全部收录论文
论文 · 第 31 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 31 / 141 页
查找论文请用站内搜索。
- The Recall Ceiling of LLM Recommendation Reranking
- Explainable Recommendations at Scale: LLM Rationales for YouTube Music Artist Discovery
- MTFM:美团统一推荐基座大模型在外卖多业务场景的落地实践
- When LLM-Based User Profiling Adds Value in Production Streaming Recommendation
- Tie Handling Is Part of the Evaluation Protocol: An Order-Invariance Audit for Tie-Heavy Recommender Scores
- Beyond a Scalar: Distributional Serving Interfaces for Watch-Time Prediction
- Calibrating Reproduced Claims in Recommender Systems
- BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval
- ItColBERT: An Italian-Specialised Late-Interaction Retriever
- Test-Time Adaptation with Query-Dependent Residuals for Visual Document Retrieval
- WARP: Wasserstein-Aligned RAG for Population Opinions
- When Learned Context Planning Fails to Beat Strong Retrieval: A Controlled Study of Planning, Routing, and Reranking for Long-Context QA
- MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos
- Distilling Lexical Product Associations into Deep Transformers: An Extreme Multi-Label Approach for Natural Language E-Commerce Search
- EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA
- Realize What Matters: Principled Context Representation for Large-Scale Reasoning
- Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
- Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
- Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices
- COMED: The Missing Middle Between Routing and Collaboration in Multi-LLM Inference
- Dual-Hypergraph Indexing: Bridging Knowledge Islands for Multi-Hop Reasoning in Retrieval-Augmented Generation
- Large Knowledge Model: From Papers to a Scientific Reasoning Landscape
- UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
- Parallel cut research time and cost in half with GPT‑6 Astra
- LEGO: Synergizing Expert GraphRAG and Expert Chain-of-Thought for Legal Reasoning
- MLCommons Sets Participation Record with New MLPerf Inference v6.1 Benchmark Results
- FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation
- Better prompt caching for GPT-6
- Hunyuan-A13B Technical Report
- Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs
- Distilling Sequential Computation in Transformer Language Models
- Topology-Aware Workload Scheduling with NVIDIA Topograph
- Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery
- Efficient MoE Training for Biological Foundation Models
- Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B
- What Makes a Good Semantic ID for Generative Recommendation? A Reproducibility Study
- Robust Fusion of Semantic and Behavioural Signals for LLM Reranking in Personalised Search
- TailSpec-EASE: Knowledge-Graph-Regularized Linear Recommendation for Web Long-Tail Discovery
- From Ranked Documents to Reliable Contexts: An Answer-Oriented Context Construct Framework for AI Search
- Parameterized Dense-Sparse Fusion for Hybrid Retrieval: Tuning a Rank-Score Mix on BEIR SciFact with Qdrant
- GroundedGEO: Auditing the Evidence Gap in Generative Search Rankings
- ReFilter: Bridging Embeddings and LLM Filtering for Similar Mobile App Retrieval
- Which Reranking Conclusions Survive the Answer Interface? A Prospective Finite-Orbit Audit
- Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval
- Scoring With the Engine: Retrieval Exposure, Cross-Engine Divergence, and the Limits of Engine-Agnostic GEO Scores
- ABAI at COLIEE 2026 Task 1: Multi-Stage Retrieval with GraphRAG-Enhanced Meta-Learning, and a Post-Hoc Study of the Cross-Validation-to-Test Gap
- Algebraic Retrieval: Composable Search for Agents
- Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
- CoVeR: Coverage-Based Routing of Verifier Calls in Agentic Retrieval
- SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue