cs.LG（2026-08-28）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9) 支柱九：具身大模型 (Embodied Foundation Models) (8)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Models 提出一种新方法以解决认证代码世界模型中的拓扑问题 world model world models
2 SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning 提出SOMTab以提高表格上下文学习的效率 Mamba foundation model
3 HARTS: Efficient Agentic Reinforcement Learning for Hybrid-Attention Models over Arbitrary Rollout Trees 提出HARTS以解决混合注意力模型中的高效强化学习问题 reinforcement learning linear attention
4 REPLICANT: Learning Policies for Evading and Hardening Malware Detectors 提出Replicant框架以增强恶意软件检测的鲁棒性 reinforcement learning deep reinforcement learning privileged information
5 VISTA: Verifier-Informed Student-to-Teacher Adaptation for On-Policy Self-Distillation 提出VISTA以解决现有自蒸馏方法的单向监督问题 distillation
6 Beyond Flat Netlist: Hierarchical Graph Representation Learning for Scalable Analysis of Sequential Circuits 提出DeepSeq3以解决工业电路分析中的时序动态建模问题 representation learning
7 VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning 提出VICT以解决长时间跨度LLM代理的细粒度信用分配问题 reinforcement learning
8 When Can Conditional Flow Matching Replace Pointwise Negative Log-Likelihood? 提出条件流匹配替代点对点负对数似然的条件 flow matching
9 PhyMamba: Physics-Modulated Mamba for Robust Battery Health Prognostics 提出PhyMamba框架以解决电池健康预测中的挑战 Mamba

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
10 Efficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring 提出COMPASS框架以解决动态环境下的预测过程监控问题 foundation model
11 There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation 提出双向扩散桥接方法以解决多模态翻译问题 multimodal
12 D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoring 提出D-TAIA以解决多任务预测过程监控中的适应性问题 large language model foundation model
13 SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data 提出SymboLLM-FE以解决自动特征工程中的可解释性与迭代问题 large language model
14 Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss 提出学习率与批量大小的缩放规律以优化OpenEuroLLM模型 large language model
15 Parser States Already Know: Structure-Conditioned KV Persistence for Structured Generation 提出PASK以解决结构化生成中的KV持久性问题 large language model
16 Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons 提出生物启发机制以促进多层感知器的Grokking过程 large language model
17 Characterization of Request and Token Energy Costs for LLM Inference Workloads on GPU Platforms 提出LLM推理能耗模型以优化GPU能效 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页