cs.AI（2025-01-29）

📊 共 14 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling Janus-Pro：通过数据和模型扩展实现统一的多模态理解与生成 multimodal instruction following
2 Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation Virus：一种绕过安全防护的大语言模型有害微调攻击方法 large language model ✅
3 Large Language Models Think Too Fast To Explore Effectively 揭示大语言模型探索能力不足：推理速度过快导致探索效率降低 large language model
4 Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization 提出IBPO算法，通过推理感知优化实现大语言模型在数学问题上的自适应推理。 large language model chain-of-thought
5 Reflections on "Can AI Understand Our Universe?" 探讨AI理解宇宙的可能性：直觉、因果与新兴AI技术 multimodal chain-of-thought
6 Early External Safety Testing of OpenAI's o3-mini: Insights from the Pre-Deployment Evaluation 利用ASTRAL工具进行早期外部安全测试，评估OpenAI o3-mini模型的安全性。 large language model
7 Using Code Generation to Solve Open Instances of Combinatorial Design Problems CPro1协议利用代码生成解决组合设计开放问题，成功构造六种设计。 large language model
8 The Imitation Game According To Turing 严格图灵测试揭示GPT-4-Turbo未通过，驳斥了当前AI“思考”的过分主张。 large language model
9 Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant 提出对话式XAI界面，提升用户理解与信任，但需警惕过度依赖 large language model ✅
10 Neural Spelling: A Spell-Based BCI System for Language Neural Decoding 提出基于课程学习的神经拼写框架，用于全字母脑机接口语言神经解码 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Aggregation Schemes for Single-Vector WSI Representation Learning in Digital Pathology 评估多种聚合方法用于数字病理中单向量WSI表征学习，提升WSI检索性能 representation learning foundation model
12 PulmoFusion: Advancing Pulmonary Health with Efficient Multi-Modal Fusion PulmoFusion：利用高效多模态融合推进肺部健康监测 predictive model MAE multimodal ✅
13 VoicePrompter: Robust Zero-Shot Voice Conversion with Voice Prompt and Conditional Flow Matching VoicePrompter：基于语音提示和条件流匹配的鲁棒零样本语音转换 flow matching ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 Large Language Models for Single-Step and Multi-Step Flight Trajectory Prediction 首个将大语言模型应用于单步和多步飞行轨迹预测的研究 spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页