全部收录论文
论文 · 第 40 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 40 / 141 页
查找论文请用站内搜索。
- It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
- Towards Effective Structured Context Modeling for Conversational Recommender Systems via Dual-node Monte Carlo Tree Search
- From Prompt to Purchase: How AI Brand Recommendations Move Consumers on the Open Web
- From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native Designs
- TGR: Advancing Industrial Recommendation from Generative-Paradigm Ranking toward Unified Generation and Reasoning
- Two-Sided State-Space Models for Sequential Recommendation with Non-Random Multimodal Review Feedback
- SwapRec: Warming Up Cold Items Through Training-Time Swaps
- World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation
- Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning
- Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation
- Sequential recommendation via knowledge graph-enhanced multi-relational learning and temporal-aware user preference modeling
- Multimodal generative sequential recommendation with adaptive contrastive learning
- StudentSim: Training LLM-based Student Simulators
- Staged Linguistic Seeding: Grounded Query Expansion for Verified-Unit QA in AI Contact Centers
- Closed Forms and Synthetic Twins: Predicting Approximate Nearest Neighbor Recall from Embedding Statistics
- MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval
- Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories
- From Saliency to Discriminability: Rank-Preserving Visual Token Pruning for VLM Rerankers
- VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models
- MUSES: A Benchmark for Prospective Intellectual-Roots Retrieval
- EM^2Mem: Event-Centric Multimodal Memory for Large Language Models
- An Organizational Second Brain: Building an AI That Learns From Experts
- How to Rerank RAG Retrieval Results: From Hybrid Retrieval to Cross-Encoders, Listwise Ranking, and Evidence-Set Selection
- APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay
- SilentProbe: Measuring Silent Failure in Production APIs Used as Agent Tools
- Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
- TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning
- trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
- RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
- Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
- Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops
- DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
- How AI-native companies turn workflows into operating capability
- BAGS: A Bit-Partitioned Quantization-Aware Architecture for Accelerating Graph-based Approximate Nearest Neighbor Search
- OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization
- From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
- SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
- CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
- Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference
- Improving Ray Serve LLM on GKE throughput and latency
- The Modern CUDA Toolbox in Practice: A Step-by-Step Optimization Walkthrough
- Polimill builds Japan's next-generation public AI infrastructure
- Developing provably correct Rust code with Verus
- ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search
- Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval
- Generative Retrieval for E-commerce: Jointly Learning Embedding and Codebook with Same Product Cluster
- HF-SID: High-Fidelity Semantic IDs for Generative Retrieval in Location-Based Services
- Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking
- Beyond Ranking Accuracy: Evaluating LLM-Cited Feature Rationales for Next Basket Repurchase Recommendation
- P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models