登录 注册
Can LLMs Reliably Self-Report Adversarial Prefills, and How?
👁 73 📚 27
Randomized YaRN Improves Length Generalization for Long-Context Reasoning
👁 150 📚 13
Beyond Global Replanning: Hierarchical Recovery for Cross-Device Agent Systems
👁 177 📚 6
StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
👁 158 📚 14
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
👁 184 📚 25
Native Active Perception as Reasoning for Omni-Modal Understanding
👁 214 📚 3
Variable-Width Transformers
👁 171 📚 14
The Value Axis: Language 模型 (Model)s Encode Whether They're on the Right Track
The Value Axis: Language Models Encode Whether They're on the Right Track
👁 176 📚 29
ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning
👁 152 📚 11
Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for 数据 (Data) Attributi...
Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution
👁 147 📚 9
学习 (Learning) to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning
👁 82 📚 18
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
👁 130 📚 19
Doc-to-Atom: 学习 (Learning) to Compile and Compose Memory Atoms
Doc-to-Atom: Learning to Compile and Compose Memory Atoms
👁 77 📚 25
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
👁 63 📚 16
Causally Evaluating the Learnability of Formal Language Tasks
👁 23 📚 23
How reliable are LLMs when it comes to playing dice?
👁 199 📚 2
Self-Augmenting Retrieval for Diffusion Language 模型 (Model)s
Self-Augmenting Retrieval for Diffusion Language Models
👁 137 📚 8
Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text...
👁 68 📚 1
Code2LoRA: Hypernetwork-Generated Adapters for Code Language 模型 (Model)s under Software Evolution
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
👁 83 📚 29
STRIDE: Training 数据 (Data) Attribution via Sparse Recovery from Subset Perturbations
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
👁 165 📚 8
海洋智能体 🌊
海洋智能体
AI科研助手 · 2983篇文献
你好!你正在浏览文献列表,我可以帮你筛选方向、推荐高引论文或解读某个研究领域。