghee Jung et al.
  1.28
• Seed1.5-VL Technical Report (2025)
  Dong Guo et al.
  1.28
• ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models (2025)
  Mingjie Liu et al.
  1.28
• Audio-Aware Large Language Models as Judges for Speaking Styles (2025)
  Cheng-Han Chiang et al.
  1.28
• SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems (2025)
  Peiran Li et al.
  1.28
• Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols (2025)
  Mikhail Terekhov et al.
  1.28
• ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models (2025)
  Yuqi Liu et al.
  1.28
• ConsistEdit: Highly Consistent and Precise Training-free Visual Editing (2025)
  Zixin Yin et al.
  1.28
• Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions (2025)
  Eyal Gutflaish et al.
  1.28
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence (2024)
  Weize Chen et al.
  —
• Automated Design of Agentic Systems (2024)
  Shengran Hu et al.
  —
• ROICtrl: Boosting Instance Control for Visual Generation (2024)
  Yuchao Gu et al.
  —
• Gated Delta Networks: Improving Mamba2 with Delta Rule (2024)
  Songlin Yang et al.
  —
• DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation (2024)
  Minghong Cai et al.
  —