cs.LG（2026-09-21）

📊 共 25 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (14) 支柱九：具身大模型 (Embodied Foundation Models) (10) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	$t_0$: A Time-Series Foundation Model for Forecasting with Context	提出$t_0$模型以解决多变量时间序列预测问题	MAE foundation model
2	Lifted Bellman Linear Programming for Offline Reinforcement Learning	提出Lifted Bellman线性规划以解决离线强化学习中的价值估计问题	reinforcement learning offline reinforcement learning
3	Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders	通过稀疏自编码器比较状态空间模型与变换器的潜在概念形成	Mamba SSM state space model
4	Pharmacokinetic State Space Models for Unbiased Prediction of Haemodynamic Collapse	提出药物动力学状态空间模型以预测血流动力学崩溃	predictive model Mamba state space model
5	Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision	提出基于强化学习的黑箱对抗攻击以解决计算机视觉模型脆弱性问题	reinforcement learning
6	Learning Prognostic Variables for AI Convective Parameterizations via Symbolic Distillation	通过符号蒸馏学习预后变量以改进气候模型参数化	distillation
7	Reinforcement Learning in Operational Research: A Technical Review and Practical Roadmap	提出强化学习以增强运筹学在动态决策中的应用	reinforcement learning
8	iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs	提出iSDFT以解决持续学习中的教师信息控制问题	distillation
9	TTSE: A Two-Track Online Self-Evolution Framework	提出TTSE框架以解决LLM自主进化问题	reinforcement learning large language model
10	H-Spec: Parallel Speculative Decoding Without a Drafter-Side KV Cache	提出H-Spec以解决KV缓存开销问题	Mamba large language model
11	Acceptance-Aware Draft Model Training for Speculative Decoding	提出接受长度感知训练损失以优化推测解码	reinforcement learning large language model
12	CLOOPD: Closing the Learner Loop in On-Policy Distillation	提出CLOOPD框架以优化在线策略蒸馏过程	distillation
13	Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective	提出分布式强化学习以解决部分可观测环境中的不确定性问题	reinforcement learning
14	MGRD: Compact morphology-gated residual diffusion for variance-aware cross-domain neurite forecasting	提出MGRD以解决神经突起形态预测中的不确定性问题	MAE spatiotemporal

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

#	题目	一句话要点	标签	🔗	⭐
15	Detecting Agitation Before Behavioral Escalation in Autistic Youth Through Multimodal Wearable Sensing	通过多模态可穿戴传感器检测自闭症青少年行为升级前的焦虑状态	foundation model multimodal
16	Misaligned Clinical Risk Classification and Cost Asymmetry in Open-Weight Large Language Models	探讨开放权重大语言模型中的临床风险分类与成本不对称问题	large language model
17	A Temporal Knowledge Graph for Music Festival Lineup Forecasting	提出时序知识图谱以解决音乐节阵容预测问题	large language model TAMP
18	LoRA-generating hypernetworks for efficient on-device LLM generative personalization	提出LoRA生成超网络以实现高效的设备端LLM个性化	large language model
19	Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction	提出Universal Multi-Modal Traceformer以解决异构上下文在事件预测中的不足	TAMP
20	RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale	提出RAILS以解决大规模LLM聚类效率问题	large language model
21	WPBench: A Comprehensive Benchmark for Wind Power Forecasting	提出WPBench以解决风电预测基准评估不足问题	foundation model
22	ARM: Attention with Routed-Memory for Learnable Sparse Control	提出ARM以解决长上下文推理中的KV缓存问题	large language model
23	Machine Learning-Based Prediction of Childhood Stunting in Bangladesh: Fairness and Temporal Robustness Assessment	基于机器学习的孟加拉国儿童生长迟缓预测模型	foundation model
24	A Distributional Optimisation Perspective on Combining Models in Deep Learning	提出基于分布优化的模型组合方法以提升深度学习性能	large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
25	Mind or Message? Auditing Theory of Mind in Multi-Agent Social Simulation	通过多代理社会模拟审计心智理论以解决理解不足问题	egocentric

⬅️ 返回 cs.LG 首页 · 🏠 返回主页