全部收录论文
论文 · 第 124 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 124 / 141 页
查找论文请用站内搜索。
- AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access
- TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
- Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
- flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation
- SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
- A Brief Comparison of Training-Free Multi-Vector Sequence Compression Methods
- ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning
- Less is More: Adapting Text Embeddings for Low-Resource Languages with Small Scale Noisy Synthetic Data
- LGSE: Lexically Grounded Subword Embedding Initialization for Low-Resource Language Adaptation
- DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona
- Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents
- Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window
- From Questions to Trust Reports: A LLM-IR Framework for the TREC 2025 DRAGUN Track
- SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
- GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
- EVA: Efficient Reinforcement Learning for End-to-End Video Agent
- STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving
- AwesomeLit: Towards Hypothesis Generation with Agent-Supported Literature Research
- PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving
- Sparser, Faster, Lighter Transformer Language Models
- EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
- FAAR: Format-Aware Adaptive Rounding for NVFP4
- Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference
- Scaling Attention via Feature Sparsity
- MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning
- KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
- Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM Service
- Arena: Efficiently Training Large Models via Dynamic Scheduling and Adaptive Parallelism Co-Design
- One Model, Two Markets: Bid-Aware Generative Recommendation
- Collaborative User Prompt for Personalized Generative Recommendation
- ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation
- Query, Decompose, Compress: Structured Query Expansion for Efficient Multi-Hop Retrieval
- Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization
- AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization
- Overview of TREC 2025 Biomedical Generative Retrieval (BioGen) Track
- TagLLM: A Fine-Grained Tag Generation Approach for Note Recommendation
- MI-DPG: Decomposable Parameter Generation Network Based on Mutual Information for Multi-Scenario Recommendation
- Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences
- TF4CTR: Twin Focus Framework for CTR Prediction via Adaptive Sample Differentiation
- PreferRec: Learning and Transferring Pareto Preferences for Multi-objective Re-ranking
- AgenticRec: End-to-End Tool-Integrated Policy Optimization for Ranking-Oriented Recommender Agents
- Gated Rotary-Enhanced Linear Attention with Rank Modulation for Long-term Sequential Recommendation
- Do LLMs Understand Collaborative Signals? Diagnosis and Repair
- User Preference Modeling for Conversational LLM Agents: Weak Rewards from Retrieval-Augmented Interaction
- LSA: A Long-Short-term Aspect Interest Transformer for Aspect-Based Recommendation
- GEM: A Native Graph-based Index for Multi-Vector Retrieval
- DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning
- Semantic Shift: the Fundamental Challenge in Text Embedding and Retrieval