Showing 1–19 of 19 results
/ Date/ Name
Feb 8, 2025Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model MergingMar 2, 2026TopoCurate:Modeling Interaction Topology for Tool-Use Agent TrainingAug 30, 2025Unifying Adversarial Perturbation for Graph Neural NetworksOct 13, 2025Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain GeneralizationOct 17, 2024Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware SubspaceAug 18, 2024Leveraging Invariant Principle for Heterophilic Graph Structure Distribution ShiftsDec 19, 2023Learning to Reweight for Graph Neural NetworkOct 16, 2025Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion ModelsJan 30, 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic VerificationMar 15, 2024Discovering Invariant Neighborhood Patterns for Heterophilic GraphsOct 9, 2025From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain AdaptationApr 30, 2025Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning OptimizationFeb 17, 2026ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation PatternsDec 5, 2025Scaling and Transferability of Annealing Strategies in Large Language Model TrainingJan 12, 2026LRAS: Advanced Legal Reasoning with Agentic SearchFeb 12, 2026SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search AgentJan 23, 2026LongCat-Flash-Thinking-2601 Technical ReportJan 25, 2025Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-Task LearningJun 20, 2025Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving