全部收录论文
论文 · 第 107 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 107 / 141 页
查找论文请用站内搜索。
- AgentSearchBench: A Benchmark for AI Agent Search in the Wild
- Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching
- Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
- ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification
- Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA
- Dynamically Acquiring Text Content to Enable the Classification of Lesser-known Entities for Real-world Tasks
- AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
- PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training
- AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
- DR-Arena: an Automated Evaluation Framework for Deep Research Agents
- Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?
- Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
- Incentivizing Neuro-symbolic Language-based Reasoning in VLMs via Reinforcement Learning
- Source-Modality Monitoring in Vision-Language Models
- Optimal Question Selection from a Large Question Bank for Clinical Field Recovery in Conversational Psychiatric Intake
- HybridGen: Efficient LLM Generative Inference via CPU-GPU Hybrid Computing
- Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
- Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
- Unlocking the Edge Deployment and On-Device Acceleration of Multi-LoRA enabled Foundational LLM
- The Recurrent Transformer: Greater Effective Depth and Efficient Decoding
- RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving
- DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge
- SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference
- Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization
- Temporally Extended Mixture-of-Experts Models
- Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking
- Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation
- Filling the Gaps: Selective Knowledge Augmentation for LLM Recommenders
- Deep Interest Mining with Cross-Modal Alignment for SemanticID Generation in Generative Recommendation
- End-to-End Semantic ID Generation for Generative Advertisement Recommendation
- Uncertainty-aware Generative Learning Path Recommendation with Cognition-Adaptive Diffusion
- Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation
- The Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation
- ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation
- Following the Eye-Tracking Evidence: Established Web-Search Assumptions Fail in Carousel Interfaces
- Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models
- CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation
- Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
- Adaptive Knowledge Transfer for Cross-Disciplinary Cold-Start Knowledge Tracing
- Two Heads Are Better Than One: Generalized Cross-Domain Federated Learning via Dual-Prototype
- From Tokens to Concepts: Leveraging SAE for SPLADE
- RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm
- Beyond Retrieval-Ranking: A Multi-Agent Cognitive Decision Framework for E-Commerce Search
- Combining Structural and Textual Knowledge for Knowledge Graph Link Prediction via Large Language Models
- IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
- GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization
- Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning
- Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations
- MTA-Agent: An Open Recipe for Multimodal Deep Search Agents
- Google Cloud Next 2026: Agentic AI tooling, A2A protocol, and Workspace Studio