2026-03-13

AI每日新闻汇总存档

前往 AI新闻雷达 看每日更新 → 返回存档列表

KernelSkill: A Multi-Agent Framework for GPU Kernel Optimization
未知来源
No summary
MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenarios
未知来源
No summary
Markovian Generation Chains in Large Language Models
未知来源
No summary
IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
未知来源
No summary
DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use
未知来源
No summary
COMPASS: The explainable agentic framework for Sovereignty, Sustainability, Compliance, and Ethics
未知来源
No summary
Distributed Kalman--Consensus Filtering with Adaptive Uncertainty Weighting for Multi-Object Tracking in Mobile Robot Networks
未知来源
No summary
Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
未知来源
No summary
One Supervisor, Many Modalities: Adaptive Tool Orchestration for Autonomous Queries
未知来源
No summary
RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
未知来源
No summary
Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
未知来源
No summary
Stop Listening to Me! How Multi-turn Conversations Can Degrade Diagnostic Reasoning
未知来源
No summary
Training Language Models via Neural Cellular Automata
未知来源
No summary
The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning
未知来源
No summary
AI Psychometrics: Evaluating the Psychological Reasoning of Large Language Models with Psychometric Validities
未知来源
No summary
FinRule-Bench: A Benchmark for Joint Reasoning over Financial Tables and Principles
未知来源
No summary
DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
未知来源
No summary
MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries
未知来源
No summary
📚 返回存档列表  |  🏠 返回首页