全部收录论文
论文 · 第 126 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 126 / 141 页
查找论文请用站内搜索。
- DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
- A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challenge
- Auditing Google's AI Overviews and Featured Snippets: A Case Study on Baby Care and Pregnancy
- Enhancing Hyperspace Analogue to Language (HAL) Representations via Attention-Based Pooling for Text Classification
- R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
- Utility-Guided Agent Orchestration for Efficient LLM Tool Use
- A Subgoal-driven Framework for Improving Long-Horizon LLM Agents
- HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning
- All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution
- The Autonomy Tax: Defense Training Breaks LLM Agents
- DLLM Agent: See Farther, Run Faster
- LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
- ClawWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
- Embodied Science: Closing the Discovery Loop with Agentic Embodied AI
- TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly
- FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning
- Understanding and Optimizing Multi-Stage AI Inference Pipelines
- Towards Next-Generation LLM Training: From the Data-Centric Perspective
- DAPA: Distribution Aware Piecewise Activation Functions for On-Device Transformer Inference and Training
- AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
- Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter
- WorldCache: Content-Aware Caching for Accelerated Video World Models
- From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation
- UNGER: Generative Recommendation with A Unified Code via Semantic and Collaborative Integration
- SORT: A Systematically Optimized Ranking Transformer for Industrial-scale Recommenders
- Not All Candidates are Created Equal: A Heterogeneity-Aware Approach to Pre-ranking in Recommender Systems
- Modeling Stage-wise Evolution of User Interests for News Recommendation
- DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation
- Negative Sampling Techniques in Information Retrieval: A Survey
- DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval
- Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval
- Evaluating the Search Agent in a Parallel World
- RAPO: Expanding Exploration for LLM Agents via Retrieval-Augmented Policy Optimization
- TopoChunker: Topology-Aware Agentic Document Chunking Framework
- MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
- RLRF: Competitive Search Agent Design via Reinforcement Learning from Ranker Feedback
- A Picture of Agentic Search
- Retrieval-Augmented LLM Agents: Learning to Learn from Experience
- SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
- inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference
- LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
- ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs
- UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation
- ASAP: Attention-Shift-Aware Pruning for Efficient LVLM Inference
- Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation
- CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval
- Exploring Training and Inference Scaling Laws in Generative Retrieval
- RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning
- Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization
- Efficient Training-Free Multi-Token Prediction via Embedding-Space Probing