全部收录论文
论文 · 第 99 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 99 / 141 页
查找论文请用站内搜索。
- From Surface Learning to Deep Understanding: A Grounded AI Tutoring System for Moodle
- Cognitive Agent Compilation for Explicit Problem Solver Modeling
- VDCook: DIY Video Data Cook Your MLLMs
- Federation of Experts: Communication Efficient Distributed Inference for Large Language Models
- MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model
- MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text
- Domain-level metacognitive monitoring in frontier LLMs: A 33-model atlas
- How enterprises are scaling AI
- Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling
- On Reasoning Behind Next Occupation Recommendation
- EKTM: Effective Knowledge Transfer for Multi-Task Recommendation Models
- TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation
- Light-FMP: Lightweight Feature and Model Pruning for Enhanced Deep Recommender Systems
- Hesitator: Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems
- Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval
- Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
- OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queries
- AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation
- Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction
- Text-Graph Synergy: A Bidirectional Verification and Completion Framework for RAG
- EnterpriseRAG-Bench: A RAG Benchmark for Company Internal Knowledge
- LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
- Streaming Tokens and Tools: Multi-Turn Agentic Harness Support in NVIDIA Dynamo
- FinAgent-RAG: Agentic Retrieval-Augmented Generation for Financial Document Question Answering
- Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
- MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
- LATTE: Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
- Enhanced LLM Reasoning by Optimizing Reward Functions with Search-Driven Reinforcement Learning
- Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
- Improving Bash Generation in Small Language Models with Grammar-Constrained Decoding
- Running Codex safely at OpenAI
- MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
- When Is the Same Model Not the Same Service? A Measurement Study of Hosted Open-Weight LLM APIs
- DITRON: Distributed Multi-level Tiling Compiler for Parallel Tensor Programs
- Statistically-Lossless Quantization of Large Language Models
- FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
- Microbenchmark-Driven Analytical Performance Modeling Across Modern GPU Architectures
- VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
- EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation
- One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving (HELM)
- Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning
- UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
- OpenAI: Testing ads in ChatGPT
- RecGPT-Mobile: On-Device Large Language Models for User Intent Understanding in Taobao Feed Recommendation
- Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation
- Rethinking Convolutional Networks for Attribute-Aware Sequential Recommendation
- Interests Burn-down Diffusion Process for Personalized Collaborative Filtering
- CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
- Storage Is Not Memory: A Retrieval-Centered Architecture for Agent Recall
- Hybrid Pooling with LLMs via Relevance Context Learning