登录 注册
MM- Web Agent: 用于网页生成的分级多式网络代理
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
👁 53 📚 24
空间Evo:通过确定几何环境实现空间情报的自我演变
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
👁 112 📚 1
场景批评: 三维室内场景合成的符号评价器
SceneCritic: A Symbolic Evaluator for 3D Indoor Scene Synthesis
👁 126 📚 12
在许多代理追踪中发现违反安全的行为
Detecting Safety Violations Across Many Agent Traces
👁 22 📚 5
案件证据核查:证据-敏感监督框架
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
👁 130 📚 27
OpenVLThinkerV2: 多领域视觉任务通用多模式理性模型
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
👁 76 📚 16
AVGen-Bench:对文本到音频视频生成进行多角度评价的任务驱动基准
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
👁 199 📚 9
B. 见而不去想:在多式混合型专家中的循环分流
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
👁 209 📚 12
个性化奖励奔驰:用人类相适应的个性化评价奖励模式
Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
👁 94 📚 14
纸圈:一个开源多剂研究发现和分析框架
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
👁 189 📚 18
Beyond the Final Actor: 为精致 LLM- Generated text 检测的创建者和编辑者双重角色建模
Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained LLM-Generated...
👁 77 📚 2
BAS:评估大语文模型信心的决定理论方法
BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence
👁 103 📚 4
没有单一的多样化最佳模式:学习多样性样本的路由器
No Single Best Model for Diversity: Learning a Router for Sample Diversity
👁 107 📚 0
基因建议 LMs 中新词汇的基调初始化
Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation
👁 195 📚 4
高效深度放大通用YOCO
Universal YOCO for Efficient Depth Scaling
👁 154 📚 22
ACT Now:通过适应性上下文集成来防止LVLM幻觉
ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration
👁 11 📚 0
在具有短范围互动的上下文敏感随机语言模型上进行阶段过渡
Phase transition on a context-sensitive random language model with short range interactions
👁 11 📚 0
B. 背景索赔:可核实的索赔检测的背景分析
ContextClaim: A Context-Driven Paradigm for Verifiable Claim Detection
👁 24 📚 0
基于奖励的在线LLM 通过神经UCB运行
Reward-Based Online LLM Routing via NeuralUCB
👁 14 📚 0
以数据驱动的语音时间调整方式,隐蔽地提高通晓性
Covertly improving intelligibility with data-driven adaptations of speech timing
👁 15 📚 0
海洋智能体 🌊
海洋智能体
AI科研助手 · 2270篇文献
你好!你正在浏览文献列表,我可以帮你筛选方向、推荐高引论文或解读某个研究领域。