Results for “binarized-neural-networks”

Proactively hunt for adversary abuse of legitimate system binaries (LOLBins) to execute malicious payloads while evading detection.

Classifies situations into 256 binary states and maps each to a prescribed action, reporting the pattern, decimal, name, range, and action to execute.

Multimodal Neurons in Artificial Neural Networks

Add the /bl switch to MSBuild-based commands to generate binary logs for build diagnostics and performance analysis.

Diagnose MSBuild build performance bottlenecks using binary log analysis, covering timeline analysis, performance summary interpretation, and seven common bottleneck categories.

Extract false-positive and false-negative gaps from VLM binary-classification-question predictions by comparing model responses against ground truth, producing a structured JSONL file and summary report for downstream root-cause analysis.

Analyze ELF binaries for exploitation vectors using checksec, ROPgadget, and pwntools for buffer overflow and ROP chain development during authorized security testing and CTF challenges.

NLVR2: A Visual Reasoning Benchmark for Natural Language

Detect abuse of legitimate Windows binaries (LOLBins) used for living off the land attacks by monitoring process creation, command-line arguments, and parent-child relationships.

Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.

Emu: Generative Pretraining in Multimodality

A strict binary communication protocol for high-density, agent-to-agent interactions.

CogVLM: Visual Expert for Pretrained Language Models

贾宝玉（古典虚构）认知与表达框架（压缩蒸馏）：情不情、反仕途经济、女儿崇拜叙事… 触发：红楼梦 等。虚构；非性别刻板侮辱

BISON v2.0 — Conviction Holder (Hardened). Top 10 assets by volume. All signals are score contributors — no hard gates. Scanner enters via create_position internally (Wolverine pattern). RatchetStop exits. Thesis exit REMOVED. v2.0: every hard gate converted to score contributor, ensureExecutionAsTaker=false, conviction-scaled margin 25-37%.

Flamingo: A Visual Language Model for Few-Shot Learning

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Hunt for Mimikatz execution using command-line patterns, LSASS access signatures, binary indicators, and in-memory detection of known modules.

Multimodal Few-Shot Learning with Frozen Language Models

Out-of-core tabular analytics with Vaex for billion-row datasets that exceed RAM — lazy evaluation, fast aggregations, big-data visualization, and ML on a single machine. Use when working with large CSV/HDF5/Arrow/Parquet files, computing fast statistics on massive datasets, visualizing big data, or building ML pipelines that do not fit in memory. For distributed clusters prefer dask; for in-memory speed prefer polars. Part of the AlterLab Academic Skills suite.

Organize, query, validate, and convert neuroscience and biomedical data using the Brain Imaging Data Structure (BIDS) standard.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Identifies and analyzes statistical arbitrage opportunities through pair trading, using correlation analysis, cointegration testing, and z-score calculations to generate entry/exit signals for market-neutral strategies.

Detect C2 beaconing patterns in network traffic using frequency analysis, jitter detection, and domain reputation to identify compromised endpoints communicating with adversary infrastructure.

Reverse engineer malware binaries using NSA's Ghidra disassembler and decompiler to understand internal logic, cryptographic routines, C2 protocols, and evasion techniques at the assembly and pseudo-C level.

Foundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decomposition

Orchestrates a complete bulk RNA-seq differential-expression study from raw FASTQ reads through QC, alignment, quantification, differential expression, pathway enrichment, and publication figures.

BALD EAGLE v3.0 — XYZ Alpha Hunter (Hardened). Focused on 6 high-liquidity XYZ assets: CL, BRENTOIL, GOLD, SILVER, SP500, XYZ100. Conviction-scaled leverage (5-10x based on score). Wider DSL for macro assets. Maker-only execution. Scanner calls create_position internally. v3.0: focused assets, conviction-scaled leverage, XYZ-tuned DSL, no thesis exit.

Structured data + RAG. NL2SQL hybrid patterns (text-to-SQL then execute vs embed rows), table embedding strategies (row-level, schema-level, hybrid), semantic layer integration (Cube, dbt metrics), LangChain SQLDatabaseChain, LlamaIndex PandasQueryEngine, safe SQL execution (read-only, sandboxed), schema-aware retrieval. Full PostgreSQL + pgvector hybrid code. USE WHEN: user mentions "tabular RAG", "NL2SQL", "text to SQL", "RAG on tables", "database RAG", "SQL RAG", "semantic layer", "structured data RAG" DO NOT USE FOR: unstructured doc RAG - use `rag-architecture`; metadata filtering only - use `self-querying-retriever`; KG retrieval - use `graph-rag`

Authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery with structured workflow and tooling.

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest", "generalized random forest", "GRF", "double machine learning", "DML", "debiased machine learning", "LASSO for variable selection", "post-LASSO", "heterogeneous treatment effects", "CATE", "conditional average treatment effect", "BLP analysis", "CLAN analysis", "causal tree", "honest estimation", "因果森林", "双重机器学习", "异质性处理效应", "条件平均处理效应", "LASSO变量选择", "机器学习因果推断", "去偏机器学习"

Perform fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O, DataFusion SQL, and pileup on Polars DataFrames via the polars-bio library, serving as a scalable alternative to bioframe and bedtools.

DataFrame operations with pandas and polars — groupby, joins, reshaping, performance. Use when manipulating tabular data, choosing between pandas and polars, optimizing DataFrame code, or translating between the two libraries.