全部收录论文
论文 · 第 26 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 26 / 141 页
查找论文请用站内搜索。
- OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models
- Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token Shuffling
- Beyond Binary Priorities: Multi-Tier SLA Scheduling for Large Language Model Serving
- Distributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs
- Validate AI Factory Changes with Digital Twins and AI Agents
- Kafila: Serving Large Language Models on a Trusted Set of Heterogeneous Commodity Machines
- A Systematic Study of Semantic ID Spaces for Generative Information Retrieval
- Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval
- Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment
- Adapting Generative Recommenders for Multi-Turn Interaction
- Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation
- Personal-Agent Mediated Recommendation with Cross-Platform User History
- Contrastive Learning for Aspect Representation towards Explainable Recommendation
- FARE: Deep Reinforcement Learning For Fair Exposure Constrained Uncertainty Aware Financial Content Personalization
- Aligning Performance with Contribution: Towards Contribution-Aware Fair Recommendation
- Seeing the Context: Enhancing Recommender Systems with Image-Derived Contextual Signals
- RAGFlip: Measuring Query-Level Negative Flips in Retriever Upgrades
- Learning to Retrieve via Reinforcement Learning in Embedding Space
- UNREAL: Unifying Retrieval and Long-Context with a Single Model
- Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA
- A Study of Prior Case Retrieval Using Lexical, Semantic, and Rhetorical Role Information in Indian Legal Documents
- Do We Still Need Gazetteers in the Era of LLMs? Chaining Retrieval with a Spatial Neuro-Symbolic Index
- DBRAG: Multi-Table Retrieval-Augmented Generation for Complex Database Queries
- From Delivery to Stateful Exploration: Rethinking the Index for Agentic Search
- Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents
- Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine
- DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
- ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning
- Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
- The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory
- From Evidence to Action: How Tool-Using Agents Fail
- Token-Budgeted Escalation for Financial Document QA: Cost Is Predictable, Benefit Is the Bottleneck
- AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
- Smart Content Ingestion for Generative AI Workloads
- WavePrune: One period is often enough for RoPE
- NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
- Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability
- CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets
- TIDE 2.0: an open, model-agnostic engine for keyed de-identification of clinical notes
- What’s new in AI infrastructure and orchestration in September
- CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching
- Investigating Model Compression for Neural Machine Translation in the Biomedical Domain
- What Reasoning Should a Recommender Have? Designing Reasoning for Inference-Time Scaling in Recommendation
- From Valid to Useful: Post-Verification Acquisition for Recursive Self-Improving Recommendation
- Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
- QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking
- Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes
- Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination
- Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks