全部收录论文
论文 · 第 28 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 28 / 141 页
查找论文请用站内搜索。
- Measuring and Mitigating Identity-Cue Preference Drift in LLM-based Recommender Systems
- AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation
- MM-VeriRec: Failure-Guided Fusion for Verifiable Agentic Multimodal Recommendation
- Embedding Subspace Partitioning for Dynamic Multi-Objective Retrieval
- Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders
- Cross-Modally Aligned and Temporally Gated Mixture of Experts for Multimodal Sequential Recommendation
- SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search
- On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers
- Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
- A Systematic Multi-Domain Evaluation of Document Retrievers
- RPTune: Learned Context Curation for LLM Catalog Search
- RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout
- ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research
- On-Device Commercial Intent Retrieval Under Size, Latency, and Privacy Constraints: A 3 MiB Retrieval System with Typed Egress Boundaries
- From Rules to Neural Graphs: Scalable Structured Prediction for Patent Prior Art Search
- ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression
- A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
- Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills
- Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval
- Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
- Agents Are Systems, Not Models: Rethinking Agentic Evaluation
- A model guide for the GPT-6 family
- Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents
- Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks
- Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning
- Introducing Agentic Search for Code and Context
- Scaling JEV-like Decision Models with SGLang
- Beyond Day-0: Optimizing DeepSeek-V4.1 Flash in SGLang
- RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models
- Toward provably private learning from federated data
- SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference
- A Method for Layer Bit-Width Allocation in LLM Quantization via Performance Maximization Under a Quality-Degradation Constraint
- Characterizing High Bandwidth Flash for LLM Serving
- Pricing Time, Not Just Tokens: Latency-Aware Mechanism Design for LLM Inference
- AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing
- LLM Inference in a Flash!
- Generative End-to-end Ad Retrieval at Douyin
- Learning Multiresolution Relevance for Hierarchical Generative Retrieval
- Exploring Forum Post Retrieval with Generative Modeling
- When the Label Ignores the Request: Auditing Policy-Selected Targets in Synthetic Conversational Music Recommendation
- Residual Trajectory Distillation for Generative Retrieval
- Can Generative Retrievers Learn Semantic IDs Without Forgetting How to Speak?
- FineSID: Scalable and Efficient Semantic Identifier Learning for Generative Recommendation
- Textual User Taste: Natural-Language User Context for Foundation-Model Recommender System at Scale
- AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation
- KUAISHOU Explorer LLM-Rec Challenge 2026: Reasoning Generative Recommendation
- Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation
- When LLM-Inferred User Context Adds Value in Production Streaming Recommendation
- RouteRec: Behavior-Guided Sparse Routing for Sequential Recommendation
- Routing Between Generative and Collaborative User Profiles: A Serving-Time Gate for Controllable Novelty