AI.news
主页教程研究工具模型AI创业讨论新闻每日简报WIKI│🚀 创业库★ 投稿
AI+医疗机器人教育金融能源健康娱乐思考
121
0
研究Multi-AUV Ad-hoc network-based Target Tracking: A Value Gradient Guidance Multi-Agent Diffusion Reinforcement Learning Approach(arxiv.org)
11天前原文·0 评论·
0
评论
122
0
研究$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution(arxiv.org)
11天前原文·0 评论·
0
评论
123
0
研究LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining(arxiv.org)
11天前原文·0 评论·
0
评论
124
0
研究MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents(arxiv.org)
11天前原文·0 评论·
0
评论
125
0
研究Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents(arxiv.org)
11天前原文·0 评论·
0
评论
126
0
研究MARCH: Scaling Recurrent Memory with Content-Routed State Anchors(arxiv.org)
11天前原文·0 评论·
0
评论
127
0
研究Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization(arxiv.org)
11天前原文·0 评论·
0
评论
128
0
研究Exploring Oversmoothing with Householder Matrices(arxiv.org)
11天前原文·0 评论·
0
评论
129
0
研究GENADA: efficient generative time series adversarial attack framework(arxiv.org)
11天前原文·0 评论·
0
评论
130
0
研究Which Site, and When: A Free-Satellite-Data Test of Himalayan Glacial Lake Bursts, Landslides, and Ice Floods(arxiv.org)
11天前原文·0 评论·
0
评论
131
0
研究Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation(arxiv.org)
11天前原文·0 评论·
0
评论
132
0
研究Geometric and Behavioral Stratification in Transformer Residual Streams(arxiv.org)
11天前原文·0 评论·
0
评论
133
0
研究Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists(arxiv.org)
11天前原文·0 评论·
0
评论
134
0
研究Position: The Alignment Community is Unintentionally Building a Censor's Toolkit(arxiv.org)
11天前原文·0 评论·
0
评论
135
0
研究Scaling Automatic Research Agents via World Models(arxiv.org)
11天前原文·0 评论·
0
评论
136
0
研究Position: Reasoning is a Learnable Rule-Based Process(arxiv.org)
11天前原文·0 评论·
0
评论
137
0
研究Roundtables: Inside the “Censorship-Industrial Complex” Idea Shaping US Policy(technologyreview.com)
11天前原文·0 评论·
0
评论
138
0
研究Flock is tightening its rules in response to a growing surveillance backlash(technologyreview.com)
12天前原文·0 评论·
0
评论
139
0
研究The Download: kids’ thoughts on AI, and female clones of male mice(technologyreview.com)
12天前原文·0 评论·
0
评论
140
0
研究How kids feel about AI, in their own words(technologyreview.com)
12天前原文·0 评论·
0
评论
141
0
研究Distribird: Literature-Informed Prior Distribution Design for Bayesian Model Calibration(arxiv.org)
12天前原文·0 评论·
0
评论
142
0
研究MaSRead: Content-Addressed Reading of Replicated Latent Stores(arxiv.org)
12天前原文·0 评论·
0
评论
143
0
研究From Monolithic to Modular: Segment-level Automatic Prompt Optimization(arxiv.org)
12天前原文·0 评论·
0
评论
144
0
研究A Conceptual Framework for Refining Influence Knowledge from Simulation Evidence in Cyber-Physical Systems(arxiv.org)
12天前原文·0 评论·
0
评论
145
0
研究Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop(arxiv.org)
12天前原文·0 评论·
0
评论
146
0
研究Dynamic Governance of Multi-LLM Agent Systems for Collaborative Conversational Outcomes(arxiv.org)
12天前原文·0 评论·
0
评论
147
0
研究AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research(arxiv.org)
12天前原文·0 评论·
0
评论
148
0
研究LLMs in Process Diagram Engineering: From Optimal PFDs to Validated P&IDs(arxiv.org)
12天前原文·0 评论·
0
评论
149
0
研究Scientists just created female clones of male mice(technologyreview.com)
12天前原文·0 评论·
0
评论
150
0
研究Scaling AI agents with trustworthy data(technologyreview.com)
12天前原文·0 评论·
0
评论
上一页1234567下一页