全部收录论文
论文 · 第 113 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 113 / 141 页
查找论文请用站内搜索。
- Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism
- How Transformers Learn to Plan via Multi-Token Prediction
- Deep Situation-Aware Interaction Network for Click-Through Rate Prediction
- SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
- LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks
- Is Sliding Window All You Need? An Open Framework for Long-Sequence Recommendation
- Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation
- Sparse Contrastive Learning for Content-Based Cold Item Recommendation
- Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
- Beyond Factual Grounding: The Case for Opinion-Aware Retrieval-Augmented Generation
- MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents
- The Effect of Document Selection on Query-focused Text Analysis
- Beyond Relevance: On the Relationship Between Retrieval and RAG Information Coverage
- Adaptive Retrieval for Reasoning-Intensive Retrieval
- Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
- AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
- Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems
- CLEAR: Cross-Lingual Enhancement in Alignment via Reverse-training
- QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
- NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
- Retrieval as a Decision: Training-Free Adaptive Gating for Efficient RAG
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
- Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
- Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
- Towards Long-horizon Agentic Multimodal Search
- From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation
- Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
- Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
- Knowledge Is Not Static: Order-Aware Hypergraph RAG for Language Models
- Latent-Condensed Transformer for Efficient Long Context Modeling
- MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization
- VFA: Relieving Vector Operations in Flash Attention with Global Maximum Pre-computation
- PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving
- Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
- OSC: Hardware Efficient W4A4 Quantization via Outlier Separation in Channel Dimension
- SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
- ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval
- Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
- An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience
- Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration
- SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance
- Differentiable Semantic ID for Generative Recommendation
- Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning
- R3-VAE: Reference Vector-Guided Rating Residual Quantization VAE for Generative Recommendation
- HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation
- Self-Distilled Reinforcement Learning for Co-Evolving Agentic Recommender Systems
- GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
- Bottleneck Tokens for Unified Multimodal Retrieval
- Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths
- SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search