全部收录论文
论文 · 第 122 页
共 7039 篇 · 按日期新到旧 · 每页 50 篇 · 第 122 / 141 页
查找论文请用站内搜索。
- IndoBERT-Relevancy: A Context-Conditioned Relevancy Classifier for Indonesian Text
- ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims
- Automating Clinical Information Retrieval from Finnish Electronic Health Records Using Large Language Models
- CitiLink: Enhancing Municipal Transparency and Citizen Engagement through Searchable Meeting Minutes
- Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
- Attention-Aligned Reasoning for Large Language Models
- AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agents
- AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation
- Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation
- Consistency Amplifies: How Behavioral Variance Shapes Agent Accuracy
- Ask or Assume? Uncertainty-Aware Clarification-Seeking in Coding Agents
- Learning to Commit: Generating Organic Pull Requests via Online Repository Memory
- Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery
- The Dual-State Architecture for Reliable LLM Agents
- Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration
- SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
- Route Experts by Sequence, not by Token
- KALAVAI: Predicting When Independent Specialist Fusion Works -- A Quantitative Model for Post-Hoc Cooperative LLM Training
- MemBoost: A Memory-Boosted Framework for Cost-Aware LLM Inference
- Label-Free Cross-Task LoRA Merging with Null-Space Compression
- Syncopate: Efficient Multi-GPU AI Kernels via Automatic Chunk-Centric Compute-Communication Overlap
- Systematic Characterization of LLM Quantization: A Performance, Energy, and Quality Perspective
- Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
- Utility-Driven Speculative Decoding for Mixture-of-Experts
- MiniRec: Data-Efficient Reinforcement Learning for LLM-based Recommendation
- LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
- Hyena Operator for Fast Sequential Recommendation
- Unbiased Multimodal Reranking for Long-Tail Short-Video Search
- DIET: Learning to Distill Dataset Continually for Recommender Systems
- MCLMR: A Model-Agnostic Causal Learning Framework for Multi-Behavior Recommendation
- Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation
- R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
- WebThinker: Empowering Large Reasoning Models with Deep Research Capability
- MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
- Knowledge-Aware Iterative Retrieval for Multi-Agent Systems
- Characterizing Deep Research: A Benchmark and Formal Definition
- KV Cache Optimization Strategies for Scalable and Efficient LLM Inference
- Demystifying When Pruning Works via Representation Hierarchies
- A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference
- ConFu: Contemplate the Future for Better Speculative Sampling
- Qwen3-Coder-Next Technical Report
- OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
- PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations
- Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits
- Self-Distillation for Multi-Token Prediction
- The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
- Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries
- HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
- Beyond Masks: Efficient, Flexible Diffusion Language Models via Deletion-Insertion Processes