全部收录论文
论文 · 第 25 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 25 / 141 页
查找论文请用站内搜索。
- RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees
- Programmatic Search Agents: Extending Agentic Search Beyond Query Reformulation
- Asana cuts model costs 76x in browser tests with GPT-6.1 Sol
- Agentic RAG Evaluation: Budget Allocation Across Questions, Trajectories, and Reads
- ATLAS: Evaluating Agents on Search-Intensive Tasks
- PhantomEnvironments: Training LLM Agents in Fictional Worlds
- Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning
- MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
- Mechanism-centric cross-domain retrieval for scientific discovery: LLM agents for structural isomorphism beyond semantic similarity
- Sophos cuts threat investigation time by 96% with OpenAI Daybreak
- AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation
- BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization
- FailBench: Evaluating Fault Tolerance Across Distributed Training Architectures
- ML Drift: Next-Gen GPU AI/ML Inference at the Edge
- XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization
- SpecForge v0.3.0: a Unified Disaggregated and Colocated Speculative Decoding Stack, and New Open SpecBundle Draft Models
- SGLang and Miles on NVIDIA Vera Rubin
- Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis
- Cross-Facility LLM Pre-training on HPC: Elastic Aggregation, Data Leasing, and Queue-Aware Placement
- QuantaSpike: Short-Window Spike-Driven Quantization for Large Language Models
- Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition
- Generate What You Can Trust: Content Credibility in Generative Recommenders
- LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation
- ScalarLens: Numerical Embeddings with Stable Coordinates and Contextual Responses for CTR Prediction
- Reading Position Is the Baseline to Beat: A Time-Ordered Evaluation of Personalised Highlight Prediction
- Behavior-Evidence-Based Dynamic User Feature Calibration for Unified-Token Click-Through Rate Prediction
- Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
- Finding the Right Balance: Relevance and Diversity in LLM Retrieval
- The Impact of Backbone Evolution on LLM-Based Relevance Assessments
- Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
- What Transfers from a VLM Teacher? Comparing Supervision Signals for Visual Document Retrieval
- Towards Explaining Query Expansion Performance in Information Retrieval
- Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives
- From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
- Inverting Multi-Vector Visual Document Indices
- From High Recall to High Utility: Dataset-Adaptive Post-Processing of LLM-Generated Customer Intents
- ExperienceIndex: Artifact-Grounded Memory
- SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
- MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
- UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy
- RunningTab: Direct Workspace Interaction with Environment-Side Tabs
- Building Reliable Data Analytics Agents: Lessons from the KDD Cup
- ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation
- From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
- System Switch: When Should a Fast Decision Model Stop and Think?
- BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
- Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders
- Building Navigable Graphs Without Search in Three Composable Stages
- Same Text, Different Prediction: Serving-Context Nondeterminism in Text Classifiers
- LRCC: Generalizing Low-Rank Compression with Conditional Computation