My Blog
A running log of notes across ACM, AI/ML systems, math, and everything in between.
- Helpful Resources 2026-09-03 Lectures, Course URLs, Blogs, Papers, etc. useful for my study.
- Permutation Groups 2026-09-01
- Overview of Convex Optimization 2026-09-01 Convex optimization focuses on a subset of optimization problems, i.e., the objectives and constraints are convex, which means \( f(ax+by) \le a f(x) + b f(y) \).
- Essential Concepts in Quantum Computing 2026-09-01
- Common Metrics 2026-08-31 Metrics are important in evaluating the quality of LLMs. Although nowadays, domain-specific datasets used for evaluating LLMs mainly treat metrics like task accuracy as the only golden standard, there are still general metrics for evaluation.
- Multi-Head Attention and Grouped-Query Attention 2026-08-31
- ZeRO - Zero Redundancy Optimizer 2026-08-31 ZeRO adopts different levels of distributed strategy to remove redundancy in memory, at the cost of more communication. This work also gives birth to FSDP, a widely used distributed training schema.
- GDN - Gated Delta Network 2026-08-29
- N-Gram Embedding 2026-08-29
- Cyclic Group 2026-08-29
- Using
jq2026-08-29 - Solution to Being Unable to Clear Screen 2026-08-28
- A Taste of ExecuTorch 2026-08-26 ExecuTorch is PyTorch’s cutting-edge solution for on-edge model deployment, with limited support for training.
- FedHera 2026-08-26
- Using
adb2026-08-26 ~adb~ is a useful tool for diagnosing Android phones, as well as running C++ programs on Android phones. - SigLIP: Sigmoid Loss for Language Image Pretraining 2026-08-25 The advantage of SigLIP over CLIP is that SigLIP only relies on image-text pairs rather than global pairwise similarity, reducing computational cost from quadric to linear w.r.t. batch size.
- Introduction to Social Psychology 2026-08-25
- Bayesian Asymototics: From Universal Source Coding to General Large-Scale MIMO Capacity 2026-08-19
- Thinking with Visual Primitives 2026-08-17
- Kimi K3 2026-08-14
- Builder 2026-08-14
- Double Buffering 2026-08-14 Double buffering is a pipelining technique in GPU programming. It allocates two staging buffers and alternates between them, so that the data movement for iteration \(k+1\) can overlap computation for iteration \(k\).
- Vectorization 2026-08-14
- Natural Numbers and Integers 2026-08-14
- Iterators 2026-08-14
- Results and Error Handling 2026-08-14
- IO and OS 2026-08-12
- String STL 2026-08-12
- Coroutines in Lua 2026-08-12
- OOP Patterns 2026-08-12
- Tables in Lua 2026-08-12
- Logging Library 2026-08-12 Introduces useful libraries for logging.
- X-Fi: Modality-Invariant Foundation Model 2026-08-11
- Numbers 2026-08-11
- Printed Representation and Read Syntax 2026-08-11
- Lists 2026-08-11 Lists are the most important data type in Emacs Lisp.
- Numbers 2026-08-11 Briefly introduces basic operations related to numbers.
- Strings 2026-08-11
- Crash Course of Lua 2026-08-11
- Sample-Efficient Integration of New Modalities into LLMs 2026-08-10 An interesting work that follows the idea of adopting a projector for modality adaptation, while leveraging a “hypernetwork” for generating LoRA weights from data samples to apply to the projector for adaptation.
- RAID 2026-08-10 Redundant Array of Inexpensive Disks (RAID) is a technology to build a faster, bigger, and more reliable disk system.
- Project Configuration 2026-08-10
- uv - Swiss Army Knife for Python 2026-08-10
- Free Space Management 2026-08-09
- Paging, TLB and Page Tables 2026-08-09 Introduction to paging mechanism.
- 14th Chongqing CPC 2026-08-07
- Use reflector to Select Best pacman Mirrors 2026-08-06
- Grammars for Building Container Images 2026-08-05 ContainerFile and DockerFile are almost the same, the difference between which is simply that the former is the default for
podman, while the latter is the default fordocker. - Ambient Sensing and Intelligence Where AI Meets Physics 2026-08-04
- Main Branches of Buddhism 2026-08-03
- Confidence Interval Estimation 2026-08-03
- Linear Regression 2026-08-03
- Sample Distribution Theory 2026-08-03
- 0622 2026-08-03
- 0611 2026-08-03
- Overview of Integer Programming 2026-08-03
- Branch-and-Bound Method 2026-08-03
- Eigenvalues and Eigenvectors 2026-08-03
- Jordan Form 2026-08-03
- Orthogonality 2026-08-03
- Determinants 2026-08-03
- 3DGS 2026-08-03
- Principles of Network Applications 2026-08-03
- Video Streaming and CDN 2026-08-03
- socket Programming 2026-08-03
- Email 2026-08-03
- DNS 2026-08-03
- HTTP 2026-08-03
- Decorator 2026-08-03
- Facade 2026-08-03
- Flyweight 2026-08-03
- Proxy 2026-08-03
- Visitor 2026-08-03
- Observer 2026-08-03
- State 2026-08-03
- Strategy 2026-08-03
- Template Method 2026-08-03
- Memento 2026-08-03
- Command 2026-08-03
- Iterator 2026-08-03
- Mediator 2026-08-03
- Prototype 2026-08-03
- Singleton 2026-08-03
- Automatic Memory Management 2026-08-03
- Code Generation 2026-08-03
- Dataflow Analysis 2026-08-03
- IR Optimization 2026-08-03
- Register Allocation 2026-08-03
- Runtime Management 2026-08-03
- Semantic Analysis 2026-08-03
- Raft Consensus Protocol 2026-08-03
- Two-Phase Commit 2026-08-03
- EEVDF 2026-08-03
- Overview 2026-08-03
- Advanced Disjoint Set Union 2026-08-03
- Persistent Segtree 2026-08-03
- Link Cut Tree 2026-08-03
- Splay Tree 2026-08-03
- WBLT 2026-08-03
- Containers in Odin 2026-08-03
- Struct of Array Types 2026-08-03
- Associative Array 2026-08-03
- tokio Tutorial 2026-08-03
- Writing Commands 2026-08-03
- ArchLinux Connect to HKU Campus WiFi 2026-08-03
- OpenTSLM 2026-08-01 OpenTSLM is a multimodal model that tries to integrate time series and textual data.
- The BTRFS Filesystem 2026-08-01
- Monad Transformers 2026-08-01
- State Monad and StateT Monad 2026-08-01
- Rank-N Types 2026-08-01
- Functions 2026-08-01
- ArchLinux Package Build Script 2026-08-01 AUR is recently under attack, so it becomes important to be able to understand pkgbuild, the script to build packages in Arch Linux.
- The Foldable Typeclass in Haskell 2026-07-31
- Modeling the Context 2026-07-31
- Reader 2026-07-31
- The Traversable Typeclass 2026-07-31
- Generalized ADT 2026-07-31
- Vector Spaces 2026-07-28
- DDPM: Denoising Diffusion Probabilistic Models 2026-07-27
- DiT: Scalable Diffusion Models with Transformers 2026-07-27 DiT has a relatively simple idea that it replaces the U-Net in usual DDPM with Transformers (ViT).
- Large Language Diffusion Models 2026-07-27
- Maximum Likelihood Learning 2026-07-27 Maximum likelihood learning is a practical approach to train generative models that adopts probabilistic modeling.
- Score-Based Models — Working Notes 2026-07-27
- Flamingo: A Visual Language Model for Few-Shot Learning 2026-07-26
- Prompt Tuning 2026-07-26
- Finite Groups and Subgroups 2026-07-26
- Matrices 2026-07-26
- Replace MathJax with KaTeX in org-mode Exporting 2026-07-25
- Closures in Lua 2026-07-24
- Functions in Lua 2026-07-24
- Modules in Lua 2026-07-24
- OCaml Variants and Algebraic Data Types 2026-07-24
- Hypothesis Testing 2026-07-24
- Elisp: Positions 2026-07-23
- FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction 2026-07-22
- MTP: Multi-Token Prediction 2026-07-22 MTP is a speculative decoding method where the target model includes native multi-token prediction capability. Unlike draft-model-based methods, we don’t need separate draft models.
- PhaseFormer: From Patches to Phases for Efficient And Effective Time Series Forecasting 2026-07-22
- Elisp Data Structures: Hash Tables 2026-07-22 Elisp has 2 types of KV collections. Hash table is unordered set of KV pairs with no duplicate keys and constant access time; Association list is ordered set of KV pairs with possibly repeated keys.
- Elisp Data Structures: Lists 2026-07-22 Lisp Lists are implemented as linked lists. Each element can be any type and need not to be of same type.
- Elisp Data Structures: Vectors 2026-07-22 Vector implements the array data structures with fixed number of elements. Element’s value can be changed, but the number of elements cannot change.
- Elisp Functions 2026-07-22
- Elisp Symbols 2026-07-22
- Federated Inference: Towards Collaborative and Privacy-Preserving Inference over Edge Devices 2026-07-21
- SensorLM: Learning the Language of Wearable Sensors 2026-07-21 SensorLM is a family of foundation models that enable wearable sensor data understanding with natural language.
- Surface Integrals 2026-07-21
- Elisp Arithmetics 2026-07-21
- Elisp Boolean 2026-07-21
- Elisp Conditionals 2026-07-21
- Elisp Loop and Iteration 2026-07-21
- Elisp Strings 2026-07-21
- Elisp Variables 2026-07-21
- Print and Output with Elisp 2026-07-21 We introduce basic methods in Elisp to output and print messages.
- Address Translation: Segmentation 2026-07-20 The generic technique we’ll be using is called hardware-based address translation.
- Managing Memory in Odin 2026-07-20
- Qwen2.5-VL Technical Report 2026-07-18
- Arrays and Slices in Odin 2026-07-18
- Vectors and Array Programming 2026-07-18
- Enums, Unions and Switch 2026-07-17
- Procedures and Scopes 2026-07-17
- Odin Structs 2026-07-17
- Unions in Odin 2026-07-17
- defer Statements 2026-07-17
- Maybe Type in Odin 2026-07-17 ~Maybe~ type is a special union in Odin. Variables can either have no value or some value.
- Clustered Federated Learning 2026-07-16
- FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments 2026-07-16
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation 2026-07-15 DSpark is a speculative decoding framework proposed by DeepSeek. Speculative decoding is an acceleration technique for LLM inference.
- Robust Federated Inference 2026-07-15 Federated inference is different from federated learning. Federated learning emphasizes the aggregation of models trained on on-edge data; while federated inference focuses on that aggregate the results from distributedly deployed models. This paper focuses on robustness of this paradigm with theoretical formulation and analysis.
- Module Systems in OCaml 2026-07-14
- Contribution of Buddhism to Chinese Attitude towards Life 2026-07-13
- Buddhism and Confucianism - Filial Piety 2026-07-12
- Outline of Buddhist Impact on Chinese Culture 2026-07-12
- LA-LoRA: Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models 2026-07-09 This article reviews federated learning under differential privacy federated learning settings.
- Buddhist Schools of Thought and Tradition 2026-07-07
- Buddhist and Chinese Attitude to Life 2026-07-07 We briefly discuss about the similarities and differences between Buddhist and traditional Chinese thoughts, as well as Buddhism’s contribution to Chinese way of life.
- Buddhism in China - Cultural Outline 2026-07-07
- Divergence Theorem 2026-07-04
- Green’s Theorem 2026-07-04
- Line Integrals 2026-07-04
- Flow Matching 2026-07-03
- FlashMask 2026-07-02
- Basic Buddhist Teachings 2026-07-01
- Differential Operators 2026-06-30
- Length of Curves 2026-06-30
- Continuity 2026-06-30
- Differentiation and Derivative 2026-06-30
- C++26 - Static Reflection 2026-06-29
- SDFT: Self-Distillation Enables Continual Learning 2026-06-28 The paper proposes Self-Distillation Fine-Tuning (SDFT) that aims to handle the problem of continual learning: keep learning new skills while not forgetting old skills.
- Local Differential Privacy 2026-06-27 Local differential privacy (LDP) follows a decentralized paradigm that each client perturbs the local data before releasing, preserving populational information while protecting individual privacy. A common statistical tool frequency oracle is built on top of LDP that can handle various data frequency queries.
- TimeXer 2026-06-26
- Centralized Image Storage with Custom Tag 2026-06-26 I implemented a feature to centrally organize my images under
.assets/folder that supports image preview and exporting to HTML with correct path. - Diffusion Models 2026-06-24 Diffusion models learn to reverse a gradual noising process, transforming a simple Gaussian prior into samples from a complex data distribution.
- Introduction to Differential Privacy 2026-06-23 Briefly looks at previous approaches to protect privacy and why they fail; then discuss several important concepts in DP and formalize the definition.
- Migrate to jujutsu VCS 2026-06-23 jujutsu is a modern version control system that auto-records file edits.
- FedLWS: Federated Learning with Adaptive Layerwise Weight Shrinking 2026-06-22
- Modality Plug-and-Play 2026-06-22
- Change of Variable Formula 2026-06-22
- Latent Variable Models: VAEs 2026-06-21 VAE extends the idea of variational inference to use neural networks to model both encoder and decoder. For encoder, it uses neural network (e.g. CNN) to study distribution \( q_{\lambda}(\mathbf{z}|\mathbf{x}) \) and outputs a distribution of \( \mathbf{z} \). For decoder, we sample from the distribution \( p(\mathbf{z}) \) and generates images from it through decoder that have learnt \( p(\mathbf{x}|\mathbf{z}) \) from dataset.
- Normalizing Flow Models 2026-06-21 Autoregressive models provide tractable likelihoods but no direct mechanism for learning features, while VAEs can learn feature representations via latent variables but have intractable marginal likelihoods.
- Variational Inference 2026-06-21 Variational inference is the core math principle supporting modern generative models like VAE.
- C++ Type Traits in SFINAE 2026-06-21 SFINAE with type traits is equivalent to C++20 concepts.
- C++ Type Traits 2026-06-21 Type traits define compile-time template-based interfaces to query the properties of types.
- C++20 Concepts 2026-06-21 C++20 concepts provides compile-time checks of template arguments and perform functino dispatch based on properties of types.
- Groups 2026-06-20
- Generic Algorithm for Integer Programming 2026-06-20
- Overview of Linear Programming 2026-06-20 Linear Programming is a subset of optimization. This post discusses about general form of linear programming, convexity, and geometry of LP (which is simplex).
- C++26 - Contracts 2026-06-20 Contracts are function modifiers that conducts checks before function execution, similar to Solidity.
- FeDaL: Federated Dataset Learning for General Time Series Foundation Models 2026-06-19 FeDaL focuses on training time series foundation models (TSFMs) under federated settings. In short, FeDaL decomposes heterogeneous TS datasets into shared generalized knowledge and preserved personalized knowledge; it mitigates local and global biases through bias elimination. FeDaL also shows how data volume, client count and join rate affect model performance under decentralization.
- SageAttention — INT8 Scheme for Inference 2026-06-19
- Convexity 2026-06-19
- Overview of Optimization 2026-06-19
- Survey of RL for LRMs 2026-06-18 RL has become an important part for Large Reasoning Models. This article briefly reviews a survey paper on RL for LRMs, focusing on LLMs’ reasoning ability
- Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models 2026-06-18 Ferret uses first-order method with shared randomness to enable scalable full-parameter update. It also projects updates to a lower dimensional space to reduce communication overhead, and then reconstructs local updates from lower dimensional space with shared randomness for effective full-parameter global aggregation.
- MapReduce 2026-06-18 MapReduce used to be a popular paradigm for processing big data.
- How to Read A Paper: A Three-Pass Method 2026-06-18 A three-pass method to read a paper.
- Left Recursion 2026-06-17
- Predictive Parsing 2026-06-17 Like recursive rescent parsing, but parser can “predict” which production to use next, by looking at the next few tokens (which requires restricted grammars) and no backtracking.
- Terms in RL Post-Training 2026-06-15 Explain terms frequently appearing in AI articles.
- RL and Markov Decision Process 2026-06-15
- KL Divergence 2026-06-15 KL disvergence measures
- Concurrency in Rust 2026-06-14
- Euler Tour Tree 2026-06-13 Euler tour tree can be used to solve dynamic tree problem. It converts operations into range operations on DFS sequence. Compared to Link-Cut Tree, ETT is more suitable for maintaining subtree information.
- Treap 2026-06-13 Non-rotational treap (FHQ Treap) can be used to maintain sequence operations and balanced tree.
- Literature Review on World Models 2026-06-13
- Recursive Descent Parsing 2026-06-13 A top-down and left-to-right parsing algorithm that terminals are seens in order of appearance in the token stream.
- AST 2026-06-13
- Error Handling in Compilers 2026-06-13
- C++ future 2026-06-13
- C++ Threading 2026-06-13
- Path to Familiarize with Any PL 2026-06-13 Personal perspective on how to quickly familiarize with any programming language. Also a collection of introductory projects.
- Effective Modern C++14 2026-06-12 Effective Modern C++14, Best practices in industry.
- CLIP 2026-06-11 Pioneering algorithm for image understanding and image-text alignment.
- ViT: Vision Transformer 2026-06-11 Vision transformer (ViT) unifies the architecture for vision tasks with transformer, enabling later VLM-related works.
- Array Programming 2026-06-11
- Types 2026-06-11
- Module Management in Rust 2026-06-11 packages, crates, modules, workspaces
- Odin Basic Grammars 2026-06-10
- Cartesian Tree 2026-06-09
- Lexical Analysis 2026-06-09 Lexical analysis is about “classify program substrings according to their role” and then “communicate tokens to the parser”
- Lexical Specification & DFAs 2026-06-09 Briefly discuss how to use regex to specify lexemes, also its implementation.
- Parsing: Context-Free Grammars 2026-06-09
- Overview of Internet and Networks: How It Works? 2026-06-09
- Protocol Layers 2026-06-09 Layering and encapsulation organizes the structure of network.
- Address Space 2026-06-08
- Trap Mechanism and Context Switch 2026-06-07
- Haskell Basic Grammars 2026-06-07
- zig Grammars 2026-06-07
- DeepSeek V3.2 Technical Report 2026-06-06
- DeepSeek FP8 Training 2026-06-06 Briefly introduces DeepSeek’s FP8 training pipeline, as released in the DeepSeek V3 technical report.
- LoRA 2026-06-06 LoRA has somehow become the standard method for finetuning LLMs.
- Radio - Rate Distortion Optimization for LLM Compression 2026-06-06 Radio provides a novel view for quantization with optimization technique and rate-distortion theory, as well as a closed form for quantization bit. The drawback is that it does not consider hardware efficiency.
- Lichao Tree 2026-06-04
- Merging and Splitting Segtree 2026-06-04
- Segtree Basics 2026-06-04
- Split Federated Learning 2026-06-03 Split federated learning is a cross-field of FL and split learning, which can be regarded as a subset of distributed learning with some special settings.
- Android Emulator 2026-06-03 Introduces how to use Android Emulator to run android apps for testing
- DeepSeek V3.2 RL Protocol 2026-06-02
- Automatic Differentiation (AutoGrad) 2026-06-02
- DeepSeek Sparse Attention 2026-06-02 DeepSeek Sparse Attention (DSA) is introduced along with the DeepSeek V3.2 technical report. It’s designed to reduce computational complexity while preserving model performance in long context scenarios.
- Retrieving Results from Activities 2026-06-02 Briefly covers how to get results from activities after closing it, e.g., get file path from file chooser activity.
- Vanilla Attention 2026-06-01
- Principle beyond Apache Spark 2026-06-01
- Completely Fair Scheduler in Linux 2026-06-01 Linux uses CFS as its process scheduler, apart from textbooks’ MLFQ
- Process Scheduling 2026-06-01
- Limit 2026-06-01
- Run DimensionToTsuLovers on Linux 2026-06-01
- FedEx-LoRA: Exact Aggregation for Federated and Efficient Finetuning of Foundation Models 2026-05-31 Direct LoRA in federated settings causes inaccurate updates. FedEx-LoRA handles this by adding a residual error term to the pretrained frozen weight matrix, achieving exact updates.
- PagedAttention 2026-05-31
- SageAttention v2 — INT4 Scheme 2026-05-31
- Remote Procedure Call 2026-05-31
- MultiThreading in Android 2026-05-31
- OkHttp Library 2026-05-31 OkHttp is an open-source library for network requests. It’s simple, supports async, filtering, and is extensible, which makes it the standard for modern Android Apps.
- Design Pattern: Adapter 2026-05-31 Adapter is a structural design pattern that allows objects with incompatible interfaces to collaborate.
- Design Pattern: Bridge 2026-05-31 Bridge is a structural design pattern that lets you split a large class or a set of closely related classes into two separate hierarchies - abstraction and implementation - which can be developed independently of each other.
- Design Pattern: Composite 2026-05-31
- Disk Management and File System in Linux 2026-05-30 Introduces naming convention of hardware devices.
- Chain of Responsibility 2026-05-30 Chain of responsibility is a behavioural design pattern that passes requests along a chain of handlers.
- Abstract Factory 2026-05-30
- Modernity 2026-05-29
- Data Storage with Native Android File System 2026-05-29
- Room Persistence Library 2026-05-29
- Resource Folder in Android Project 2026-05-29
- Factory Method 2026-05-29
- SOLID Principles 2026-05-29
- Module Management in Haskell 2026-05-29
- Kotlin Grammars 2026-05-29
- Programming with Apache Spark 2026-05-28
- Programming with Hadoop 2026-05-28
- Content Providers 2026-05-28
- SQLite in Android 2026-05-28
- Data Storage in Android: SharedPreferences 2026-05-28
- Data Storage in Native Android: Overview 2026-05-28
- MVVM 2026-05-28
- Triple Products 2026-05-28
- Dynamic Segtree 2026-05-24
- Stokes Theorem 2026-05-24
- Helpful Resources 2026-09-03 Lectures, Course URLs, Blogs, Papers, etc. useful for my study.
- ACM (13)
- Advanced Disjoint Set Union 2026-08-03
- Cartesian Tree 2026-06-09
- Dynamic Segtree 2026-05-24
- Euler Tour Tree 2026-06-13 Euler tour tree can be used to solve dynamic tree problem. It converts operations into range operations on DFS sequence. Compared to Link-Cut Tree, ETT is more suitable for maintaining subtree information.
- Lichao Tree 2026-06-04
- Link Cut Tree 2026-08-03
- Merging and Splitting Segtree 2026-06-04
- Persistent Segtree 2026-08-03
- Segtree Basics 2026-06-04
- Splay Tree 2026-08-03
- Treap 2026-06-13 Non-rotational treap (FHQ Treap) can be used to maintain sequence operations and balanced tree.
- WBLT 2026-08-03
- Contests (1)
- 14th Chongqing CPC 2026-08-07
- AI (62)
- A Taste of ExecuTorch 2026-08-26 ExecuTorch is PyTorch’s cutting-edge solution for on-edge model deployment, with limited support for training.
- Automatic Differentiation (AutoGrad) 2026-06-02
- CLIP 2026-06-11 Pioneering algorithm for image understanding and image-text alignment.
- Clustered Federated Learning 2026-07-16
- Common Metrics 2026-08-31 Metrics are important in evaluating the quality of LLMs. Although nowadays, domain-specific datasets used for evaluating LLMs mainly treat metrics like task accuracy as the only golden standard, there are still general metrics for evaluation.
- DDPM: Denoising Diffusion Probabilistic Models 2026-07-27
- DeepSeek Sparse Attention 2026-06-02 DeepSeek Sparse Attention (DSA) is introduced along with the DeepSeek V3.2 technical report. It’s designed to reduce computational complexity while preserving model performance in long context scenarios.
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation 2026-07-15 DSpark is a speculative decoding framework proposed by DeepSeek. Speculative decoding is an acceleration technique for LLM inference.
- DeepSeek FP8 Training 2026-06-06 Briefly introduces DeepSeek’s FP8 training pipeline, as released in the DeepSeek V3 technical report.
- DiT: Scalable Diffusion Models with Transformers 2026-07-27 DiT has a relatively simple idea that it replaces the U-Net in usual DDPM with Transformers (ViT).
- FastMTP: Accelerating LLM Inference with Enhanced Multi-Token Prediction 2026-07-22
- FeDaL: Federated Dataset Learning for General Time Series Foundation Models 2026-06-19 FeDaL focuses on training time series foundation models (TSFMs) under federated settings. In short, FeDaL decomposes heterogeneous TS datasets into shared generalized knowledge and preserved personalized knowledge; it mitigates local and global biases through bias elimination. FeDaL also shows how data volume, client count and join rate affect model performance under decentralization.
- FedDAG: Clustered Federated Learning via Global Data and Gradient Integration for Heterogeneous Environments 2026-07-16
- FedEx-LoRA: Exact Aggregation for Federated and Efficient Finetuning of Foundation Models 2026-05-31 Direct LoRA in federated settings causes inaccurate updates. FedEx-LoRA handles this by adding a residual error term to the pretrained frozen weight matrix, achieving exact updates.
- FedHera 2026-08-26
- FedLWS: Federated Learning with Adaptive Layerwise Weight Shrinking 2026-06-22
- Federated Inference: Towards Collaborative and Privacy-Preserving Inference over Edge Devices 2026-07-21
- Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models 2026-06-18 Ferret uses first-order method with shared randomness to enable scalable full-parameter update. It also projects updates to a lower dimensional space to reduce communication overhead, and then reconstructs local updates from lower dimensional space with shared randomness for effective full-parameter global aggregation.
- Flamingo: A Visual Language Model for Few-Shot Learning 2026-07-26
- FlashMask 2026-07-02
- Flow Matching 2026-07-03
- GDN - Gated Delta Network 2026-08-29
- Diffusion Models 2026-06-24 Diffusion models learn to reverse a gradual noising process, transforming a simple Gaussian prior into samples from a complex data distribution.
- LA-LoRA: Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models 2026-07-09 This article reviews federated learning under differential privacy federated learning settings.
- Large Language Diffusion Models 2026-07-27
- Latent Variable Models: VAEs 2026-06-21 VAE extends the idea of variational inference to use neural networks to model both encoder and decoder. For encoder, it uses neural network (e.g. CNN) to study distribution \( q_{\lambda}(\mathbf{z}|\mathbf{x}) \) and outputs a distribution of \( \mathbf{z} \). For decoder, we sample from the distribution \( p(\mathbf{z}) \) and generates images from it through decoder that have learnt \( p(\mathbf{x}|\mathbf{z}) \) from dataset.
- LoRA 2026-06-06 LoRA has somehow become the standard method for finetuning LLMs.
- Multi-Head Attention and Grouped-Query Attention 2026-08-31
- Modality Plug-and-Play 2026-06-22
- MTP: Multi-Token Prediction 2026-07-22 MTP is a speculative decoding method where the target model includes native multi-token prediction capability. Unlike draft-model-based methods, we don’t need separate draft models.
- Maximum Likelihood Learning 2026-07-27 Maximum likelihood learning is a practical approach to train generative models that adopts probabilistic modeling.
- N-Gram Embedding 2026-08-29
- Normalizing Flow Models 2026-06-21 Autoregressive models provide tractable likelihoods but no direct mechanism for learning features, while VAEs can learn feature representations via latent variables but have intractable marginal likelihoods.
- OpenTSLM 2026-08-01 OpenTSLM is a multimodal model that tries to integrate time series and textual data.
- PagedAttention 2026-05-31
- PhaseFormer: From Patches to Phases for Efficient And Effective Time Series Forecasting 2026-07-22
- Prompt Tuning 2026-07-26
- RL and Markov Decision Process 2026-06-15
- Radio - Rate Distortion Optimization for LLM Compression 2026-06-06 Radio provides a novel view for quantization with optimization technique and rate-distortion theory, as well as a closed form for quantization bit. The drawback is that it does not consider hardware efficiency.
- Robust Federated Inference 2026-07-15 Federated inference is different from federated learning. Federated learning emphasizes the aggregation of models trained on on-edge data; while federated inference focuses on that aggregate the results from distributedly deployed models. This paper focuses on robustness of this paradigm with theoretical formulation and analysis.
- SDFT: Self-Distillation Enables Continual Learning 2026-06-28 The paper proposes Self-Distillation Fine-Tuning (SDFT) that aims to handle the problem of continual learning: keep learning new skills while not forgetting old skills.
- Sample-Efficient Integration of New Modalities into LLMs 2026-08-10 An interesting work that follows the idea of adopting a projector for modality adaptation, while leveraging a “hypernetwork” for generating LoRA weights from data samples to apply to the projector for adaptation.
- Split Federated Learning 2026-06-03 Split federated learning is a cross-field of FL and split learning, which can be regarded as a subset of distributed learning with some special settings.
- SageAttention v2 — INT4 Scheme 2026-05-31
- SageAttention — INT8 Scheme for Inference 2026-06-19
- Score-Based Models — Working Notes 2026-07-27
- SensorLM: Learning the Language of Wearable Sensors 2026-07-21 SensorLM is a family of foundation models that enable wearable sensor data understanding with natural language.
- SigLIP: Sigmoid Loss for Language Image Pretraining 2026-08-25 The advantage of SigLIP over CLIP is that SigLIP only relies on image-text pairs rather than global pairwise similarity, reducing computational cost from quadric to linear w.r.t. batch size.
- TimeXer 2026-06-26
- Vanilla Attention 2026-06-01
- Variational Inference 2026-06-21 Variational inference is the core math principle supporting modern generative models like VAE.
- ViT: Vision Transformer 2026-06-11 Vision transformer (ViT) unifies the architecture for vision tasks with transformer, enabling later VLM-related works.
- X-Fi: Modality-Invariant Foundation Model 2026-08-11
- ZeRO - Zero Redundancy Optimizer 2026-08-31 ZeRO adopts different levels of distributed strategy to remove redundancy in memory, at the cost of more communication. This work also gives birth to FSDP, a widely used distributed training schema.
- Overview (3)
- Literature Review on World Models 2026-06-13
- Survey of RL for LRMs 2026-06-18 RL has become an important part for Large Reasoning Models. This article briefly reviews a survey paper on RL for LRMs, focusing on LLMs’ reasoning ability
- Terms in RL Post-Training 2026-06-15 Explain terms frequently appearing in AI articles.
- Tech Reports (5)
- DeepSeek (3)
- DeepSeek V3.2 RL Protocol 2026-06-02
- DeepSeek V3.2 Technical Report 2026-06-06
- Thinking with Visual Primitives 2026-08-17
- Kimi (1)
- Kimi K3 2026-08-14
- Qwen (1)
- Qwen2.5-VL Technical Report 2026-07-18
- DeepSeek (3)
- Arts (9)
- Buddhist Impact on Chinese Culture (8)
- Basic Buddhist Teachings 2026-07-01
- Buddhism and Confucianism - Filial Piety 2026-07-12
- Buddhist Schools of Thought and Tradition 2026-07-07
- Buddhist and Chinese Attitude to Life 2026-07-07 We briefly discuss about the similarities and differences between Buddhist and traditional Chinese thoughts, as well as Buddhism’s contribution to Chinese way of life.
- Contribution of Buddhism to Chinese Attitude towards Life 2026-07-13
- Buddhism in China - Cultural Outline 2026-07-07
- Main Branches of Buddhism 2026-08-03
- Outline of Buddhist Impact on Chinese Culture 2026-07-12
- Social Psychology (1)
- Introduction to Social Psychology 2026-08-25
- Buddhist Impact on Chinese Culture (8)
- BookReview (1)
- Lectures on Modern Western Thought (1)
- Modernity 2026-05-29
- Lectures on Modern Western Thought (1)
- Computer Science (78)
- Compilers (15)
- principles (15)
- AST 2026-06-13
- Automatic Memory Management 2026-08-03
- Code Generation 2026-08-03
- Dataflow Analysis 2026-08-03
- Error Handling in Compilers 2026-06-13
- IR Optimization 2026-08-03
- Register Allocation 2026-08-03
- Runtime Management 2026-08-03
- Semantic Analysis 2026-08-03
- lexing (2)
- Lexical Analysis 2026-06-09 Lexical analysis is about “classify program substrings according to their role” and then “communicate tokens to the parser”
- Lexical Specification & DFAs 2026-06-09 Briefly discuss how to use regex to specify lexemes, also its implementation.
- parsing (4)
- Left Recursion 2026-06-17
- Parsing: Context-Free Grammars 2026-06-09
- Predictive Parsing 2026-06-17 Like recursive rescent parsing, but parser can “predict” which production to use next, by looking at the next few tokens (which requires restricted grammars) and no backtracking.
- Recursive Descent Parsing 2026-06-13 A top-down and left-to-right parsing algorithm that terminals are seens in order of appearance in the token stream.
- principles (15)
- Computer Graphics (1)
- 3D Gaussian Splatting (1)
- 3DGS 2026-08-03
- 3D Gaussian Splatting (1)
- Computer Networks (8)
- Overview of Internet and Networks: How It Works? 2026-06-09
- Protocol Layers 2026-06-09 Layering and encapsulation organizes the structure of network.
- Application Layer (6)
- DNS 2026-08-03
- Email 2026-08-03
- HTTP 2026-08-03
- Principles of Network Applications 2026-08-03
- Video Streaming and CDN 2026-08-03
- socket Programming 2026-08-03
- Distributed Systems (7)
- Principle beyond Apache Spark 2026-06-01
- MapReduce 2026-06-18 MapReduce used to be a popular paradigm for processing big data.
- Raft Consensus Protocol 2026-08-03
- Remote Procedure Call 2026-05-31
- Two-Phase Commit 2026-08-03
- practical (2)
- Programming with Apache Spark 2026-05-28
- Programming with Hadoop 2026-05-28
- Operating System (11)
- CPU (5)
- Overview 2026-08-03
- Trap Mechanism and Context Switch 2026-06-07
- scheduling (3)
- Completely Fair Scheduler in Linux 2026-06-01 Linux uses CFS as its process scheduler, apart from textbooks’ MLFQ
- EEVDF 2026-08-03
- Process Scheduling 2026-06-01
- File System (1)
- RAID 2026-08-10 Redundant Array of Inexpensive Disks (RAID) is a technology to build a faster, bigger, and more reliable disk system.
- Memory (4)
- Address Space 2026-06-08
- Address Translation: Segmentation 2026-07-20 The generic technique we’ll be using is called hardware-based address translation.
- Free Space Management 2026-08-09
- Paging, TLB and Page Tables 2026-08-09 Introduction to paging mechanism.
- case study - linux (1)
- Disk Management and File System in Linux 2026-05-30 Introduces naming convention of hardware devices.
- CPU (5)
- Software Engineering (36)
- MVVM 2026-05-28
- App Development (12)
- Client App Development (12)
- Native Android with Java and Kotlin (12)
- Data Storage in Native Android: Overview 2026-05-28
- Resource Folder in Android Project 2026-05-29
- Using
adb2026-08-26 ~adb~ is a useful tool for diagnosing Android phones, as well as running C++ programs on Android phones. - basics (1)
- Retrieving Results from Activities 2026-06-02 Briefly covers how to get results from activities after closing it, e.g., get file path from file chooser activity.
- data storage (5)
- Content Providers 2026-05-28
- Data Storage with Native Android File System 2026-05-29
- Room Persistence Library 2026-05-29
- SQLite in Android 2026-05-28
- Data Storage in Android: SharedPreferences 2026-05-28
- emulator (1)
- Android Emulator 2026-06-03 Introduces how to use Android Emulator to run android apps for testing
- networking (2)
- MultiThreading in Android 2026-05-31
- OkHttp Library 2026-05-31 OkHttp is an open-source library for network requests. It’s simple, supports async, filtering, and is extensible, which makes it the standard for modern Android Apps.
- Native Android with Java and Kotlin (12)
- Client App Development (12)
- Design Patterns (23)
- SOLID Principles 2026-05-29
- Behavioural (10)
- Chain of Responsibility 2026-05-30 Chain of responsibility is a behavioural design pattern that passes requests along a chain of handlers.
- Command 2026-08-03
- Iterator 2026-08-03
- Mediator 2026-08-03
- Memento 2026-08-03
- Observer 2026-08-03
- State 2026-08-03
- Strategy 2026-08-03
- Template Method 2026-08-03
- Visitor 2026-08-03
- Creational (5)
- Abstract Factory 2026-05-30
- Builder 2026-08-14
- Factory Method 2026-05-29
- Prototype 2026-08-03
- Singleton 2026-08-03
- Structural (7)
- Design Pattern: Adapter 2026-05-31 Adapter is a structural design pattern that allows objects with incompatible interfaces to collaborate.
- Design Pattern: Bridge 2026-05-31 Bridge is a structural design pattern that lets you split a large class or a set of closely related classes into two separate hierarchies - abstraction and implementation - which can be developed independently of each other.
- Design Pattern: Composite 2026-05-31
- Decorator 2026-08-03
- Facade 2026-08-03
- Flyweight 2026-08-03
- Proxy 2026-08-03
- Compilers (15)
- Differential Privacy (2)
- Introduction to Differential Privacy 2026-06-23 Briefly looks at previous approaches to protect privacy and why they fail; then discuss several important concepts in DP and formalize the definition.
- Local Differential Privacy 2026-06-27 Local differential privacy (LDP) follows a decentralized paradigm that each client perturbs the local data before releasing, preserving populational information while protecting individual privacy. A common statistical tool frequency oracle is built on top of LDP that can handle various data frequency queries.
- GPU Programming (2)
- Techniques (2)
- Double Buffering 2026-08-14 Double buffering is a pipelining technique in GPU programming. It allocates two staging buffers and alternates between them, so that the data movement for iteration \(k+1\) can overlap computation for iteration \(k\).
- Vectorization 2026-08-14
- Techniques (2)
- Mathematics (31)
- Abstract Algebra (4)
- Group Theory (4)
- Cyclic Group 2026-08-29
- Finite Groups and Subgroups 2026-07-26
- Groups 2026-06-20
- Permutation Groups 2026-09-01
- Group Theory (4)
- Analysis (11)
- Continuity 2026-06-30
- Differentiation and Derivative 2026-06-30
- Limit 2026-06-01
- Vector Calculus (8)
- Differential Operators 2026-06-30
- Divergence Theorem 2026-07-04
- Green’s Theorem 2026-07-04
- Length of Curves 2026-06-30
- Line Integrals 2026-07-04
- Stokes Theorem 2026-05-24
- Surface Integrals 2026-07-21
- Triple Products 2026-05-28
- Linear Algebra (6)
- Determinants 2026-08-03
- Eigenvalues and Eigenvectors 2026-08-03
- Jordan Form 2026-08-03
- Matrices 2026-07-26
- Orthogonality 2026-08-03
- Vector Spaces 2026-07-28
- Number Theory (1)
- Natural Numbers and Integers 2026-08-14
- Optimization (7)
- Convexity 2026-06-19
- Overview of Optimization 2026-06-19
- Convex (1)
- Overview of Convex Optimization 2026-09-01 Convex optimization focuses on a subset of optimization problems, i.e., the objectives and constraints are convex, which means \( f(ax+by) \le a f(x) + b f(y) \).
- integer (3)
- Branch-and-Bound Method 2026-08-03
- Generic Algorithm for Integer Programming 2026-06-20
- Overview of Integer Programming 2026-08-03
- linear (1)
- Overview of Linear Programming 2026-06-20 Linear Programming is a subset of optimization. This post discusses about general form of linear programming, convexity, and geometry of LP (which is simplex).
- Probability (2)
- Change of Variable Formula 2026-06-22
- KL Divergence 2026-06-15 KL disvergence measures
- Abstract Algebra (4)
- Miscellaneous (10)
- How to Read A Paper: A Three-Pass Method 2026-06-18 A three-pass method to read a paper.
- Meetings (2)
- TechTips (7)
- Grammars for Building Container Images 2026-08-05 ContainerFile and DockerFile are almost the same, the difference between which is simply that the former is the default for
podman, while the latter is the default fordocker. - Migrate to jujutsu VCS 2026-06-23 jujutsu is a modern version control system that auto-records file edits.
- The BTRFS Filesystem 2026-08-01
- Using
jq2026-08-29 - orgmode (1)
- Centralized Image Storage with Custom Tag 2026-06-26 I implemented a feature to centrally organize my images under
.assets/folder that supports image preview and exporting to HTML with correct path.
- Centralized Image Storage with Custom Tag 2026-06-26 I implemented a feature to centrally organize my images under
- uv (2)
- Project Configuration 2026-08-10
- uv - Swiss Army Knife for Python 2026-08-10
- Grammars for Building Container Images 2026-08-05 ContainerFile and DockerFile are almost the same, the difference between which is simply that the former is the default for
- Programming Languages (73)
- Path to Familiarize with Any PL 2026-06-13 Personal perspective on how to quickly familiarize with any programming language. Also a collection of introductory projects.
- Bash (1)
- Associative Array 2026-08-03
- C++ (8)
- Effective Modern C++14 2026-06-12 Effective Modern C++14, Best practices in industry.
- Features (2)
- C++26 - Contracts 2026-06-20 Contracts are function modifiers that conducts checks before function execution, similar to Solidity.
- C++26 - Static Reflection 2026-06-29
- STL (2)
- C++ future 2026-06-13
- C++ Threading 2026-06-13
- template (3)
- C++20 Concepts 2026-06-21 C++20 concepts provides compile-time checks of template arguments and perform functino dispatch based on properties of types.
- meta-programming (2)
- C++ Type Traits in SFINAE 2026-06-21 SFINAE with type traits is equivalent to C++20 concepts.
- C++ Type Traits 2026-06-21 Type traits define compile-time template-based interfaces to query the properties of types.
- Elisp (16)
- Print and Output with Elisp 2026-07-21 We introduce basic methods in Elisp to output and print messages.
- Printed Representation and Read Syntax 2026-08-11
- Emacs Lisp (2)
- Elisp: Positions 2026-07-23
- Writing Commands 2026-08-03
- Lisp Basics (12)
- Elisp Arithmetics 2026-07-21
- Elisp Boolean 2026-07-21
- Elisp Conditionals 2026-07-21
- Elisp Functions 2026-07-22
- Elisp Loop and Iteration 2026-07-21
- Elisp Strings 2026-07-21
- Elisp Symbols 2026-07-22
- Elisp Variables 2026-07-21
- Numbers 2026-08-11
- Data Structure (3)
- Elisp Data Structures: Hash Tables 2026-07-22 Elisp has 2 types of KV collections. Hash table is unordered set of KV pairs with no duplicate keys and constant access time; Association list is ordered set of KV pairs with possibly repeated keys.
- Elisp Data Structures: Lists 2026-07-22 Lisp Lists are implemented as linked lists. Each element can be any type and need not to be of same type.
- Elisp Data Structures: Vectors 2026-07-22 Vector implements the array data structures with fixed number of elements. Element’s value can be changed, but the number of elements cannot change.
- Haskell (10)
- Haskell Basic Grammars 2026-06-07
- Module Management in Haskell 2026-05-29
- Modeling Effects (6)
- The Foldable Typeclass in Haskell 2026-07-31
- Modeling the Context 2026-07-31
- Monad Transformers 2026-08-01
- Reader 2026-07-31
- State Monad and StateT Monad 2026-08-01
- The Traversable Typeclass 2026-07-31
- Type System (2)
- Generalized ADT 2026-07-31
- Rank-N Types 2026-08-01
- Koka (1)
- Basic Grammars (1)
- Functions 2026-08-01
- Basic Grammars (1)
- Kotlin (1)
- Kotlin Grammars 2026-05-29
- Lisp Family (3)
- Lua (11)
- Closures in Lua 2026-07-24
- Coroutines in Lua 2026-08-12
- Crash Course of Lua 2026-08-11
- Functions in Lua 2026-07-24
- Iterators 2026-08-14
- Modules in Lua 2026-07-24
- OOP Patterns 2026-08-12
- Results and Error Handling 2026-08-14
- Tables in Lua 2026-08-12
- Library (2)
- IO and OS 2026-08-12
- String STL 2026-08-12
- OCaml (2)
- Module Systems in OCaml 2026-07-14
- Data Types (1)
- OCaml Variants and Algebraic Data Types 2026-07-24
- Odin (14)
- Array Programming 2026-06-11
- Managing Memory in Odin 2026-07-20
- Odin Basic Grammars 2026-06-10
- Struct of Array Types 2026-08-03
- Types 2026-06-11
- Array Programming (2)
- Arrays and Slices in Odin 2026-07-18
- Vectors and Array Programming 2026-07-18
- Grammars (5)
- Enums, Unions and Switch 2026-07-17
- Procedures and Scopes 2026-07-17
- Odin Structs 2026-07-17
- Unions in Odin 2026-07-17
- defer Statements 2026-07-17
- STL (2)
- Containers in Odin 2026-08-03
- Maybe Type in Odin 2026-07-17 ~Maybe~ type is a special union in Odin. Variables can either have no value or some value.
- Python (1)
- Logging Library 2026-08-12 Introduces useful libraries for logging.
- Rust (3)
- Concurrency in Rust 2026-06-14
- Module Management in Rust 2026-06-11 packages, crates, modules, workspaces
- tokio Tutorial 2026-08-03
- Zig (1)
- zig Grammars 2026-06-07
- Quantum Computing (1)
- Essential Concepts in Quantum Computing 2026-09-01
- Seminars (2)
- Statistics (4)
- Confidence Interval Estimation 2026-08-03
- Hypothesis Testing 2026-07-24
- Linear Regression 2026-08-03
- Sample Distribution Theory 2026-08-03
- Techtips (6)
- Replace MathJax with KaTeX in org-mode Exporting 2026-07-25
- Linux Tips (5)
- ArchLinux Connect to HKU Campus WiFi 2026-08-03
- ArchLinux Package Build Script 2026-08-01 AUR is recently under attack, so it becomes important to be able to understand pkgbuild, the script to build packages in Arch Linux.
- Run DimensionToTsuLovers on Linux 2026-06-01
- Solution to Being Unable to Clear Screen 2026-08-28
- Use reflector to Select Best pacman Mirrors 2026-08-06