Key papers

• CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models (2026)
  Wenxuan Song et al.
  1.94
• Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State Replacement (2026)
  Injin Kong et al.
  1.94
• Delta Attention Residuals (2026)
  Cheng Luo et al.
  1.94
• Is Position Bias in Dense Retrievers Built In-or Learned from Data? (2026)
  Daegon Yu et al.
  1.94
• Geometric Latent Reasoning Induces Shorter Generations in LLMs (2026)
  Shashi Kumar et al.
  1.94
• Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models (2026)
  Nikita Kachaev et al.
  1.94
• Representation Distribution Matching for One-Step Visual Generation (2026)
  Lan Feng et al.
  1.94
• Instruction-Guided Autoregressive Neural Network Parameter Generation (2025)
  Soro Bedionita et al.
  1.28
• Provable Benefits of In-Tool Learning for Large Language Models (2025)
  Sam Houliston et al.
  1.28
• Language Self-Play For Data-Free Training (2025)
  Jakub Grudzien Kuba et al.
  1.28
• DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing (2025)
  Zihan Zhou et al.
  1.28
• Native Hybrid Attention for Efficient Sequence Modeling (2025)
  Jusen Du et al.
  1.28
• Document Understanding, Measurement, and Manipulation Using Category Theory (2025)
  Jared Claypoole et al.
  1.28
• Generalist Foundation Models Are Not Clinical Enough for Hospital Operations (2025)
  Lavender Y. Jiang et al.
  1.28
• Simple Token-Level Confidence Improves Caption Correctness (2023)
  Suzanne Petryk et al.
  —
• CodeTF: One-stop Transformer Library for State-of-the-art Code LLM (2023)
  Nghi D. Q. Bui et al.
  —
• Inserting Anybody in Diffusion Models via Celeb Basis (2023)
  Ge Yuan et al.
  —
• SITTA: A Semantic Image-Text Alignment for Image Captioning (2023)
  Fabian Paischer et al.
  —
• Interactive Task Planning with Language Models (2023)
  Boyi Li et al.
  —
• Training-Free Consistent Text-to-Image Generation (2024)
  Yoad Tewel et al.
  —
• Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance (2024)
  Somnath Banerjee et al.
  —
• JEN-1 DreamStyler: Customized Musical Concept Learning via Pivotal Parameters Tuning (2024)
  Boyu Chen et al.
  —
• Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining (2024)
  Dongyang Liu et al.
  —
• Vector-ICL: In-context Learning with Continuous Vector Representations (2024)
  Yufan Zhuang et al.
  —
• Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities (2024)
  Zhifei Xie et al.
  —
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning (2024)
  Zhiwei Hao et al.
  —