全部收录论文
论文 · 第 84 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 84 / 141 页
查找论文请用站内搜索。
- End-to-End Context Compression at Scale
- FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
- RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching
- Driving Video Retrieval for Complex Queries with Structured Grounding
- PulseBench-Tab: A Multilingual Benchmark for Table Extraction with Graph-Based Evaluation
- PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment
- Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
- Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
- Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory
- VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents
- Decoy-Calibrated Failure Audits for Language Models
- Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA
- Detection and Interpretability Analysis of Quotation Errors by Large Language Models
- OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
- End-to-End Context Compression at Scale
- FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
- Model Quantization: Turn FP8 Checkpoints into High-Performance Inference Engines with NVIDIA TensorRT
- Accelerating Federated Learning Research with AI Agents and NVIDIA FLARE Auto-FL
- Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce
- Gated Bidirectional Linear Attention for Generative Retrieval
- DREAM: Dynamic Refinement of Early Assignment Mappings
- Caption Injection for Optimization in Generative Search Engine
- Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation
- Mind the Gap: Bridging Behavioral Silos with LLMs in Multi-Vertical Recommendations
- PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
- Bradley-Terry Rankings for Recommender Systems Across Dataset Taxonomies
- Re-Centering Humans in LLM Personalization
- When Should Queries Be Decomposed? A Stage-Aware Study of Query Decomposition for Multi-Condition Retrieval
- Generative Reasoning Re-ranker
- Improving User Experience with Personalized Review Ranking and Summarization
- Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
- Projection and Quantisation: A Unifying View of Learning to Hash, from Random Projections to the RAG Era
- EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval
- jXBW: A Compressed Index for Structure-Aware JSONL Retrieval in Structured RAG
- ToolRec: Calibrated Preference Alignment for Query Recommendation in On-Device Assistants
- TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models
- Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation
- Real-world grounding in agentic AI
- Bridging intent and execution in agentic systems
- Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents
- FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A
- Constrained Dominant Sets for Multimodal Document Question Answering
- Kunlun: Establishing Scaling Laws for Massive-Scale Recommendation Systems through Unified Architecture Design
- DeRes: Decoupling Residual Stability and Adaptivity for Scalable CTR Prediction
- ASH: Asymmetric Scalar Hashing With Learned Dimensionality Reduction for High-Fidelity Vector Quantization
- Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors
- Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling
- Train Models Faster with JAX and MaxText Using NVFP4 on NVIDIA Blackwell
- QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation
- Self-supervised User Profile Generation for Personalization