全部收录论文
论文 · 第 95 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 95 / 141 页
查找论文请用站内搜索。
- Conventional Contrastive Learning Often Falls Short: Improving Dense Retrieval with Cross-Encoder Listwise Distillation and Synthetic Data
- Automated Query-Product Relevance Labeling using Large Language Models for E-commerce Search
- In a Few Words: Comparing Weak Supervision and LLMs for Short Query Intent Classification
- Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion
- Towards Self-Evolving Agentic Literature Retrieval
- Self-Distilled Agentic Reinforcement Learning
- Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
- EvolveMem: Self-Evolving Memory Architecture via AutoResearch for LLM Agents
- HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
- Orchard: An Open-Source Agentic Modeling Framework
- Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis
- WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
- PREPING: Building Agent Memory without Tasks
- Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability
- RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
- XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
- KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
- Diagnosing Training Inference Mismatch in LLM Reinforcement Learning
- A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models
- PreFT: Prefill-only finetuning for efficient inference
- AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
- An Interpretable Latency Model for Speculative Decoding in LLM Serving
- The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
- 美团 LongCat 开源 General 365:树立推理评测新标尺
- EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
- Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation
- Granite Embedding Multilingual R2 Models
- ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence
- Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
- LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving
- Many-Shot CoT-ICL: Making In-Context Learning Truly Learn
- Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
- Context Training with Active Information Seeking
- MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
- RAG-Enhanced Large Language Models for Dynamic Content Expiration Prediction in Web Search
- F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking
- Task-Aware Automated User Profile Generation for Recommendation Simulation Using Large Language Models
- A Standardized Re-evaluation of Conversational Recommender Systems on the ReDial Dataset
- Beyond Centralization: User-Controlled Federated Recommendations in Practice
- PersonalAI 2.0: Enhancing Knowledge Graph Traversal/Retrieval with Planning Mechanism for Personalized LLM Agents
- GAAMA: Graph Augmented Associative Memory for Agents
- VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense
- GovScape: A Public Multimodal Search System for 70 Million Pages of Government PDFs
- SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking
- Retrieval-Augmented Tutoring for Algorithm Tracing and Problem-Solving in AI Education
- Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings
- A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
- Promptimus: Improving already good LLM prompts with zero manual engineering
- Helping ChatGPT better recognize context in sensitive conversations
- Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations