全部收录论文
论文 · 第 136 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 136 / 141 页
查找论文请用站内搜索。
- Contrastive Retrieval Heads Improve Attention-Based Re-Ranking
- Reproducing and Comparing Distillation Techniques for Cross-Encoders
- Timehash: Hierarchical Time Indexing for Efficient Business Hours Search
- Leveraging LLM-Assisted Query Understanding for Live Retrieval-Augmented Generation
- From Missteps to Mastery: Enhancing Low-Resource Dense Retrieval through Adaptive Query Generation
- Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades
- Full Stage Learning to Rank: A Unified Framework for Multi-Stage Systems
- HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval
- Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL
- MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
- Super Research: Answering Highly Complex Questions with Large Language Models through Super Deep and Super Wide Research
- Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
- Search-o1: Agentic Search-Enhanced Large Reasoning Models
- Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests
- MaskSearch: A Universal Pre-Training Framework to Enhance Agentic Search Capability
- SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
- CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification
- WideSeek: Advancing Wide Research via Multi-Agent Scaling
- Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs
- TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
- SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
- Cross-Family Speculative Prefill: Training-Free Long-Context Compression with Small Draft Models
- Speculative Speculative Decoding
- Expert Divergence Learning for MoE-based Language Models
- DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks
- Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression
- FreeAct: Freeing Activations for LLM Quantization
- GPUTOK: GPU Accelerated Byte Level BPE Tokenization
- Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study
- SODA: Semantic-Oriented Distributional Alignment for Generative Recommendation
- Fine-grained Semantics Integration for Large Language Model-based Recommendation
- Trinity: A Scenario-Aware Recommendation Framework for Large-Scale Cold-Start Users
- Unleashing the Native Recommendation Potential: LLM-Based Generative Recommendation via Structured Term Identifiers
- LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval
- Scaling Retrieval Augmented Generation with RAG Fusion: Lessons from an Industry Deployment
- Uncertainty Quantification of Click and Conversion Estimates for the Autobidding
- Mag-Mamba: Modeling Coupled spatiotemporal Asymmetry for POI Recommendation
- Token-Efficient Item Representation via Images for LLM Recommender Systems
- IDProxy: Cold-Start CTR Prediction for Ads and Recommendation at Xiaohongshu with Multimodal LLMs
- Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale
- Beyond the Flat Sequence: Hierarchical and Preference-Aware Generative Recommendations
- MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation
- CSRv2: Unlocking Ultra-Sparse Embeddings
- Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
- MealRec: Multi-granularity Sequential Modeling via Hierarchical Diffusion Models for Micro-Video Recommendation
- RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendation
- CLEAR: Null-Space Projection for Cross-Modal De-Redundancy in Multimodal Recommendation
- NextAds: Towards Next-generation Personalized Video Advertising
- ReFeed: Retrieval Feedback-Guided Dataset Construction for Style-Aware Query Rewriting
- Scaling Laws For Dense Retrieval