Papers

• Qwen3.5-Omni Technical Report (2026)
  Qwen Team
  7.08
• Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (2026)
  Tommaso Cerruti et al.
  2.00
• Delta Attention Residuals (2026)
  Cheng Luo et al.
  1.94
• LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence (2026)
  Xiang An et al.
  1.94
• Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale (2026)
  Ang Li et al.
  1.94
• VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation (2026)
  Bo Li et al.
  1.89
• Residual Stream Duality in Modern Transformer Architectures (2026)
  Yifan Zhang
  1.78
• Graph-Aware Isomorphic Attention for Adaptive Dynamics in Transformers (2025)
  Markus J. Buehler
  1.28
• Normalized Attention Guidance: Universal Negative Guidance for Diffusion Model (2025)
  Dar-Yen Chen et al.
  1.28
• LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer (2025)
  Ying Shen et al.
  1.28
• LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer (2025)
  Yuzhuo Chen et al.
  1.28
• Cut2Next: Generating Next Shot via In-Context Tuning (2025)
  Jingwen He et al.
  1.28
• CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification (2025)
  Wei Li et al.
  1.28
• Native Hybrid Attention for Efficient Sequence Modeling (2025)
  Jusen Du et al.
  1.28
• Higher-order Linear Attention (2025)
  Yifan Zhang et al.
  1.28
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models (2025)
  DeepSeek-AI et al.
  1.28
• HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models (2023)
  Hayk Manukyan et al.
  —
• LinFusion: 1 GPU, 1 Minute, 16K Image (2024)
  Songhua Liu et al.
  —
• Mitigating Object Hallucination via Concentric Causal Attention (2024)
  Yun Xing et al.
  —
• Taipan: Efficient and Expressive State Space Language Models with Selective Attention (2024)
  Chien Van Nguyen et al.
  —