全部收录论文
论文 · 第 49 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 49 / 141 页
查找论文请用站内搜索。
- StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows
- Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting
- TCMIIES: A Browser-Based LLM-Powered Intelligent Information Extraction System for Academic Literature
- Asana cleared 5 years of engineering work in 2 weeks with Codex
- ArborMem: Navigating Interaction States with Memory Forests
- PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX
- NVIDIA Dynamo: 实现生成式 AI 的扩展和服务化部署
- MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
- Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection
- What Tokens are Learned when Tokenization is Optimized Jointly with Language Modeling?
- Cross-Model Memory Transfer via Target-Side Reader Adaptation
- EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
- 腾讯云大模型训推平台 TI-ONE
- Q-Interference: Memory-Efficient Phase-Aware Quantum-Inspired Attention
- Abra: Scaling Diffusion Image Training
- From Token Generation to Item Ranking: Direct Generative Recommendation with Semantic IDs
- Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semantic Discovery
- Rich-Media Re-Ranker: A User Satisfaction-Driven LLM Re-ranking Framework for Rich-Media Search
- GEO-Flag: Detecting and Measuring GEO-Optimized Web Content
- Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation
- LineageRAG: Harnessing GraphRAG by Constructing Evidence Lineages with Source Grounding
- From IR to RecSys: Evaluating LLM-based Judges in Cranfield-style Recommendation Collections
- LlamaRec-LKG-RAG: A Single-Pass, Learnable Knowledge Graph-RAG Framework for LLM-Based Ranking
- Conversational generative retrieval with contextual denoising
- Unbiased Recommender Systems with Implicit Feedback
- Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay
- UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation
- TRACER: Balancing Stability-Plasticity-Cognitivity Trilemma for LLM Enhanced Continual Recommendation
- Decoupled Temporal Encoding for Generative Recommendation
- GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation
- POI Recommendation with LLM-Augmented Multi-Graph Learning and Contrastive Alignment
- SAGA: Structure-Attended Generative Action Embedding Model that encodes Multi-Surface User Action Sequences
- FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation
- Impression Share Prediction: An Offline Evaluation Task for Ranking Systems
- SAHC-NS: Structure-Aware and Hardness-Calibrated Negative Sampling for Implicit Collaborative Filtering
- Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval
- Static Pruning Across Sparse Retrieval Regimes: What Transfers, What Breaks, and What Still Helps
- RCEM: Embedder Equipped with Query Rewriting Skill for Robust Conversational Search in Distributional Shift
- Coverage Is Not Redundancy: Maintenance Cost and Exposure of Query-Aware Admission Indexes in Vector Databases Under Workload Drift
- NeuRoute: Logit-Guided Neural Routing for Billion-Scale Vector Search with Sub-Hour Index Construction
- Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval
- FROG: Efficient Range-Filtering Approximate Nearest Neighbor Search on GPUs
- Run Massive-Scale UMAP in Minutes Using Multiple GPUs—Without Losing Accuracy
- Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark
- An Empirical Analysis of Pruning Techniques: Performance, Retrievability and Bias.
- When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control
- The Commercial Tax: Rent-vs-Own Blind Spots in Multi-Hop Retrieval Benchmarks
- The Recall Trap: A Recall-Maximizing Retriever Configuration Reduces Issue Resolution in Fixed-Budget Code Context
- Plan Before Search: Search Agents Need Plan
- When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval