全部收录论文
论文 · 第 116 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 116 / 141 页
查找论文请用站内搜索。
- ColBERT-Att: Late-Interaction Meets Attention for Enhanced Retrieval
- Learning to Retrieve from Agent Trajectories
- STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness
- Improving Search Suggestions for Alphanumeric Queries
- Agentic-R: Learning to Retrieve for Agentic Search
- Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search
- Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback
- Attention Residuals
- Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models
- Generative Retrieval Overcomes Limitations of Dense Retrieval but Struggles with Identifier Ambiguity
- Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search
- DMax: Aggressive Parallel Decoding for dLLMs
- MARS: Enabling Autoregressive Models Multi-Token Generation
- Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
- STDec: Spatio-Temporal Stability Guided Decoding for dLLMs
- A Comparative Study of Demonstration Selection for Practical Large Language Models-based Next POI Prediction
- Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization
- Fast-dVLM: Efficient Block-Diffusion VLM via Direct Conversion from Autoregressive VLM
- HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
- The Unreasonable Effectiveness of Data for Recommender Systems
- CASE: Cadence-Aware Set Encoding for Large-Scale Next Basket Repurchase Recommendation
- Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation
- NestPipe: Large-Scale Recommendation Training on 1,500+ Accelerators via Nested Pipelining
- Leveraging Artist Catalogs for Cold-Start Music Recommendation
- EviSnap: Faithful Evidence-Cited Explanations for Cold-Start Cross-Domain Recommendation
- TREASURE: The Visa Payment Foundation Model for High-Volume Transaction Understanding
- Robustness Risk of Conversational Retrieval: Identifying and Mitigating Noise Sensitivity in Qwen3-Embedding Model
- Improving Neural Retrieval with Attribution-Guided Query Rewriting
- WebExpert: domain-aware web agents with critic-guided expert experience for high-precision search
- Feedback Adaptation for Retrieval-Augmented Generation
- MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL
- BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment
- HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrieval
- A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
- CubeGraph: Efficient Retrieval-Augmented Generation for Spatial and Temporal Data
- JU'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections
- Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
- Beyond Stochastic Exploration: What Makes Training Data Valuable for Agentic Search
- SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
- SubSearch: Intermediate Rewards for Unsupervised Guided Reasoning in Complex Retrieval
- Tool Retrieval Bridge: Aligning Vague Instructions with Retriever Preferences via Bridge Model
- Benchmarking LLM Tool-Use in the Wild
- SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
- Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
- Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
- How Much LLM Does a Self-Revising Agent Actually Need?
- Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
- Fast Heterogeneous Serving: Scalable Mixed-Scale LLM Allocation for SLO-Constrained Inference
- MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU
- Robust Length Prediction: A Perspective from Heavy-Tailed Prompt-Conditioned Distributions