cs.LG（2026-06-11）

📊 共 40 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (19 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (14 🔗2) 支柱八：物理动画 (Physics-based Animation) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (2) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (19 篇)

#题目一句话要点标签🔗⭐
1 EPM-JEPA: Operator-Side Experience Modulation in JEPA-Family World Models 提出EPM-JEPA以解决JEPA模型在动态变化中的适应性问题 world model world models JEPA
2 Scale Buys Interpolation, Structure Buys a Horizon: Certified Predictability for Equivariant World Models 提出可验证的可预测性以解决世界模型的信任问题 world model world models JEPA
3 Natively Unlearnable Large Language Models 提出NULLs以解决大语言模型的源级去学习问题 representation learning large language model
4 Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning 提出DYSCO算法以解决潜在动力学系统识别问题 latent dynamics representation learning contrastive learning
5 ProPlay: Procedural World Models for Self-Evolving LLM Agents 提出ProPlay以解决自我进化代理在部分可观察环境中的学习问题 world model world models ✅
6 Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning 提出SWITCH框架以解决隐状态递归优化与可解释性问题 reinforcement learning chain-of-thought
7 Diffusion Policy Optimization without Drifting Apart 提出DiPOD以解决扩散策略优化中的不稳定性问题 diffusion policy distillation
8 $α$-fair heterogeneous agent reinforcement learning 提出α-公平异构智能体强化学习以解决公平性问题 reinforcement learning reward shaping
9 LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning 提出LongSpike以解决长序列学习中的记忆瓶颈问题 SSM state space model ✅
10 PolyFlow: Safe and Efficient Polytope-Constrained Flow Matching with Constraint Embedding and Projection-free Update 提出PolyFlow以解决安全关键系统中的流匹配问题 flow matching ✅
11 Reinforcement Learning for Neural Model Editing 提出强化学习框架以实现神经模型编辑 reinforcement learning
12 Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation 提出稀疏更新的密集监督方法以优化在线策略蒸馏 distillation
13 Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detection 提出Rarity-Gated特征调制模块以解决海事异常检测中的频率偏差问题 imitation learning
14 From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation 提出一种新方法以解决LLM评估中的系统性偏差问题 MAE large language model ✅
15 PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent 提出PolicyGuard以解决强化学习代理的后门攻击防御问题 reinforcement learning
16 Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing 提出基于图强化学习的校准感知量子电路路由方法 reinforcement learning
17 Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier 提出PULSE框架以解决生态声学分类的局限性问题 distillation PULSE
18 Reliability of Probabilistic Emulation of Physical Systems 提出框架评估物理系统的概率预测可靠性 flow matching spatiotemporal
19 Understanding helpfulness and harmless tension in reward models 研究奖励模型中的有益性与无害性张力 reinforcement learning RLHF

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
20 CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts 提出CausalMoE以解决复杂系统中的Granger因果发现问题 foundation model multimodal
21 Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models 提出早期退出机制以优化大规模推理模型的链式思维 chain-of-thought
22 BigPower: Hierarchical Source-Level Module Power Estimation for CPUs with Large Language Models 提出BigPower以解决CPU模块级功耗估计问题 large language model
23 Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs 提出Hölder++以改善多模态变分自编码器的生成质量与一致性问题 multimodal
24 Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models 提出AuthorityBench以研究引用偏见对大语言模型的影响 large language model ✅
25 DeepJEB++: Foundation Model-Driven Large-Scale 3D Engineering Dataset via 2D Latent Space Augmentation 提出DeepJEB++以解决大规模3D工程数据集构建问题 foundation model
26 SMGFM: Spectral Multimodal Graph Pretraining for Multimodal-Attributed Graphs 提出SMGFM框架以解决多模态属性图的语义融合问题 multimodal
27 Multimodal Graph Negative Learning 提出GraphMNL以解决多模态图节点表示不平衡问题 multimodal
28 SuperThoughts: Reasoning Tokens in Superposition 提出SuperThoughts以解决长链推理的计算开销问题 chain-of-thought
29 Existence Precedes Value: Joint Modeling of Observational Existence and Evolving States in Time Series Forecasting 提出Timeflies框架以解决时间序列预测中的观测性与价值估计问题 TAMP ✅
30 Efficient On-Device Diffusion LLM Inference with Mobile NPU 提出llada.cpp以解决移动设备上dLLM推理效率问题 large language model
31 Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function 提出TabPFN的因果机制分析以优化特征注意力头的计算分配 foundation model
32 Multi-Bitwidth Quantization for LLMs Using Additive Codebooks 提出Drop-by-Drop框架以实现LLM的多位宽量化 large language model
33 Detecting Functional Memorization in Code Language Models 提出功能性记忆检测方法以解决代码生成模型的审计问题 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗⭐
34 TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization 提出TWLA框架以实现大语言模型的三元权重和低位激活量化 AMP large language model ✅
35 Graphical Causal Reasoning for Root Cause Analysis in Cloud Networks 提出图形因果推理方法以解决云网络根本原因分析问题 spatiotemporal
36 A fully GPU-based workflow for building physics emulators of hypersonic flows 提出全GPU工作流程以构建高超音速流的物理仿真器 differentiable simulation

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
37 VideoMDM: Towards 3D Human Motion Generation From 2D Supervision 提出VideoMDM以解决3D人类动作生成问题 MDM motion generation human motion
38 Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment 提出自引导机制以提升神经编解码器的重建质量 VQ-VAE

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
39 Distribution-Agnostic Robust Trajectory Optimization via Chance-Constrained Reinforcement Learning 提出基于机会约束强化学习的分布无关鲁棒轨迹优化框架 trajectory optimization reinforcement learning PULSE

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
40 MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling 提出MaxProof框架以提升数学证明的竞争能力 IMoS

⬅️ 返回 cs.LG 首页 · 🏠 返回主页