全部收录论文
论文 · 第 23 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 23 / 141 页
查找论文请用站内搜索。
- PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
- Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support
- Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents
- LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
- Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation
- Optimizing Agent Reliability and Tool Calling Efficiency for Chip Design Using NVIDIA NeMo Gym
- Analyzing technical documents with Deep Review
- RIVO: Lightweight Adaptive Rerouting for Deep Research Agents
- Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
- FlashVector: Agent for Hierarchical Model Serving Stack Optimization
- Deploying RDMA for Distributed Inference and Training At Scale
- RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
- FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving
- SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG
- Stable Token-level Scheduling for Serverless LLM Inference
- FidelityQ: Preserving Predictive Fidelity in Ultra-Low-Bit Language Model Quantization
- Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU Architectures
- The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation
- LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation
- Beyond Semantic IDs: Finite-Beam Reachability and Continuous-Query Generation in Generative Recommendation
- Guiding the coarse levels of semantic IDs makes the fine levels learnable
- Efficient Clustering with Quality Guardrails for LLM-based Recommender Systems at Industry Scale
- Learning Robust Personalized Prompts for LLM-Driven Sequential Recommendation
- A Behavioral Trait Leaks into Preferences: Diagnosing Trait Interference in LLM User Simulators
- Overview and Analysis of the RecSys Challenge 2026: Conversational Music Recommendation
- VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
- FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models
- CALMRec: Causally Aligned Language Memory for Long-Horizon Recommendation
- Constraint-Aware Conversational Job Recommendation in Code-Mixed Low-Resource Settings
- Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI
- WARMER: Meta-Learned Graph Warming for User Cold-Start Recommendation
- Compact and Efficient Indexes for Learned Sparse Retrieval
- Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
- GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
- GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks
- SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents
- Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study
- Test-Time Memory Construction
- MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents
- How to Rewrite Apache Spark UDFs for GPU Acceleration with AI Agents
- Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory
- Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution
- Scaling Agentic Data for Long-Horizon Terminal Intelligence
- Agent Evaluation Metric for multi-turn conversations
- Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
- KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse
- NVIDIA Run:ai Is Now Open Source as Part of NVIDIA DSX AI Factory Platform
- PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling
- Host-Aware Web Crawling for LLM Pretraining Data
- Overcoming Data Imbalances with Expert Selection Biases