全部收录论文
论文 · 第 37 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 37 / 141 页
查找论文请用站内搜索。
- Off-Policy Evaluation for Semantic ID Recommenders: Does the Model's Own Code Hierarchy Help?
- Continual Graph Memory for Adaptive Recommendation under Intent Drift
- RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation
- DrEM: Dual-Side Robust Ensemble Ranking from Noisy User Preference Predictions in Video Recommendation
- NMKFR: A Robust Framework for Time-Aware Cold-Start Recommendation
- Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval
- SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions
- GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric Matching
- Configurable Semantic Chunking for Biomedical Information Extraction in Retrieval-Augmented Generation
- First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
- Dense Process Supervision for Search Agents via Fact Utility Estimation
- CoBRA: Learning Tool-Use Boundaries via Counterfactual Margins
- Skill Following: Evaluating Actual Skill Use in Retrieval-Enabled LLM Agents
- Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe
- Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives
- Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents
- Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents
- Multi agent retrieval validation and knowledge reasoning for enhanced retrieval augmented generation
- 1Password increases engineering productivity 21% with Codex
- The Structure of Quantization Damage in LLMs: Why the Next Bit Should Be Spent Globally
- Adaptive Context Parallelism for Production LLM Serving
- Scalable Context Orchestration for Serving LLMs Over Voice
- CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
- Introducing CUDA Rust: Two Tracks for Writing GPU Kernels
- LLM Inference on IMC-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism
- AtomRec: Evolving Atomic Memory for Agentic Recommendation
- Collaborative Memory Augmentation for Generative Recommendation
- Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
- Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources
- Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation
- MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning
- Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling?
- Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro
- Latent-Aligned Reasoning for Multimodal Recommendation
- Building a User Foundation Model for the Open Web
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval
- CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation
- LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs
- GUIR at SemEval-2026 Task 8: Training-Free Multi-Query Fusion for Robust Conversational Retrieval
- SAGE: Semantic Attribute Graphs for Multi-Entity Visual Retrieval
- DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM Reranking for ADHD Symptom Sentences
- You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments
- AutoConcept: Training-Free Concept-Guided Reranking for Metadata-Available Composed Image Retrieval
- Aggregating Neighbor Embedding Projection and Rank-Based Manifold Learning for Image Retrieval
- Inventory-Grounded Policy-Level Optimization for Training-Free AI Search
- A Tree-based RAG Framework for Evidence-Intensive QA via Adaptive Planning and Topology-Aware Evidence Gathering
- AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing
- EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?
- Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability