Showing 1–12 of 12 results
/ Date/ Name
Jun 6, 2023Model Spider: Learning to Rank Pre-Trained Models EfficientlyDec 9, 2024OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-ExtensionsMar 11, 2026$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL RolloutsAug 17, 2023ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model ReuseJun 5, 2024Wings: Learning Multimodal LLMs without Text-only ForgettingMar 27, 2025Model Assembly Learning with Heterogeneous Layer Weight MergingFeb 24, 2025Capability Instruction Tuning: A New Paradigm for Dynamic LLM RoutingFeb 3, 2026$V_0$: A Generalist Value Model for Any Policy at State ZeroFeb 3, 2026CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMsDec 8, 2023Few-Shot Class-Incremental Learning via Training-Free Prototype CalibrationJan 23, 2026LongCat-Flash-Thinking-2601 Technical ReportFeb 6, 2026ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training