全部收录论文
论文 · 第 91 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 91 / 141 页
查找论文请用站内搜索。
- SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
- TPMM-DPO: Trajectory-aware Preference-guided Model Merging for Iterative Direct Preference Optimization
- PALS: Power-Aware LLM Serving for Mixture-of-Experts Models
- Charon: A Unified and Fine-Grained Simulator for Large-Scale LLM Training and Inference
- Multi-Layer Scheduling for MoE-Based LLM Reasoning
- Reasoning to Rank: An End-to-End Solution for Exploiting Large Language Models for Recommendation (R2Rank)
- FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation
- Reinforced Preference Optimization for Reasoning-Augmented Recommendations
- Behavior-Guided Candidate Calibration for Multimodal Recommendation
- Online Advertising with Spatial Interactions
- One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
- Integrating Chain-of-Thought into Generative Retrieval: A Preliminary Study
- IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions
- Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
- BeLink: Biomedical Entity Linking Meets Generative Re-Ranking
- Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance
- GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering
- Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging
- Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems
- MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
- SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
- SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain
- DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation
- MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
- Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG
- RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation
- TIDE: Efficient and Lossless MoE Diffusion LLM Inference with I/O-aware Expert Offload
- Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
- Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding
- RLHFless: Serverless Computing for Efficient RLHF
- Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
- BitCal-TTS: Bit-Calibrated Test-Time Scaling for Quantized Reasoning Models
- Access Paths for Efficient Ordering with Large Language Models
- FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
- HRM-Text: Efficient Pretraining Beyond Scaling
- Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
- Generative Recursive Reasoning
- Mem-π: Adaptive Memory through Learning When and What to Generate
- Robust Personalized Recommendation under Hidden Confounding in MNAR
- Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework
- Sequential Data Augmentation for Generative Recommendation
- Will It Go Viral? Grounding Micro-Video Popularity Prediction on the Open Web
- Offline Contextual Bandits in the Presence of New Actions
- Layer-wise Token Compression for Efficient Document Reranking
- DIVE: Embedding Compression via Self-Limiting Gradient Updates
- Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting
- Efficient Table QA via TableGrid Navigation and Progressive Inference Prompting
- GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval
- Legal Retrieval for Public Defenders
- SG-LegalCite: A Principle-Augmented Benchmark for Legal Citation Retrieval in Singapore Law