全部收录论文
论文 · 第 52 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 52 / 141 页
查找论文请用站内搜索。
- 企业网盘全文搜索引擎架构:ES与向量检索的混合方案实践
- QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation
- Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
- Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
- Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents
- AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
- Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
- Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
- Better, Faster, Stronger: Programmatic Skill Learning Best Reduces Agent Cost
- ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents
- The builder’s guide to GPT‑5.6
- Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
- Retrofitting Recurrent Depth into a Pretrained Language Model: Installation, Extrapolation, Transfer, and Retention at Two Parameter Budgets
- Defending against Model Extraction for GNNs with Model Reprogramming
- ODE-Based Transformer Decoders for Iterative Sign Language Translation
- Grounding at scale: Engineering the retrieval system for the agentic web
- Q2 earnings: AWS on AI inference, vector databases, and agent infrastructure
- Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
- Easper: An Accessible ASR Pipeline for Language Documentation
- LLM Inference Serving 2026 — Comparing vLLM, SGLang, and TensorRT-LLM
- Shape Your Feed: An LLM-based Agentic System for Conversational Recommendation
- MERGE: Next-Generation Item Indexing Paradigm for Large-Scale Streaming Recommendation
- SIDInspector: A Mapping-First Diagnostic Resource for Semantic-ID Tokenizers
- Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness
- Towards Comprehensible Recommendation with Large Language Model Fine-tuning
- Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging
- Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72
- The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding
- UniScale: Synergistic Entire Space Data and Model Scaling for Search Ranking
- Empty shelves or lost keys? Recall is the bottleneck for parametric factuality
- Sona Technical Report
- ConnectionMind: Leveraging Social Networks and Large Language Models for Personalized Recommendation at Meta
- DualSpectralCF: Training-Free Sign-Aware Spectral Collaborative Filtering
- GenRec: An LLM-Backed Recommendation Ranker at Netflix
- Multi Interests for Joint Search-Recommendation Modeling
- Sequential Modality Dropout for Robust Multi-Modal Sequential Recommendation
- Are We Really Making Progress in Group Recommendation? Unmasking the Tie-Breaking Illusion
- TimeRoute: Time-Aware Modality Routing and Diffusion for Multi-Modal Recommendation
- Neural Tree Collaborative Filtering: Rethinking Graph Collaborative Filtering as Tree Collaborative Filtering with Curvature-Aware Propagation Depth
- Deciding When to Rely on Visual Information: Gated Multimodal Fusion in Sequential Recommendation
- Training Dense Retrievers with Multiple Positive Passages
- When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design
- Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection
- Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems
- Reasoning-enhanced Query Understanding through Decomposition and Interpretation
- Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation
- : Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives
- GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs
- DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
- Self-Knowledge Retrieval Augmented Generation Framework for Patent Matching