全部收录论文
论文 · 第 19 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 19 / 141 页
查找论文请用站内搜索。
- Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval
- Conditional information Retrieval for Longitudinal Survey Harmonisation
- MemRevise: A Self-Revising Memory for Conversational Search
- StrucChunk: Structure-Aware Retrieval for Legal Document RAG
- MEMORA: A Memory-Enhanced Multimodal Committee Reranking Agent for Reasoning-Intensive Retrieval
- Exact Risk Certificates for Pairwise-Judged Reranking
- KhyontekAI at CheckThat! 2026: Multilingual Dense Retrieval and Cross-Encoder Reranking for Scientific Web Claims
- OpenSaC: A Python Library for Search as Code in Deep Research Agents
- EG-GRPO: Evidence-Guided Step-level Credit Assignment for Deep Search Agents
- ClueFlow: Learning Long-Horizon Search through Attributed Research-State Transitions
- Learning to Program Retrievals: Composing Search Primitives via Reinforcement Learning
- HybridResearcher: Bridging the Structured-Unstructured Boundary for Deep Research Agents
- OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
- The Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search Agents
- Fine-tune a search agent with multi-turn RL on Amazon SageMaker AI
- MemT-1.0: Towards Memory-Native Evolution
- AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
- RemoteANN: A Native Vector Search Engine for Cloud Object Storage
- TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
- KVCompass: A Discovery Plane for Internet-Scale Prefix Cache Sharing in LLM Serving
- MOSAIC: Multi-Objective Search for Allocating Inference Cache Across LLM Decoder Layers
- Announcing New vLLM and SGLang Inference Engines on TPU
- SigmaTrace: Library-Agnostic Observability for CPU/GPU-Initiated RDMA Communication
- PACT: NVFP4 Data-Flow LoRA Fine-Tuning on Consumer GPUs
- When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding
- Integrating TorchTPU into TorchTitan and Optimizing Models for TPU
- Managed RAG search inside the sovereign perimeter: Gemini on GDC enterprise search
- Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making
- The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do
- HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
- Humanity's Last Choice: A Common Evaluation Standard for Generative Engine Optimization
- Causal Edit Serialization
- LED: Improving Masked Diffusion Language Models by Lookahead Editing
- On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
- Trust but Verify: Designing Region-Inhomogeneous Forward Dynamics for Discrete Diffusion
- Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference
- Accelerating Mamba-2 with High-Performance Forward Pass Kernels in NVIDIA CUDA Tile
- LSNR: Learned Sparse News Recommendations with Attentive User Modeling
- Predictable Scaling: Efficient Model Exploration via Scaling-Law Prediction
- GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary
- Learning User Representations to Improve Simulation Fidelity
- Reasoning Reranking with Semantic IDs as the Sole Item Representation
- Learning Personalized Memory Gating from Delayed One-Sided Feedback
- VISTA: Steering LLMs with Latent User Values Inferred from a Few Survey Answers
- Chance-Constrained Personalized LLM Routing with Online Preference Learning
- Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task Needs
- QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity
- EKLAV: Elicited Key CoT Learning via Answer only superVision
- Jev-as-a-Judge for Brazilian Portuguese Information Retrieval: Relevance Assessment and Reranking
- Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal