Papers

• mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT (2026)
  Woosung Koh et al.
  1.94
• Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning (2026)
  Dian Zheng et al.
  1.89
• VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing (2026)
  Juan Rodriguez et al.
  1.78
• FullDiT: Multi-Task Video Generative Foundation Model with Full Attention (2025)
  Xuan Ju et al.
  1.28
• Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction (2025)
  Mahdi Pourmirzaei et al.
  1.28
• DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design (2025)
  Xiwei Hu et al.
  1.28
• GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface (2025)
  Urchade Zaratiana et al.
  1.28
• OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning (2025)
  Yuan Gong et al.
  1.28
• CWM: An Open-Weights LLM for Research on Code Generation with World Models (2025)
  FAIR CodeGen team et al.
  1.28
• SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding (2023)
  Haoxiang Wang et al.
  —
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models (2023)
  Yunfei Chu et al.
  —
• SpeechVerse: A Large-scale Generalizable Audio Language Model (2024)
  Nilaksh Das et al.
  —
• Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning (2024)
  Kaiwen Wang et al.
  —
• VITA: Towards Open-Source Interactive Omni Multimodal LLM (2024)
  Chaoyou Fu et al.
  —
• L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding? (2024)
  Zecheng Tang et al.
  —