Showing 21–37 of 37 results
/ Date/ Name
Jul 21, 2025Pixels, Patterns, but No Poetry: To See The World like HumansJul 28, 2025Kimi K2: Open Agentic IntelligenceFeb 11, 2026MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool CallingApr 6, 2026OpenWorldLib: A Unified Codebase and Definition of Advanced World ModelsOct 19, 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPApr 11, 2022Exploring the Universal Vulnerability of Prompt-based Learning ParadigmMay 19, 2025G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement LearningJul 11, 2023Emu: Generative Pretraining in MultimodalityDec 20, 2024SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe GenerationJan 22, 2025Kimi k1.5: Scaling Reinforcement Learning with LLMsJun 16, 2023Evaluating the Robustness of Text-to-image Diffusion Models against Real-world AttacksJun 19, 2024AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language ModelsMar 25, 2025Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and MitigationApr 21, 2025FlowReasoner: Reinforcing Query-Level Meta-AgentsNov 11, 2024Token Merging for Training-Free Semantic Binding in Text-to-Image SynthesisFeb 2, 2026Kimi K2.5: Visual Agentic IntelligenceFeb 2, 2026Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks