Showing 1–20 of 42 results
/ Date/ Name
Jan 29, 2026Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language ModelsSep 8, 2025Interleaving Reasoning for Better Text-to-Image GenerationMar 9, 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language ModelsMar 19, 2026Confidential Databases Without Cryptographic MappingsMar 31, 2024A General and Efficient Training for Transformer via Token ExpansionJul 16, 2018An L$_0$L$_1$-norm compressive sensing paradigm for the construction of sparse predictive lattice models using mixed integer quadratic programmingMar 10, 2025LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?Dec 1, 2024Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context SparsificationJun 23, 2016Constructing and proving the ground state of a generalized Ising model by the cluster tree optimization algorithmApr 22, 2016Finding and proving the exact ground state of a generalized Ising model by convex optimization and MAX-SATJul 1, 2023Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter SamplerMar 2, 2026HarmonyCell: Automating Single-Cell Perturbation Modeling under Semantic and Distribution ShiftsFeb 2, 2026Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language ModelsOct 7, 2025Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning?Jun 12, 2025Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and ReasoningJun 18, 2025AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System NeedMay 8, 2025ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance GenerationMar 1, 2026GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat AssistantFeb 13, 2026VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory GraphApr 19, 2026SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents