全部收录论文
论文 · 第 87 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 87 / 141 页
查找论文请用站内搜索。
- Scaling Search Relevance: Augmenting App Store Ranking with LLM-Generated Judgments
- Whole-Pool Setwise Reranking with Long-Context Language Models
- Test-Time Training for Zero-Resource Dense Retrieval Reranking
- Reconstructing Content via Collaborative Attention to Improve Multimodal Embedding Quality
- Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents
- Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems
- Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM
- From Noise to Order: Learning to Rank via Denoising Diffusion
- Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
- Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback
- MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
- TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
- OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents
- Policy and World Modeling Co-Training for Language Agents
- Don't Ask the LLM to Track Freshness: A Deterministic Recipe for Memory Conflict Resolution
- MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
- An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking
- Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Systems
- Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Models
- Differentially Private Datastore Generation for Retrieval-Augmented Inference
- DOT-MoE: Differentiable Optimal Transport for MoEfication
- SplitZip: Ultra Fast Lossless KV Compression for Disaggregated LLM Serving
- Climber-Pilot: A Non-Myopic Generative Recommendation Model Towards Better Instruction-Following
- FOSTER: First-order Dataset Distillation for Text-based Sequential Recommendation
- Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge
- GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing
- Beyond Instance-Level Alignment and Uniformity: Semantic Factor Learning for Collaborative Filtering
- Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems
- Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media
- Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search Relevance
- Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search
- MIMO: Multilingual Information Retrieval via Monolingual Objectives
- Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages
- SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
- DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
- Vector Linking via Cross-Model Local Isometric Consistency
- SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
- DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval
- On the impact of retrieved content representations in RAG Pipelines
- Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA
- Evaluating Factual Density in Multi-Source RAG: A Study in Medical AI Accuracy
- Exploring Autonomous Agentic Data Engineering for Model Specialization
- Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
- Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs
- CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case Law
- Probing the Prompt KV Cache: Where It Becomes Dispensable
- Speculative Decoding Across Languages
- NVIDIA Vera CPU Sets a New Standard for Agentic Workloads in AI Factories
- NVIDIA DSX OS Delivers Open, Modular Software for Operating AI Factories at Scale
- An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations