Author

Machine Learning Algorithms & Natural Language Processing

Focused on frontier AI technologies, empowering AI researchers' progress.

216

Articles

Likes

Views

Comments

Latest from Machine Learning Algorithms & Natural Language Processing

100 recent articles max

Machine Learning Algorithms & Natural Language Processing

Apr 16, 2026 · Artificial Intelligence

Can AI Generate Full Repositories from a README? Inside Microsoft’s RepoGenesis Benchmark

RepoGenesis, a new ACL 2026 benchmark introduced by Microsoft Research, evaluates whether large‑language‑model agents can turn a structured README into a complete, deployable microservice repository, measuring Pass@1, API coverage and deployment success across 106 Python and Java projects.

JavaPythonRepoGenesis

0 likes · 8 min read

Can AI Generate Full Repositories from a README? Inside Microsoft’s RepoGenesis Benchmark

Machine Learning Algorithms & Natural Language Processing

Apr 16, 2026 · Artificial Intelligence

Evidence Mining for Explainable AI: Methods and Applications

The talk introduces evidence‑mining techniques that extract supporting information from input text to improve model explainability, discusses the shortcut‑learning pitfalls of existing methods, and presents a new approach that enhances reliability and integrates with large‑model chain‑of‑thought compression for more interpretable, efficient reasoning.

AI researchModel Interpretabilityevidence mining

0 likes · 4 min read

Evidence Mining for Explainable AI: Methods and Applications

Machine Learning Algorithms & Natural Language Processing

Apr 15, 2026 · Artificial Intelligence

Industrial Code LLM Learns to Think Before Writing – InCoder-32B Thinking Tackles Verilog and CUDA Pitfalls

The article analyzes InCoder-32B Thinking, an industrial‑code large language model that incorporates error‑driven chain‑of‑thought and an Industrial Code World Model to predict execution outcomes, adapt reasoning depth, and achieve high accuracy across diverse hardware‑centric benchmarks.

CUDALarge Language ModelVerilog

0 likes · 7 min read

Industrial Code LLM Learns to Think Before Writing – InCoder-32B Thinking Tackles Verilog and CUDA Pitfalls

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Artificial Intelligence

Revisiting On-Policy Distillation (OPD): Typical Failures and a More Stable Fix

On‑Policy Distillation (OPD) is widely used for post‑training large language models, but the sampled‑token variant often becomes unstable due to token‑level reward imbalance, teacher‑student signal mismatch on student‑generated prefixes, and tokenizer mismatches; this article analyses the bias‑variance trade‑off, identifies three root failure modes, and proposes a teacher‑top‑K local‑support‑set objective with top‑p rollout and special‑token masking that yields more stable training and better performance on both math and agentic benchmarks.

OPDOn-Policy Distillationlarge language models

0 likes · 32 min read

Revisiting On-Policy Distillation (OPD): Typical Failures and a More Stable Fix

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Artificial Intelligence

Beware the Cost Reversal in LLMs: Are Cheaper Models More Expensive?

A recent study of eight popular large language models across nine benchmark tasks shows that lower‑priced APIs often lead to higher actual expenses because inference token usage varies dramatically, making model cost highly unpredictable and exposing a hidden "boots" phenomenon.

AI economicscost analysisinference tokens

0 likes · 10 min read

Beware the Cost Reversal in LLMs: Are Cheaper Models More Expensive?

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Artificial Intelligence

Why Harness Is the Strategic Asset for AI Agents in 2026

The article analyzes the 2026 turning point where AI model intelligence plateaued and argues that mastering Harness—an infrastructure that wraps models—has become the decisive factor for building controllable, scalable Agent systems, tracing its necessity through three decades of software engineering evolution.

AI agentsClaude CodeContext Engineering

0 likes · 20 min read

Why Harness Is the Strategic Asset for AI Agents in 2026

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Artificial Intelligence

Two‑Year‑Old Chinese Forecast Gains Global Consensus as Meta, METR and Others Confirm the Same AI Scaling Law

A Chinese research team’s 2024 "density law"—which predicts that the parameters needed for a given LLM performance halve every 3.5 months—has been independently validated by Meta’s scaling ladder, METR’s time‑horizon report, and subsequent analyses, revealing a unified exponential growth curve that reshapes expectations for inference cost, edge AI feasibility, and optimal model‑development strategies.

AI scalingEdge AILLM density law

0 likes · 11 min read

Two‑Year‑Old Chinese Forecast Gains Global Consensus as Meta, METR and Others Confirm the Same AI Scaling Law

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Artificial Intelligence

Balancing Usability, Fun, and Safety: How Fudan’s Post‑00 Team Built XSafeClaw for Controllable AI Agents

Amid soaring hype for autonomous agents, a Meta incident exposed how hidden execution steps can cause real‑world damage, prompting Fudan’s XSafeClaw project to deliver a visual, layer‑by‑layer security framework that makes agent behavior observable, auditable, and safely interceptable.

Agent safetyHuman-in-the-loopRuntime monitoring

0 likes · 10 min read

Balancing Usability, Fun, and Safety: How Fudan’s Post‑00 Team Built XSafeClaw for Controllable AI Agents

Machine Learning Algorithms & Natural Language Processing

Apr 14, 2026 · Information Security

SkillAttack Reveals 6,500+ Attack Paths – Community‑Built SkillAtlas Secures Agent Skills

SkillAttack automates red‑team testing of LLM‑driven Agent Skills, exposing real attack paths across dozens of models, while the community‑curated SkillAtlas now hosts over 6,500 publicly searchable traces covering 233 skills and 18 major model families, inviting researchers and developers to contribute.

AI safetyAgent SecurityAttack Path Library

0 likes · 7 min read

SkillAttack Reveals 6,500+ Attack Paths – Community‑Built SkillAtlas Secures Agent Skills

Machine Learning Algorithms & Natural Language Processing

Apr 12, 2026 · Artificial Intelligence

Deep Dive into Forward vs Reverse KL Divergence: When to Use Which?

The article explains the definitions, properties, and asymmetric nature of KL divergence, compares Forward KL (mean‑seeking) and Reverse KL (mode‑seeking) through bimodal examples, and provides practical guidelines for choosing between them based on sampling and probability‑evaluation capabilities in machine‑learning tasks.

Forward KLKL DivergenceReverse KL

0 likes · 10 min read

Deep Dive into Forward vs Reverse KL Divergence: When to Use Which?