Expert-guided red-teaming framework for financial LLM safety evaluation.

Converts visual algorithms to microcontroller C code

A public repository providing a comprehensive index and standards for sign-language datasets.

A framework integrating Lean proof assistant for process-level reward signals in RL for theorem proving.

Large-scale training dataset with 238K episodes for embodied dialog navigation.

A framework for interpreting Neural Combinatorial Optimization policies via distilled program portfolios.

Algebraic Symbolic Mathematical Operations Benchmark for evaluating LLM reasoning in math.

A frequency-domain framework for analyzing what State Space Models learn about code.

A geometric embedding method for multi-hop reasoning on knowledge graphs with transitive relations.

An open-source RL platform used to implement the Spotlight system.

Rust implementation of the Mistral model for high-performance inference.

A proxy gateway that allows calling multiple LLM providers using a single OpenAI-compatible API.

Research proposing foundation models for Reinforcement Learning using synthetic MDPs.

A morphology-aware neural tokenizer and word embedder for the Turkish language.

Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering

Context management via Uncertainty-aware admission and Redundancy aware Eviction for TFMs

A library for faster and more memory-efficient LLM fine-tuning.

Implementation of structured adversarial camouflage using Voronoi diagrams for AI evasion.

An LLM-choreographed multi-agent world model for multi-view driving video generation.

Activation explainer for deception auditing in reasoning LLMs using hidden state decoding.