• 2
• 0
• 0

DX

• 2
• 0
• 0

ROCK

A construction kit for reinforcement learning environment management.

• 2
• 0
• 0

SimCIT

• 2
• 0
• 0

vllm_xformers_prefetch

• 2
• 0
• 0

Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.(Fork for contributing. All changes intended for upstream ...

• 2
• 0
• 0

nvshmem

NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM.(Fork for contributing. All changes intended for upstream PRs.)

• 2
• 0
• 0

results

Data for the MTEB leaderboard(Fork for contributing. All changes intended for upstream PRs.)

• 2
• 0
• 0

UI-Ins

Official implementation of UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning

• 2
• 0
• 0

mteb

MTEB: Massive Text Embedding Benchmark (Fork for contributing to mteb. All changes intended for upstream PRs.)

• 2
• 0
• 0

SmartResume

• 2
• 0
• 0

XiYan-SQL

• 2
• 0
• 0

ReWatch-R1

• 2
• 0
• 0

unified-audio

• 2
• 0
• 0

InferSim

A Lightweight LLM Inference Performance Simulator

• 2
• 0
• 0

page-agent

• 2
• 0
• 0

identity-grpo

Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning

• 2
• 0
• 0

Helios

• 2
• 0
• 0

SKYLENAGE-ReasoningMath

• 2
• 0
• 0

seckit

• 2
• 0
• 0

TPO

[EMNLP 2025] The official implementation of the paper "Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination...