每月论文更新 - 2026年02月02日

## 最后更新：2026-02-02 00:05
**本次更新执行命令**
```
D:\a\MyAutoPapers\MyAutoPapers\target\release\my_auto_papers.exe --keywords=
             efficient RL,
             partial observable markov decision process/pomdp,sparse reward reinforcement learning,
             casual RL/counterfactual RL/casual reinforcement learning,
             causal inference/causal discovery/counterfactual reasoning,
             video super resolution,
             knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding,
             combinatorial game theory/xiangqi/chinese chess,
             code llm,
             speech recognition,
             zero shot tracking/few shot tracking/pose tracking/pose estimation,
             text to 3d/image to 3d/text to texture,
             automated theorem proving/interactive theorem proving/formal verification
              --exclude-keywords=multi-agent,multiagent --per-keyword-max-result=8
```

**参数详解**
- 关键词：`efficient RL`, `partial observable markov decision process/pomdp`, `sparse reward reinforcement learning`, `casual RL/counterfactual RL/casual reinforcement learning`, `causal inference/causal discovery/counterfactual reasoning`, `video super resolution`, `knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding`, `combinatorial game theory/xiangqi/chinese chess`, `code llm`, `speech recognition`, `zero shot tracking/few shot tracking/pose tracking/pose estimation`, `text to 3d/image to 3d/text to texture`, `automated theorem proving/interactive theorem proving/formal verification`
- 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（202篇）

**更好的阅读体验请访问 [Github页面](https://github.com/dbsxdbsx/MyAutoPapers)。**


### 1. efficient RL
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents](https://arxiv.org/abs/2601.21699v1)** | 2026-01-29 |
| **2** | **[Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes](https://arxiv.org/abs/2601.18795v1)** | 2026-01-26 |
| **3** | **[Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge](https://arxiv.org/abs/2601.17534v1)** | 2026-01-24 |
| **4** | **[Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models](https://arxiv.org/abs/2601.04731v1)** | 2026-01-08 |
| **5** | **[Evaluating Parameter Efficient Methods for RLVR](https://arxiv.org/abs/2512.23165v2)** | 2025-12-29 |
| **6** | **[$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models](https://arxiv.org/abs/2510.25889v3)** | 2025-10-29 |
| **7** | **[RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation](https://arxiv.org/abs/2509.15965v2)** | 2025-09-19 |
| **8** | **[Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation](https://arxiv.org/abs/2502.10138v4)** | 2025-02-14 |
### 2. partial observable markov decision process/pomdp
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function](https://arxiv.org/abs/2601.20554v1)** | 2026-01-28 |
| **2** | **[Structural Monotonicity in Transmission Scheduling for Remote State Estimation with Hidden Channel Mode](https://arxiv.org/abs/2601.19131v1)** | 2026-01-27 |
| **3** | **[Toward Learning POMDPs Beyond Full-Rank Actions and State Observability](https://arxiv.org/abs/2601.18930v1)** | 2026-01-26 |
| **4** | **[Neural Value Iteration](https://arxiv.org/abs/2511.08825v2)** | 2025-11-11 |
| **5** | **[The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://arxiv.org/abs/2509.02547v4)** | 2025-09-02 |
| **6** | **[Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents](https://arxiv.org/abs/2505.11708v2)** | 2025-05-16 |
| **7** | **[Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information](https://arxiv.org/abs/2306.08762v4)** | 2023-06-14 |
### 3. sparse reward reinforcement learning
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?](https://arxiv.org/abs/2509.03790v2)** | 2025-09-04 |
| **2** | **[LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning](https://arxiv.org/abs/2508.18420v1)** | 2025-08-25 |
| **3** | **[SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning](https://arxiv.org/abs/2506.01096v2)** | 2025-06-01 |
| **4** | **[DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning](https://arxiv.org/abs/2505.19850v2)** | 2025-05-26 |
| **5** | **[STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs](https://arxiv.org/abs/2505.15804v3)** | 2025-05-21 |
| **6** | **[Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model](https://arxiv.org/abs/2503.11339v2)** | 2025-03-14 |
| **7** | **[Hedging with Sparse Reward Reinforcement Learning](https://arxiv.org/abs/2503.04218v1)** | 2025-03-06 |
| **8** | **[Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations](https://arxiv.org/abs/2412.01114v2)** | 2024-12-02 |
### 4. casual RL/counterfactual RL/casual reinforcement learning
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL](https://arxiv.org/abs/2502.12436v3)** | 2025-02-18 |
| **2** | **[Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation](https://arxiv.org/abs/2012.09092v1)** | 2020-12-16 |
### 5. causal inference/causal discovery/counterfactual reasoning
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[ECSEL: Explainable Classification via Signomial Equation Learning](https://arxiv.org/abs/2601.21789v1)** | 2026-01-29 |
| **2** | **[Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation](https://arxiv.org/abs/2601.21335v1)** | 2026-01-29 |
| **3** | **[Causal Discovery for Explainable AI: A Dual-Encoding Approach](https://arxiv.org/abs/2601.21221v1)** | 2026-01-29 |
| **4** | **[AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection](https://arxiv.org/abs/2601.21171v1)** | 2026-01-29 |
| **5** | **[Causal Inference in Biomedical Imaging via Functional Linear Structural Equation Models](https://arxiv.org/abs/2601.20610v1)** | 2026-01-28 |
| **6** | **[Exact Graph Learning via Integer Programming](https://arxiv.org/abs/2601.20589v1)** | 2026-01-28 |
| **7** | **[MuVaC: AVariational Causal Framework for Multimodal Sarcasm Understanding in Dialogues](https://arxiv.org/abs/2601.20451v1)** | 2026-01-28 |
| **8** | **[A generative machine learning model for designing metal hydrides applied to hydrogen storage](https://arxiv.org/abs/2601.20892v1)** | 2026-01-28 |
| **9** | **[Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control](https://arxiv.org/abs/2601.20090v2)** | 2026-01-27 |
| **10** | **[Decoupling and randomization for double-indexed permutation statistics](https://arxiv.org/abs/2601.20018v1)** | 2026-01-27 |
| **11** | **[GraIP: A Benchmarking Framework For Neural Graph Inverse Problems](https://arxiv.org/abs/2601.18917v1)** | 2026-01-26 |
| **12** | **[Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients](https://arxiv.org/abs/2601.18189v1)** | 2026-01-26 |
| **13** | **[LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatment](https://arxiv.org/abs/2601.18118v1)** | 2026-01-26 |
| **14** | **[Ordering-based Causal Discovery via Generalized Score Matching](https://arxiv.org/abs/2601.16249v2)** | 2026-01-22 |
| **15** | **[From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models](https://arxiv.org/abs/2601.15533v1)** | 2026-01-21 |
| **16** | **[Causal Regime Detection in Energy Markets With Augmented Time Series Structural Causal Models](https://arxiv.org/abs/2511.04361v2)** | 2025-11-06 |
| **17** | **[Causal Graph Neural Networks for Healthcare](https://arxiv.org/abs/2511.02531v4)** | 2025-11-04 |
| **18** | **[DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning](https://arxiv.org/abs/2509.20912v2)** | 2025-09-25 |
| **19** | **[Networks of Causal Abstractions: A Sheaf-theoretic Framework](https://arxiv.org/abs/2509.25236v2)** | 2025-09-25 |
| **20** | **[Causality-guided Prompt Learning for Vision-language Models via Visual Granulation](https://arxiv.org/abs/2509.03803v4)** | 2025-09-04 |
| **21** | **[Differentiable Cyclic Causal Discovery Under Unmeasured Confounders](https://arxiv.org/abs/2508.08450v3)** | 2025-08-11 |
| **22** | **[A Bayesian approach to the survivor average causal effect in cluster-randomized crossover trials](https://arxiv.org/abs/2505.21447v2)** | 2025-05-27 |
| **23** | **[Causal Meta-Analysis: Rethinking the Foundations of Evidence-Based Medicine](https://arxiv.org/abs/2505.20168v2)** | 2025-05-26 |
| **24** | **[PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation](https://arxiv.org/abs/2504.01509v2)** | 2025-04-02 |
### 6. video super resolution
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[OSDEnhancer: Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion](https://arxiv.org/abs/2601.20308v1)** | 2026-01-28 |
| **2** | **[S3-CLIP: Video Super Resolution for Person-ReID](https://arxiv.org/abs/2601.08807v1)** | 2026-01-13 |
| **3** | **[HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution](https://arxiv.org/abs/2601.04682v1)** | 2026-01-08 |
| **4** | **[Seeing the Unseen: Zooming in the Dark with Event Cameras](https://arxiv.org/abs/2601.02206v1)** | 2026-01-05 |
| **5** | **[Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion](https://arxiv.org/abs/2512.23709v1)** | 2025-12-29 |
| **6** | **[FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring](https://arxiv.org/abs/2512.04390v1)** | 2025-12-04 |
| **7** | **[HunyuanVideo 1.5 Technical Report](https://arxiv.org/abs/2511.18870v2)** | 2025-11-24 |
| **8** | **[STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution](https://arxiv.org/abs/2511.18786v1)** | 2025-11-24 |
### 7. knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts](https://arxiv.org/abs/2601.22156v1)** | 2026-01-29 |
| **2** | **[SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control](https://arxiv.org/abs/2601.22044v1)** | 2026-01-29 |
| **3** | **[Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning](https://arxiv.org/abs/2601.21978v1)** | 2026-01-29 |
| **4** | **[OVD: On-policy Verbal Distillation](https://arxiv.org/abs/2601.21968v1)** | 2026-01-29 |
| **5** | **[Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models](https://arxiv.org/abs/2601.21851v1)** | 2026-01-29 |
| **6** | **[The Double-Edged Sword of Knowledge Transfer: Diagnosing and Curing Fairness Pathologies in Cross-Domain Recommendation](https://arxiv.org/abs/2601.21805v1)** | 2026-01-29 |
| **7** | **[CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answering](https://arxiv.org/abs/2601.21733v1)** | 2026-01-29 |
| **8** | **[Computational investigation of single herbal drugs in Ayurveda for diabetes and obesity using knowledge graph and network pharmacology](https://arxiv.org/abs/2601.21643v1)** | 2026-01-29 |
| **9** | **[PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization](https://arxiv.org/abs/2601.21617v1)** | 2026-01-29 |
| **10** | **[Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance](https://arxiv.org/abs/2601.21611v1)** | 2026-01-29 |
| **11** | **[Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning](https://arxiv.org/abs/2601.21345v1)** | 2026-01-29 |
| **12** | **[Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning](https://arxiv.org/abs/2601.21341v1)** | 2026-01-29 |
| **13** | **[Grounding and Enhancing Informativeness and Utility in Dataset Distillation](https://arxiv.org/abs/2601.21296v1)** | 2026-01-29 |
| **14** | **[From Scattered to Structured: A Vision for Automating Architectural Knowledge Management](https://arxiv.org/abs/2601.19548v1)** | 2026-01-27 |
| **15** | **[DREAMSTATE: Diffusing States and Parameters for Recurrent Large Language Models](https://arxiv.org/abs/2601.19221v1)** | 2026-01-27 |
| **16** | **[Cutting the Gordian Knot: Detecting Malicious PyPI Packages via a Knowledge-Mining Framework](https://arxiv.org/abs/2601.16463v2)** | 2026-01-23 |
| **17** | **[Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation](https://arxiv.org/abs/2601.16462v1)** | 2026-01-23 |
| **18** | **[LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models](https://arxiv.org/abs/2601.14674v1)** | 2026-01-21 |
| **19** | **[Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems](https://arxiv.org/abs/2601.13887v2)** | 2026-01-20 |
| **20** | **[Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams](https://arxiv.org/abs/2601.13299v1)** | 2026-01-19 |
| **21** | **[UniHash: Unifying Pointwise and Pairwise Hashing Paradigms](https://arxiv.org/abs/2601.09828v3)** | 2026-01-14 |
| **22** | **[Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method](https://arxiv.org/abs/2601.09238v1)** | 2026-01-14 |
| **23** | **[EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers](https://arxiv.org/abs/2601.08499v2)** | 2026-01-13 |
| **24** | **[Computing Supported Models via Transformation to Stable Models](https://arxiv.org/abs/2512.05437v2)** | 2025-12-05 |
| **25** | **[Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models](https://arxiv.org/abs/2512.00590v2)** | 2025-11-29 |
| **26** | **[Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture](https://arxiv.org/abs/2511.07110v3)** | 2025-11-10 |
| **27** | **[The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation](https://arxiv.org/abs/2511.05903v2)** | 2025-11-08 |
| **28** | **[VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree](https://arxiv.org/abs/2510.22693v3)** | 2025-10-26 |
| **29** | **[RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation](https://arxiv.org/abs/2509.23480v2)** | 2025-09-27 |
| **30** | **[SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation](https://arxiv.org/abs/2509.15703v2)** | 2025-09-19 |
| **31** | **[Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking](https://arxiv.org/abs/2508.07286v3)** | 2025-08-10 |
| **32** | **[X-SAM: From Segment Anything to Any Segmentation](https://arxiv.org/abs/2508.04655v2)** | 2025-08-06 |
| **33** | **[GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning](https://arxiv.org/abs/2507.23581v2)** | 2025-07-31 |
| **34** | **[Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation](https://arxiv.org/abs/2506.03229v3)** | 2025-06-03 |
| **35** | **[From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization](https://arxiv.org/abs/2503.07520v4)** | 2025-03-10 |
| **36** | **[RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation](https://arxiv.org/abs/2502.10996v3)** | 2025-02-16 |
| **37** | **[A Concept-Centric Approach to Multi-Modality Learning](https://arxiv.org/abs/2412.13847v2)** | 2024-12-18 |
| **38** | **[One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs](https://arxiv.org/abs/2409.13959v3)** | 2024-09-21 |
### 8. combinatorial game theory/xiangqi/chinese chess
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Additive sink subtraction](https://arxiv.org/abs/2601.18715v1)** | 2026-01-26 |
| **2** | **[Variants of Wythoff game with terminal positions or blocking maneuvers](https://arxiv.org/abs/2512.11601v1)** | 2025-12-12 |
| **3** | **[Impartial Games with Activeness](https://arxiv.org/abs/2511.20984v1)** | 2025-11-26 |
| **4** | **[$\mathcal{L}\mathcal{R}$-Ending partisan rulesets](https://arxiv.org/abs/2511.14468v1)** | 2025-11-18 |
| **5** | **[Various Diamond Properties in Combinatorial Game Theory](https://arxiv.org/abs/2509.21744v2)** | 2025-09-26 |
| **6** | **[Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning](https://arxiv.org/abs/2507.12215v2)** | 2025-07-16 |
| **7** | **[On 3-terminal positions in Hex](https://arxiv.org/abs/2507.08247v2)** | 2025-07-11 |
| **8** | **[A number game reconciliation](https://arxiv.org/abs/2507.04717v1)** | 2025-07-07 |
| **9** | **[Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search](https://arxiv.org/abs/2506.15880v1)** | 2025-06-18 |
| **10** | **[Computational and Algebraic Structure of Board Games](https://arxiv.org/abs/2503.01850v1)** | 2025-02-18 |
| **11** | **[RemoteChess: Enhancing Older Adults' Social Connectedness via Designing a Virtual Reality Chinese Chess (Xiangqi) Community](https://arxiv.org/abs/2502.11627v1)** | 2025-02-17 |
| **12** | **[Complete Implementation of WXF Chinese Chess Rules](https://arxiv.org/abs/2412.17334v1)** | 2024-12-23 |
| **13** | **[Mastering Chinese Chess AI (Xiangqi) Without Search](https://arxiv.org/abs/2410.04865v1)** | 2024-10-07 |
| **14** | **[XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi](https://arxiv.org/abs/2407.04678v1)** | 2024-07-05 |
| **15** | **[Shogi and Frieze group](https://arxiv.org/abs/2401.08591v2)** | 2023-11-15 |
| **16** | **[JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games](https://arxiv.org/abs/2308.04719v1)** | 2023-08-09 |
| **17** | **[Niel's Chess -- Rules for Xiangqi](https://arxiv.org/abs/2311.12181v2)** | 2023-06-27 |
| **18** | **[On the complexity of Dark Chinese Chess](https://arxiv.org/abs/2112.02989v1)** | 2021-12-06 |
| **19** | **[Cumulative Games: Who is the current player?](https://arxiv.org/abs/2005.06326v2)** | 2020-05-13 |
### 9. code llm
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Multi-task Code LLMs: Data Mix or Model Merge?](https://arxiv.org/abs/2601.21115v1)** | 2026-01-28 |
| **2** | **[Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study](https://arxiv.org/abs/2601.20112v1)** | 2026-01-27 |
| **3** | **[AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://arxiv.org/abs/2601.19697v1)** | 2026-01-27 |
| **4** | **[Evaluating and Achieving Controllable Code Completion in Code LLM](https://arxiv.org/abs/2601.15879v1)** | 2026-01-22 |
| **5** | **[Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility](https://arxiv.org/abs/2601.13398v1)** | 2026-01-19 |
| **6** | **[Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs](https://arxiv.org/abs/2601.10496v1)** | 2026-01-15 |
| **7** | **[X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests](https://arxiv.org/abs/2601.06953v1)** | 2026-01-11 |
| **8** | **[Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://arxiv.org/abs/2404.00971v3)** | 2024-04-01 |
### 10. speech recognition
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WER](https://arxiv.org/abs/2601.21347v1)** | 2026-01-29 |
| **2** | **[Qwen3-ASR Technical Report](https://arxiv.org/abs/2601.21337v1)** | 2026-01-29 |
| **3** | **[asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation](https://arxiv.org/abs/2601.20992v1)** | 2026-01-28 |
| **4** | **[Text-only adaptation in LLM-based ASR through text denoising](https://arxiv.org/abs/2601.20900v1)** | 2026-01-28 |
| **5** | **[Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection](https://arxiv.org/abs/2601.20898v1)** | 2026-01-28 |
| **6** | **[A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models](https://arxiv.org/abs/2601.20896v1)** | 2026-01-28 |
| **7** | **[Unheard in the Digital Age: Rethinking AI Bias and Speech Diversity](https://arxiv.org/abs/2601.18641v2)** | 2026-01-26 |
| **8** | **[CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition](https://arxiv.org/abs/2502.01777v3)** | 2025-02-03 |
### 11. zero shot tracking/few shot tracking/pose tracking/pose estimation
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture](https://arxiv.org/abs/2601.19580v1)** | 2026-01-27 |
| **2** | **[On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training](https://arxiv.org/abs/2601.18929v1)** | 2026-01-26 |
| **3** | **[ME-WARD: A multimodal ergonomic analysis tool for musculoskeletal risk assessment from inertial and video data in working plac](https://arxiv.org/abs/2601.17571v1)** | 2026-01-24 |
| **4** | **[GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss](https://arxiv.org/abs/2601.16885v2)** | 2026-01-23 |
| **5** | **[DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views](https://arxiv.org/abs/2601.15516v2)** | 2026-01-21 |
| **6** | **[Diffusion-based Inverse Model of a Distributed Tactile Sensor for Object Pose Estimation](https://arxiv.org/abs/2601.13250v1)** | 2026-01-19 |
| **7** | **[Dual-quaternion learning control for autonomous vehicle trajectory tracking with safety guarantees](https://arxiv.org/abs/2601.03097v1)** | 2026-01-06 |
| **8** | **[UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots](https://arxiv.org/abs/2512.24321v1)** | 2025-12-30 |
| **9** | **[KV-Tracker: Real-Time Pose Tracking with Transformers](https://arxiv.org/abs/2512.22581v1)** | 2025-12-27 |
| **10** | **[ParaMaP: Parallel Mapping and Collision-free Motion Planning for Reactive Robot Manipulation](https://arxiv.org/abs/2512.22575v1)** | 2025-12-27 |
| **11** | **[Tracking by Predicting 3-D Gaussians Over Time](https://arxiv.org/abs/2512.22489v2)** | 2025-12-27 |
| **12** | **[Optical Flow-Guided 6DoF Object Pose Tracking with an Event Camera](https://arxiv.org/abs/2512.21053v1)** | 2025-12-24 |
| **13** | **[Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence](https://arxiv.org/abs/2512.04619v1)** | 2025-12-04 |
| **14** | **[RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis](https://arxiv.org/abs/2511.17045v3)** | 2025-11-21 |
| **15** | **[PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting](https://arxiv.org/abs/2510.18714v2)** | 2025-10-21 |
| **16** | **[When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos](https://arxiv.org/abs/2510.02100v1)** | 2025-10-02 |
| **17** | **[FERA: A Pose-Based Semantic Pipeline for Automated Foil Fencing Refereeing](https://arxiv.org/abs/2509.18527v4)** | 2025-09-23 |
| **18** | **[Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation for Zero-shot Generalization](https://arxiv.org/abs/2509.11772v1)** | 2025-09-15 |
| **19** | **[PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation](https://arxiv.org/abs/2508.02806v2)** | 2025-08-04 |
| **20** | **[From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation](https://arxiv.org/abs/2507.12884v2)** | 2025-07-17 |
| **21** | **[Matching Anything by Segmenting Anything](https://arxiv.org/abs/2406.04221v1)** | 2024-06-06 |
| **22** | **[Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection](https://arxiv.org/abs/2308.04789v2)** | 2023-08-09 |
| **23** | **[Fusion of Visual-Inertial Odometry with LiDAR Relative Localization for Cooperative Guidance of a Micro-Scale Aerial Vehicle](https://arxiv.org/abs/2306.17544v3)** | 2023-06-30 |
| **24** | **[APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://arxiv.org/abs/2305.17382v3)** | 2023-05-27 |
| **25** | **[Unifying Tracking and Image-Video Object Detection](https://arxiv.org/abs/2211.11077v2)** | 2022-11-20 |
| **26** | **[Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizations](https://arxiv.org/abs/2206.10695v1)** | 2022-06-21 |
| **27** | **[The Multi-speaker Multi-style Voice Cloning Challenge 2021](https://arxiv.org/abs/2104.01818v1)** | 2021-04-05 |
### 12. text to 3d/image to 3d/text to texture
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming](https://arxiv.org/abs/2601.19433v1)** | 2026-01-27 |
| **2** | **[TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment](https://arxiv.org/abs/2601.19247v1)** | 2026-01-27 |
| **3** | **[Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting](https://arxiv.org/abs/2601.18633v1)** | 2026-01-26 |
| **4** | **[Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations](https://arxiv.org/abs/2601.13371v1)** | 2026-01-19 |
| **5** | **[KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction](https://arxiv.org/abs/2601.12736v1)** | 2026-01-19 |
| **6** | **[Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models](https://arxiv.org/abs/2601.12234v1)** | 2026-01-18 |
| **7** | **[PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation](https://arxiv.org/abs/2512.24200v1)** | 2025-12-30 |
| **8** | **[Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection](https://arxiv.org/abs/2512.12884v2)** | 2025-12-14 |
| **9** | **[Geodiffussr: Generative Terrain Texturing with Elevation Fidelity](https://arxiv.org/abs/2511.23029v1)** | 2025-11-28 |
| **10** | **[Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding](https://arxiv.org/abs/2510.09110v4)** | 2025-10-10 |
| **11** | **[CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion](https://arxiv.org/abs/2508.11603v2)** | 2025-08-15 |
| **12** | **[LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding Tasks](https://arxiv.org/abs/2507.20174v2)** | 2025-07-27 |
| **13** | **[TexTailor: Customized Text-aligned Texturing via Effective Resampling](https://arxiv.org/abs/2506.10612v1)** | 2025-06-12 |
| **14** | **[CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx](https://arxiv.org/abs/2506.04931v2)** | 2025-06-05 |
| **15** | **[CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading](https://arxiv.org/abs/2504.06856v2)** | 2025-04-09 |
| **16** | **[MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection](https://arxiv.org/abs/2504.02762v1)** | 2025-04-03 |
| **17** | **[Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data](https://arxiv.org/abs/2503.21694v1)** | 2025-03-27 |
| **18** | **[A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments](https://arxiv.org/abs/2503.12052v3)** | 2025-03-15 |
| **19** | **[ProcTex: Consistent and Interactive Text-to-texture Synthesis for Part-based Procedural Models](https://arxiv.org/abs/2501.17895v2)** | 2025-01-28 |
| **20** | **[PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion](https://arxiv.org/abs/2412.04827v3)** | 2024-12-06 |
| **21** | **[GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data](https://arxiv.org/abs/2411.18624v3)** | 2024-11-27 |
| **22** | **[TexPro: Text-guided PBR Texturing with Procedural Material Modeling](https://arxiv.org/abs/2410.15891v2)** | 2024-10-21 |
| **23** | **[Reconstructing Hand-Held Objects in 3D from Images and Videos](https://arxiv.org/abs/2404.06507v4)** | 2024-04-09 |
| **24** | **[Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video](https://arxiv.org/abs/2401.08742v5)** | 2024-01-16 |
### 13. automated theorem proving/interactive theorem proving/formal verification
| **序号** | **标题** | **日期** |
| --- | --- | --- |
| **1** | **[SecIC3: Customizing IC3 for Hardware Security Verification](https://arxiv.org/abs/2601.21353v1)** | 2026-01-29 |
| **2** | **[Position: Certifiable State Integrity in Cyber-Physical Systems -- Why Modular Sovereignty Solves the Plasticity-Stability Paradox](https://arxiv.org/abs/2601.21249v1)** | 2026-01-29 |
| **3** | **[VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning](https://arxiv.org/abs/2601.20055v1)** | 2026-01-27 |
| **4** | **[How to Verify a Turing Machine with Dafny](https://arxiv.org/abs/2601.15230v1)** | 2026-01-21 |
| **5** | **[Quantum automated theorem proving](https://arxiv.org/abs/2601.07953v1)** | 2026-01-12 |
| **6** | **[GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning](https://arxiv.org/abs/2601.06795v3)** | 2026-01-11 |
| **7** | **[Automated Theorem Proving for Prolog Verification](https://arxiv.org/abs/2601.03849v1)** | 2026-01-07 |
| **8** | **[Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving](https://arxiv.org/abs/2512.23511v1)** | 2025-12-29 |
| **9** | **[Symbolic Specification and Reasoning for Quantum Data and Operations](https://arxiv.org/abs/2512.22383v1)** | 2025-12-26 |
| **10** | **[MSC-180: A Benchmark for Automated Formal Theorem Proving from Mathematical Subject Classification](https://arxiv.org/abs/2512.18256v1)** | 2025-12-20 |
| **11** | **[Advancing Mathematical Research via Human-AI Interactive Theorem Proving](https://arxiv.org/abs/2512.09443v2)** | 2025-12-10 |
| **12** | **[DUET: Agentic Design Understanding via Experimentation and Testing](https://arxiv.org/abs/2512.06247v2)** | 2025-12-06 |
| **13** | **[Formal Verification of Noisy Quantum Reinforcement Learning Policies](https://arxiv.org/abs/2512.01502v2)** | 2025-12-01 |
| **14** | **[Proof Strategy Extraction from LLMs for Enhancing Symbolic Provers](https://arxiv.org/abs/2510.10131v1)** | 2025-10-11 |
| **15** | **[L-Mosaics and Bounded Join-Semilattices in Isabelle/HOL](https://arxiv.org/abs/2509.19854v1)** | 2025-09-24 |
| **16** | **[An ACL2s Interface to Z3](https://arxiv.org/abs/2507.19014v1)** | 2025-07-25 |
| **17** | **[Interpolation with Automated First-Order Reasoning](https://arxiv.org/abs/2507.01577v2)** | 2025-07-02 |
| **18** | **[Quantifying Bounded Rationality: Formal Verification of Simon's Satisficing Through Flexible Stochastic Dominance](https://arxiv.org/abs/2507.07052v1)** | 2025-07-02 |
| **19** | **[Software is infrastructure: failures, successes, costs, and the case for formal verification](https://arxiv.org/abs/2506.13821v4)** | 2025-06-15 |
| **20** | **[Automated Discovery of Tactic Libraries for Interactive Theorem Proving](https://arxiv.org/abs/2503.24036v2)** | 2025-03-31 |
| **21** | **[LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction](https://arxiv.org/abs/2502.17925v3)** | 2025-02-25 |


Provide feedback

Saved searches

Use saved searches to filter your results more quickly

每月论文更新 - 2026年02月02日 #31

最后更新：2026-02-02 00:05

论文汇总（202篇）

1. efficient RL

2. partial observable markov decision process/pomdp

3. sparse reward reinforcement learning

4. casual RL/counterfactual RL/casual reinforcement learning

5. causal inference/causal discovery/counterfactual reasoning

6. video super resolution

7. knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding

8. combinatorial game theory/xiangqi/chinese chess

9. code llm

10. speech recognition

11. zero shot tracking/few shot tracking/pose tracking/pose estimation

12. text to 3d/image to 3d/text to texture

13. automated theorem proving/interactive theorem proving/formal verification

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

序号	标题	日期
1	Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents	2026-01-29
2	Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes	2026-01-26
3	Efficient Self-Learning and Model Versioning for AI-native O-RAN Edge	2026-01-24
4	Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models	2026-01-08
5	Evaluating Parameter Efficient Methods for RLVR	2025-12-29
6	$π_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models	2025-10-29
7	RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation	2025-09-19
8	Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation	2025-02-14

序号	标题	日期
1	Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function	2026-01-28
2	Structural Monotonicity in Transmission Scheduling for Remote State Estimation with Hidden Channel Mode	2026-01-27
3	Toward Learning POMDPs Beyond Full-Rank Actions and State Observability	2026-01-26
4	Neural Value Iteration	2025-11-11
5	The Landscape of Agentic Reinforcement Learning for LLMs: A Survey	2025-09-02
6	Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents	2025-05-16
7	Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information	2023-06-14

序号	标题	日期
1	What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?	2025-09-04
2	LLM-Driven Intrinsic Motivation for Sparse Reward Reinforcement Learning	2025-08-25
3	SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning	2025-06-01
4	DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning	2025-05-26
5	STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs	2025-05-21
6	Contextual Similarity Distillation: Ensemble Uncertainties with a Single Model	2025-03-14
7	Hedging with Sparse Reward Reinforcement Learning	2025-03-06
8	Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations	2024-12-02

序号	标题	日期
1	Should I Trust You? Detecting Deception in Negotiations using Counterfactual RL	2025-02-18
2	Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation	2020-12-16

序号	标题	日期
1	ECSEL: Explainable Classification via Signomial Equation Learning	2026-01-29
2	Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation	2026-01-29
3	Causal Discovery for Explainable AI: A Dual-Encoding Approach	2026-01-29
4	AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection	2026-01-29
5	Causal Inference in Biomedical Imaging via Functional Linear Structural Equation Models	2026-01-28
6	Exact Graph Learning via Integer Programming	2026-01-28
7	MuVaC: AVariational Causal Framework for Multimodal Sarcasm Understanding in Dialogues	2026-01-28
8	A generative machine learning model for designing metal hydrides applied to hydrogen storage	2026-01-28
9	Should I Have Expressed a Different Intent? Counterfactual Generation for LLM-Based Autonomous Control	2026-01-27
10	Decoupling and randomization for double-indexed permutation statistics	2026-01-27
11	GraIP: A Benchmarking Framework For Neural Graph Inverse Problems	2026-01-26
12	Smooth, Sparse, and Stable: Finite-Time Exact Skeleton Recovery via Smoothed Proximal Gradients	2026-01-26
13	LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatment	2026-01-26
14	Ordering-based Causal Discovery via Generalized Score Matching	2026-01-22
15	From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models	2026-01-21
16	Causal Regime Detection in Energy Markets With Augmented Time Series Structural Causal Models	2025-11-06
17	Causal Graph Neural Networks for Healthcare	2025-11-04
18	DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning	2025-09-25
19	Networks of Causal Abstractions: A Sheaf-theoretic Framework	2025-09-25
20	Causality-guided Prompt Learning for Vision-language Models via Visual Granulation	2025-09-04
21	Differentiable Cyclic Causal Discovery Under Unmeasured Confounders	2025-08-11
22	A Bayesian approach to the survivor average causal effect in cluster-randomized crossover trials	2025-05-27
23	Causal Meta-Analysis: Rethinking the Foundations of Evidence-Based Medicine	2025-05-26
24	PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation	2025-04-02

序号	标题	日期
1	OSDEnhancer: Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion	2026-01-28
2	S3-CLIP: Video Super Resolution for Person-ReID	2026-01-13
3	HATIR: Heat-Aware Diffusion for Turbulent Infrared Video Super-Resolution	2026-01-08
4	Seeing the Unseen: Zooming in the Dark with Event Cameras	2026-01-05
5	Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion	2025-12-29
6	FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring	2025-12-04
7	HunyuanVideo 1.5 Technical Report	2025-11-24
8	STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution	2025-11-24

序号	标题	日期
1	Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts	2026-01-29
2	SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control	2026-01-29
3	Bridging Graph Structure and Knowledge-Guided Editing for Interpretable Temporal Knowledge Graph Reasoning	2026-01-29
4	OVD: On-policy Verbal Distillation	2026-01-29
5	Visual Disentangled Diffusion Autoencoders: Scalable Counterfactual Generation for Foundation Models	2026-01-29
6	The Double-Edged Sword of Knowledge Transfer: Diagnosing and Curing Fairness Pathologies in Cross-Domain Recommendation	2026-01-29
7	CE-GOCD: Central Entity-Guided Graph Optimization for Community Detection to Augment LLM Scientific Question Answering	2026-01-29
8	Computational investigation of single herbal drugs in Ayurveda for diabetes and obesity using knowledge graph and network pharmacology	2026-01-29
9	PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization	2026-01-29
10	Thinking Broad, Acting Fast: Latent Reasoning Distillation from Multi-Perspective Chain-of-Thought for E-Commerce Relevance	2026-01-29
11	Semantic-Guided Dynamic Sparsification for Pre-Trained Model-based Class-Incremental Learning	2026-01-29
12	Dynamical Adapter Fusion: Constructing A Global Adapter for Pre-Trained Model-based Class-Incremental Learning	2026-01-29
13	Grounding and Enhancing Informativeness and Utility in Dataset Distillation	2026-01-29
14	From Scattered to Structured: A Vision for Automating Architectural Knowledge Management	2026-01-27
15	DREAMSTATE: Diffusing States and Parameters for Recurrent Large Language Models	2026-01-27
16	Cutting the Gordian Knot: Detecting Malicious PyPI Packages via a Knowledge-Mining Framework	2026-01-23
17	Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation	2026-01-23
18	LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models	2026-01-21
19	Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems	2026-01-20
20	Enginuity: Building an Open Multi-Domain Dataset of Complex Engineering Diagrams	2026-01-19
21	UniHash: Unifying Pointwise and Pairwise Hashing Paradigms	2026-01-14
22	Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method	2026-01-14
23	EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformers	2026-01-13
24	Computing Supported Models via Transformation to Stable Models	2025-12-05
25	Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models	2025-11-29
26	Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture	2025-11-10
27	The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation	2025-11-08
28	VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree	2025-10-26
29	RestoRect: Degraded Image Restoration via Latent Rectified Flow & Feature Distillation	2025-09-27
30	SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation	2025-09-19
31	Arce: Augmented Roberta with Contextualized Elucidations for Ner in Automated Rule Checking	2025-08-10
32	X-SAM: From Segment Anything to Any Segmentation	2025-08-06
33	GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning	2025-07-31
34	Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptation	2025-06-03
35	From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization	2025-03-10
36	RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation	2025-02-16
37	A Concept-Centric Approach to Multi-Modality Learning	2024-12-18
38	One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs	2024-09-21

序号	标题	日期
1	Additive sink subtraction	2026-01-26
2	Variants of Wythoff game with terminal positions or blocking maneuvers	2025-12-12
3	Impartial Games with Activeness	2025-11-26
4	$\mathcal{L}\mathcal{R}$-Ending partisan rulesets	2025-11-18
5	Various Diamond Properties in Combinatorial Game Theory	2025-09-26
6	Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning	2025-07-16
7	On 3-terminal positions in Hex	2025-07-11
8	A number game reconciliation	2025-07-07
9	Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search	2025-06-18
10	Computational and Algebraic Structure of Board Games	2025-02-18
11	RemoteChess: Enhancing Older Adults' Social Connectedness via Designing a Virtual Reality Chinese Chess (Xiangqi) Community	2025-02-17
12	Complete Implementation of WXF Chinese Chess Rules	2024-12-23
13	Mastering Chinese Chess AI (Xiangqi) Without Search	2024-10-07
14	XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi	2024-07-05
15	Shogi and Frieze group	2023-11-15
16	JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games	2023-08-09
17	Niel's Chess -- Rules for Xiangqi	2023-06-27
18	On the complexity of Dark Chinese Chess	2021-12-06
19	Cumulative Games: Who is the current player?	2020-05-13

序号	标题	日期
1	Multi-task Code LLMs: Data Mix or Model Merge?	2026-01-28
2	Usage, Effects and Requirements for AI Coding Assistants in the Enterprise: An Empirical Study	2026-01-27
3	AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion	2026-01-27
4	Evaluating and Achieving Controllable Code Completion in Code LLM	2026-01-22
5	Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility	2026-01-19
6	Model See, Model Do? Exposure-Aware Evaluation of Bug-vs-Fix Preference in Code LLMs	2026-01-15
7	X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests	2026-01-11
8	Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code	2024-04-01

序号	标题	日期
1	Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WER	2026-01-29
2	Qwen3-ASR Technical Report	2026-01-29
3	asr_eval: Algorithms and tools for multi-reference and streaming speech recognition evaluation	2026-01-28
4	Text-only adaptation in LLM-based ASR through text denoising	2026-01-28
5	Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection	2026-01-28
6	A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models	2026-01-28
7	Unheard in the Digital Age: Rethinking AI Bias and Speech Diversity	2026-01-26
8	CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition	2025-02-03

序号	标题	日期
1	QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture	2026-01-27
2	On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training	2026-01-26
3	ME-WARD: A multimodal ergonomic analysis tool for musculoskeletal risk assessment from inertial and video data in working plac	2026-01-24
4	GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Loss	2026-01-23
5	DeltaDorsal: Enhancing Hand Pose Estimation with Dorsal Features in Egocentric Views	2026-01-21
6	Diffusion-based Inverse Model of a Distributed Tactile Sensor for Object Pose Estimation	2026-01-19
7	Dual-quaternion learning control for autonomous vehicle trajectory tracking with safety guarantees	2026-01-06
8	UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots	2025-12-30
9	KV-Tracker: Real-Time Pose Tracking with Transformers	2025-12-27
10	ParaMaP: Parallel Mapping and Collision-free Motion Planning for Reactive Robot Manipulation	2025-12-27
11	Tracking by Predicting 3-D Gaussians Over Time	2025-12-27
12	Optical Flow-Guided 6DoF Object Pose Tracking with an Event Camera	2025-12-24
13	Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence	2025-12-04
14	RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis	2025-11-21
15	PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting	2025-10-21
16	When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos	2025-10-02
17	FERA: A Pose-Based Semantic Pipeline for Automated Foil Fencing Refereeing	2025-09-23
18	Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation for Zero-shot Generalization	2025-09-15
19	PyCAT4: A Hierarchical Vision Transformer-based Framework for 3D Human Pose Estimation	2025-08-04
20	From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation	2025-07-17
21	Matching Anything by Segmenting Anything	2024-06-06
22	Multi-Scale Memory Comparison for Zero-/Few-Shot Anomaly Detection	2023-08-09
23	Fusion of Visual-Inertial Odometry with LiDAR Relative Localization for Cooperative Guidance of a Micro-Scale Aerial Vehicle	2023-06-30
24	APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD	2023-05-27
25	Unifying Tracking and Image-Video Object Detection	2022-11-20
26	Exploring the Effectiveness of Self-supervised Learning and Classifier Chains in Emotion Recognition of Nonverbal Vocalizations	2022-06-21
27	The Multi-speaker Multi-style Voice Cloning Challenge 2021	2021-04-05

序号	标题	日期
1	RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming	2026-01-27
2	TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment	2026-01-27
3	Splat-Portrait: Generalizing Talking Heads with Gaussian Splatting	2026-01-26
4	Spherical Geometry Diffusion: Generating High-quality 3D Face Geometry via Sphere-anchored Representations	2026-01-19
5	KaoLRM: Repurposing Pre-trained Large Reconstruction Models for Parametric 3D Face Reconstruction	2026-01-19
6	Proc3D: Procedural 3D Generation and Parametric Editing of 3D Shapes with Large Language Models	2026-01-18
7	PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation	2025-12-30
8	Cross-Level Sensor Fusion with Object Lists via Transformer for 3D Object Detection	2025-12-14
9	Geodiffussr: Generative Terrain Texturing with Elevation Fidelity	2025-11-28
10	Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding	2025-10-10
11	CoreEditor: Consistent 3D Editing via Correspondence-constrained Diffusion	2025-08-15
12	LRR-Bench: Left, Right or Rotate? Vision-Language models Still Struggle With Spatial Understanding Tasks	2025-07-27
13	TexTailor: Customized Text-aligned Texturing via Effective Resampling	2025-06-12
14	CzechLynx: A Dataset for Individual Identification and Pose Estimation of the Eurasian Lynx	2025-06-05
15	CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading	2025-04-09
16	MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection	2025-04-03
17	Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data	2025-03-27
18	A Text-to-3D Framework for Joint Generation of CG-Ready Humans and Compatible Garments	2025-03-15
19	ProcTex: Consistent and Interactive Text-to-texture Synthesis for Part-based Procedural Models	2025-01-28
20	PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion	2024-12-06
21	GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data	2024-11-27
22	TexPro: Text-guided PBR Texturing with Procedural Material Modeling	2024-10-21
23	Reconstructing Hand-Held Objects in 3D from Images and Videos	2024-04-09
24	Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video	2024-01-16

序号	标题	日期
1	SecIC3: Customizing IC3 for Hardware Security Verification	2026-01-29
2	Position: Certifiable State Integrity in Cyber-Physical Systems -- Why Modular Sovereignty Solves the Plasticity-Stability Paradox	2026-01-29
3	VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning	2026-01-27
4	How to Verify a Turing Machine with Dafny	2026-01-21
5	Quantum automated theorem proving	2026-01-12
6	GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning	2026-01-11
7	Automated Theorem Proving for Prolog Verification	2026-01-07
8	Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving	2025-12-29
9	Symbolic Specification and Reasoning for Quantum Data and Operations	2025-12-26
10	MSC-180: A Benchmark for Automated Formal Theorem Proving from Mathematical Subject Classification	2025-12-20
11	Advancing Mathematical Research via Human-AI Interactive Theorem Proving	2025-12-10
12	DUET: Agentic Design Understanding via Experimentation and Testing	2025-12-06
13	Formal Verification of Noisy Quantum Reinforcement Learning Policies	2025-12-01
14	Proof Strategy Extraction from LLMs for Enhancing Symbolic Provers	2025-10-11
15	L-Mosaics and Bounded Join-Semilattices in Isabelle/HOL	2025-09-24
16	An ACL2s Interface to Z3	2025-07-25
17	Interpolation with Automated First-Order Reasoning	2025-07-02
18	Quantifying Bounded Rationality: Formal Verification of Simon's Satisficing Through Flexible Stochastic Dominance	2025-07-02
19	Software is infrastructure: failures, successes, costs, and the case for formal verification	2025-06-15
20	Automated Discovery of Tactic Libraries for Interactive Theorem Proving	2025-03-31
21	LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction	2025-02-25

每月论文更新 - 2026年02月02日 #31

Description

最后更新：2026-02-02 00:05

论文汇总（202篇）

1. efficient RL

2. partial observable markov decision process/pomdp

3. sparse reward reinforcement learning

4. casual RL/counterfactual RL/casual reinforcement learning

5. causal inference/causal discovery/counterfactual reasoning

6. video super resolution

7. knowledge graph/knowledge distillation/knowledge representation/knowledge transfer/knowledge embedding

8. combinatorial game theory/xiangqi/chinese chess

9. code llm

10. speech recognition

11. zero shot tracking/few shot tracking/pose tracking/pose estimation

12. text to 3d/image to 3d/text to texture

13. automated theorem proving/interactive theorem proving/formal verification

Metadata

Metadata

Assignees

Labels

Projects

Milestone

Relationships

Development

Issue actions