全部收录论文
论文 · 第 22 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 22 / 141 页
查找论文请用站内搜索。
- RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation
- Plan or Retrieve First? A Scale Study of Tool Discovery Architectures
- HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks
- ProgAgent: Learning Tool Orchestration through Programmatic Training
- τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions
- How Meta Built Forum With AI-Native Engineering
- Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
- Neos: Learning to Interleave Search and Visual Reasoning
- Putting Earth AI to work: Geospatial agents for our planet's biggest challenges
- SLM 生成式高并发推理引擎:延迟约束下的有效吞吐优化
- CacheSmith: Accurate RAG Serving under Latency SLOs with Adaptive KV Reuse
- Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs
- Your Transformer Is Secretly Elastic
- PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference
- JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs
- Latent Compaction with Test-Time Training
- Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training
- SpectrumQuant: Spectrum Alignment for LLM Quantization
- KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization
- WeGR: Unified Generative Retrieval for Industrial Search Systems in WeChat
- Computed, not Memorized: Bit-Factorized Identifiers for Efficient Generative Retrieval
- UniSGR-V2: Stepwise Target-Side Feature Anticipation and Crossing for Generative Recommendation
- HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation
- Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction
- AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decoding-Aligned Prefixes
- Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders
- From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation
- Eval4DiRec: A Unified and Systematic Evaluation Framework for Diffusion-based Recommender Systems
- SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
- Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking
- DRanker: A Transformer-Based Multi-Task Ranking Model for the Disney+ Homepage
- Mitigating Popularity Bias in Sequential Recommendations with Sparse Prior-Regularized Objective
- Pathwise Alignment for Collaborative Filtering: Bilateral Conditional Flow Regularization
- Tackling the Modality Inhibitance Effect with Wavelet-based Modality Integration in Multi-modal Recommendation
- Rethinking Evidence Modeling: Context-Coupled Graph Learning for Multimodal Recommendation
- Federated Semantic Residuals for Multimodal Recommendation
- OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation
- Better Capturing Interactions Between Products in~Retail: Revisited Negative Sampling for~Basket Choice Modeling
- Toward Explainability in Multimodal Recommendation
- WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search
- Data Curation and Model Souping: Unlocking Qwen3-0.6B for MS MARCO Passage Ranking
- From a Large-Scale Teacher to Efficient Multimodal Students for Search Relevance Prediction
- Simple Linear Corrections for Compression in Late Interaction
- Faithful Query Resolution for Conversational Search
- CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets
- Self-improving data synthesis can scale embedding models across domains and tasks
- RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval
- Graph-free Retrieval with Graph-Modified Embeddings
- On Reranking Space for Multi-Tenant Retrieval with Adapted Queries
- Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents