每月论文更新 - 2026年05月02日

[github-actions]

最后更新：2026-05-02 06:52

本次更新执行命令

D:\a\MyAutoPapers\MyAutoPapers\target\release\my_auto_papers.exe --keywords=
             efficient reinforcement learning/sample efficient reinforcement learning,
             model-based reinforcement learning/world model,
             offline reinforcement learning,
             efficient vision transformer/mobile vit/lightweight vit,
             efficient image classification/efficient object detection/efficient semantic segmentation,
             efficient diffusion model/one-step diffusion/distillation diffusion,
             efficient cpu inference/on-device inference/edge inference,
             model quantization/low-bit quantization/binary neural network,
             network pruning/sparse neural network/knowledge distillation,
             tensor compilation/computation graph optimization/operator fusion,
             image super resolution/efficient super resolution,
             video super resolution,
             quantitative trading/algorithmic trading/reinforcement learning for trading,
             stock prediction/portfolio optimization/financial time series forecasting,
             neuroevolution/NEAT/evolutionary neural network,
             neural architecture search/multi-objective neural architecture search
              --exclude-keywords=multi-agent,multiagent --per-keyword-max-result=8

参数详解

• 关键词：efficient reinforcement learning/sample efficient reinforcement learning, model-based reinforcement learning/world model, offline reinforcement learning, efficient vision transformer/mobile vit/lightweight vit, efficient image classification/efficient object detection/efficient semantic segmentation, efficient diffusion model/one-step diffusion/distillation diffusion, efficient cpu inference/on-device inference/edge inference, model quantization/low-bit quantization/binary neural network, network pruning/sparse neural network/knowledge distillation, tensor compilation/computation graph optimization/operator fusion, image super resolution/efficient super resolution, video super resolution, quantitative trading/algorithmic trading/reinforcement learning for trading, stock prediction/portfolio optimization/financial time series forecasting, neuroevolution/NEAT/evolutionary neural network, neural architecture search/multi-objective neural architecture search
• 排除关键词：multi-agent, multiagent
• 每关键词最大结果：8
• 目标领域：cs, stat
• 每关键词重试次数：3

论文汇总（152篇）

更好的阅读体验请访问 Github页面。

1. efficient reinforcement learning/sample efficient reinforcement learning

序号	标题	日期
1	Factorized Latent Reasoning for LLM-based Recommendation	2026-04-29
2	TL-RL-FusionNet: An Adaptive and Efficient Reinforcement Learning-Driven Transfer Learning Framework for Detecting Evolving Ransomware Threats	2026-04-22
3	Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems	2026-04-21
4	Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification	2026-04-21
5	Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning	2026-04-19
6	A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions	2026-04-19
7	EasyVideoR1: Easier RL for Video Understanding	2026-04-18
8	WOMBET: World Model-based Experience Transfer for Robust and Sample-efficient Reinforcement Learning	2026-04-10
9	What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators	2026-03-23
10	Discounted Beta--Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards	2026-03-19
11	Structured Uncertainty guided Clarification for LLM Agents	2025-11-11
12	Reinforcement Learning Using known Invariances	2025-11-05
13	Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning	2025-10-01
14	Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor	2025-01-30
15	Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning	2025-01-27

2. model-based reinforcement learning/world model

序号	标题	日期
1	HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation	2026-04-30
2	LaST-R1: Reinforcing Action via Adaptive Physical Latent Reasoning for VLA Models	2026-04-30
3	Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling	2026-04-30
4	Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces	2026-04-30
5	Dreaming Across Towns: Semantic Rollout and Town-Adversarial Regularization for Zero-Shot Held-Out-Town Fixed-Route Driving in CARLA	2026-04-30
6	GUI Agents with Reinforcement Learning: Toward Digital Inhabitants	2026-04-30
7	Flying by Inference: Active Inference World Models for Adaptive UAV Swarms	2026-04-30
8	Simulating clinical interventions with a generative multimodal model of human physiology	2026-04-30
9	Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift	2026-04-30
10	Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Space Models	2026-04-28
11	Efficient Reinforcement Learning using Linear Koopman Dynamics for Nonlinear Robotic Systems	2026-04-21
12	Model-Based Reinforcement Learning Exploits Passive Body Dynamics for High-Performance Biped Robot Locomotion	2026-04-16
13	DynaWeb: Model-Based Reinforcement Learning of Web Agents	2026-01-29
14	Model-Based Reinforcement Learning under Random Observation Delays	2025-09-25
15	Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories	2024-11-07

3. offline reinforcement learning

序号	标题	日期
1	Lyapunov-Guided Self-Alignment: Test-Time Adaptation for Offline Safe Reinforcement Learning	2026-04-29
2	TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning	2026-04-28
3	Learning from Demonstration with Failure Awareness for Safe Robot Navigation	2026-04-25
4	Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning	2026-04-24
5	OpAgent: Operator Agent for Web Navigation	2026-02-14
6	Generalisation in Multitask Fitted Q-Iteration and Offline Q-learning	2025-12-23
7	Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning	2025-08-27

4. efficient vision transformer/mobile vit/lightweight vit

序号	标题	日期
1	MPM: Mutual Pair Merging for Efficient Vision Transformers	2026-04-07
2	A Two-stage Transformer Framework for Temporal Localization of Distracted Driver Behaviors	2026-03-22
3	$D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation	2026-03-17
4	BornoViT: A Novel Efficient Vision Transformer for Bengali Handwritten Basic Characters Classification	2026-02-28
5	TCFormer: A 5M-Parameter Transformer with Density-Guided Aggregation for Weakly-Supervised Crowd Counting	2025-12-21
6	GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search	2025-12-13
7	Energy-Efficient Vision Transformer Inference for Edge-AI Deployment	2025-11-28
8	GSPN-2: Efficient Parallel Sequence Modeling	2025-11-28
9	Frequency-Aware Token Reduction for Efficient Vision Transformer	2025-11-26
10	Neural-HAR: A Dimension-Gated CNN Accelerator for Real-Time Radar Human Activity Recognition	2025-10-26
11	M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception	2025-10-20
12	When Small Guides Large: Cross-Model Co-Learning for Test-Time Adaptation	2025-06-30
13	S2AFormer: Strip Self-Attention for Efficient Vision Transformer	2025-05-28
14	WriteViT: Handwritten Text Generation with Vision Transformer	2025-05-19
15	Image Recognition with Online Lightweight Vision Transformer: A Survey	2025-05-06
16	Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment	2025-04-03
17	Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking	2025-03-09
18	Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors	2024-06-07

5. efficient image classification/efficient object detection/efficient semantic segmentation

序号	标题	日期
1	Breaking the Resource Wall: Geometry-Guided Sequence Modeling for Efficient Semantic Segmentation	2026-04-25
2	Semantic-Fast-SAM: Efficient Semantic Segmenter	2026-04-22
3	Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling	2026-04-13
4	Cross-Stage Attention Propagation for Efficient Semantic Segmentation	2026-04-07
5	AceleradorSNN: A Neuromorphic Cognitive System Integrating Spiking Neural Networks and DynamicImage Signal Processing on FPGA	2026-03-30
6	Vision Tiny Recursion Model (ViTRM): Parameter-Efficient Image Classification via Recursive State Refinement	2026-03-19
7	Explainability-Inspired Layer-Wise Pruning of Deep Neural Networks for Efficient Object Detection	2026-02-15
8	Cross-Layer Attentive Feature Upsampling for Low-latency Semantic Segmentation	2026-01-03
9	Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification	2025-11-24
10	Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision	2025-11-18
11	MCAQ-YOLO: Morphological Complexity-Aware Quantization for Efficient Object Detection with Curriculum Learning	2025-11-17
12	An Efficient Semantic Segmentation Decoder for In-Car or Distributed Applications	2025-10-19
13	Quantization Robustness to Input Degradations for Object Detection	2025-08-27
14	KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learning	2025-08-11
15	DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detection	2025-06-29
16	Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction	2025-06-20
17	Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks	2025-06-09
18	Hierarchical Sparse Attention Framework for Computationally Efficient Classification of Biological Cells	2025-05-12
19	Identifying regions of interest in whole slide images of renal cell carcinoma	2025-04-09
20	Adaptive Object Detection for Indoor Navigation Assistance: A Performance Evaluation of Real-Time Algorithms	2025-01-30
21	SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neural Networks	2025-01-25
22	SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation	2024-11-26
23	FBNetV5: Neural Architecture Search for Multiple Tasks in One Run	2021-11-19

6. efficient diffusion model/one-step diffusion/distillation diffusion

序号	标题	日期
1	Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models	2026-04-29
2	MetaSR: Content-Adaptive Metadata Orchestration for Generative Super-Resolution	2026-04-29
3	GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution	2026-04-28
4	Bridging Restoration and Generation Manifolds in One-Step Diffusion for Real-World Super-Resolution	2026-04-27
5	One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection	2026-04-20
6	Efficient Diffusion Models under Nonconvex Equality and Inequality constraints via Landing	2026-04-20
7	DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration	2026-04-16
8	1.x-Distill: Breaking the Diversity, Quality, and Efficiency Barrier in Distribution Matching Distillation	2026-04-05
9	FODMP: Fast One-Step Diffusion of Movement Primitives Generation for Time-Dependent Robot Actions	2026-03-25
10	Timestep-Aware Block Masking for Efficient Diffusion Model Inference	2026-03-20
11	TempoSyncDiff: Distilled Temporally-Consistent Diffusion for Low-Latency Audio-Driven Talking Head Generation	2026-03-06
12	Manifold-Aligned Generative Transport	2026-02-23
13	IDLM: Inverse-distilled Diffusion Language Models	2026-02-22
14	Robot-DIFT: Distilling Diffusion Features for Geometrically Consistent Visuomotor Control	2026-02-12
15	d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation	2026-01-12
16	From Structure to Detail: Hierarchical Distillation for Efficient Diffusion Model	2025-11-12
17	Test-Time Iterative Error Correction for Efficient Diffusion Models	2025-11-09
18	Adversarial Concept Distillation for One-Step Diffusion Personalization	2025-10-23
19	FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring	2025-10-02
20	Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution	2025-09-28
21	SpecDiff: Accelerating Diffusion Model Inference with Self-Speculation	2025-09-17
22	R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation	2025-06-09
23	Distributional Statistics Restore Training Data Auditability in One-step Distilled Diffusion Models	2025-02-05
24	Learnable Sparsity for Vision Generative Models	2024-12-03

7. efficient cpu inference/on-device inference/edge inference

序号	标题	日期
1	EdgeFM: Efficient Edge Inference for Vision-Language Models	2026-04-30
2	Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices	2026-04-25
3	Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities	2026-04-24
4	Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference	2026-04-23
5	Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM	2026-04-20
6	MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment	2026-04-18
7	Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition	2026-04-17
8	A Fully GPU-Accelerated Framework for High-Performance Configuration Interaction Selection with Neural Network Quantum States	2026-04-17
9	Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks	2026-04-17
10	A Case Study on Energy-Efficient Edge AI Crack Segmentation	2026-04-15
11	Systems-Level Attack Surface of Edge Agent Deployments on IoT	2026-02-26
12	SLIDE: Simultaneous Model Downloading and Inference at the Wireless Network Edge	2025-12-24
13	Programmable and GPU-Accelerated Edge Inference for Real-Time ISAC on NVIDIA Aerial Testbed	2025-12-06
14	Harnessing Non-convex Quantum Correlations of Independent Qubits	2025-10-14
15	Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement	2025-08-18
16	Combolutional Neural Networks	2025-07-28
17	Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT	2024-07-06
18	Neural Waveshaping Synthesis	2021-07-11

8. model quantization/low-bit quantization/binary neural network

序号	标题	日期
1	CoQuant: Joint Weight-Activation Subspace Projection for Mixed-Precision LLMs	2026-04-29
2	Transformer-Based Rhythm Quantization of Performance MIDI Using Beat Annotations	2026-04-24
3	IoT-Enhanced CNN-Based Labelled Crack Detection for Additive Manufacturing Image Annotation in Industry 4.0	2026-04-22
4	LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation	2026-04-21
5	Towards Joint Quantization and Token Pruning of Vision-Language Models	2026-04-19
6	LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning	2026-04-16
7	Slithering Through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging	2026-04-12
8	SEPTQ: A Simple and Effective Post-Training Quantization Paradigm for Large Language Models	2026-04-11
9	Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory	2026-04-10
10	Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference	2026-03-16
11	Scalable Digital Compute-in-Memory Ising Machines for Robustness Verification of Binary Neural Networks	2026-03-05
12	Robustness Verification of Binary Neural Networks: An Ising and Quantum-Inspired Framework	2026-02-14
13	Eventizing Traditionally Opaque Binary Neural Networks as 1-safe Petri net Models	2026-02-13
14	LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs	2026-02-04
15	Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks	2026-01-30
16	From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs	2026-01-07
17	BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training	2025-12-03
18	Highly Efficient and Effective LLMs with Multi-Boolean Architectures	2025-05-28
19	Optimizing Binary and Ternary Neural Network Inference on RRAM Crossbars using CIM-Explorer	2025-05-20
20	Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall	2025-05-20
21	Sampling-Aware Quantization for Diffusion Models	2025-05-04
22	Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration	2025-03-27
23	AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization	2025-03-05
24	Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization	2024-08-01

12. video super resolution

序号	标题	日期
1	BurstGP: Enhancing Raw Burst Image Super Resolution with Generative Priors	2026-04-26
2	A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models	2026-04-23
3	GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting	2026-04-20
4	Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models	2026-04-12
5	ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation	2026-03-18
6	Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution	2026-02-03
7	Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion	2025-12-29
8	Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolution	2025-09-28