-
3d-gen-for-llm-builders Public
A hands-on guide to 3D latent diffusion for LLM/VLM builders
-
-
-
cc-agent-fork-archive Public
Forked from ultraworkers/claw-codeBetter Harness Tools, not merely storing the archive of leaked Claude Code but also make shit things done. Now rewriting in Rust.
-
AgentSynth Public
AgentSynth: Industrial-Grade Agent Data Synthesis Pipeline
-
AdaRubrics Public
AdaRubric: Adaptive Dynamic Rubric Evaluator for Agent Trajectories
-
AgentHER Public
AgentHER: Hindsight Experience Replay for LLM Agents
-
NemoClaw Public
Forked from NVIDIA/NemoClawNVIDIA plugin for secure installation of OpenClaw
JavaScript Apache License 2.0 UpdatedMar 19, 2026 -
page-agent Public
Forked from alibaba/page-agentJavaScript in-page GUI agent. Control web interfaces with natural language.
TypeScript MIT License UpdatedMar 19, 2026 -
unsloth Public
Forked from unslothai/unslothFine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Python Apache License 2.0 UpdatedMar 16, 2026 -
FibrationPO Public
unofficial implementation of Fibration Policy Optimization (https://arxiv.org/pdf/2603.08239)
-
ms-swift Public
Forked from modelscope/ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
Python Apache License 2.0 UpdatedMar 14, 2026 -
openclaw Public
Forked from openclaw/openclawYour own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
TypeScript MIT License UpdatedMar 14, 2026 -
DDCA Public
dynamic decoupled conditional advantage for efficient reasoning
-
trajectory_tokenization Public
Trajectory Tokenization for ReAct: compress older steps into tokens, keep recent steps full—no training, drop-in
-
officeqa-agentbeats-leaderboard Public
Forked from RDI-Foundation/officeqa-agentbeats-leaderboardPython UpdatedMar 7, 2026 -
agentx-agentbeats-officeqa Public
OfficeQA Purple Agent for Berkeley RDI AgentX-AgentBeats (Finance track)
Python UpdatedMar 7, 2026 -
BiT Public
BiT: Improving neural machine translation with bidirectional training - EMNLP 2021
-
CCAN Public
CCAN: Context-Aware Cross-Attention for Non-Autoregressive Translation - COLING 2020
-
Bottleneck_LC Public
Bottleneck_LC: Widening the bottleneck of lexical choice in NAT - Computer Speech & Language 2025
-
Recurrent Graph Syntax Encoder (RGSE) for NMT - arxiv 2019
-
LCNAT Public
LCNAT: Lexical choice in NAT - ICLR 2021
-
RLFW-NAT.mono Public
RLFW-NAT.mono: Redistributing low-frequency words (monolingual data) - ACL 2022
-
RLFW-NAT Public
RLFW-NAT: Rejuvenating low-frequency words (parallel data) - ACL 2021
-
XLPE Public
XLPE: Cross-lingual position encoding - ACL 2020
-
-
darts.pytorch1.1 Public
Implementation with latest PyTorch (v1.1) for multi-gpu differentiable architecture search https://arxiv.org/abs/1806.09055
-
R1 Public
🚀enhanced GRPO with more verifiable rewards and real-time evaluators
-
dr-tulu Public
Forked from rlresearch/dr-tuluOfficial repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Python Apache License 2.0 UpdatedNov 22, 2025 -
DeepAgent Public
Forked from RUC-NLPIR/DeepAgent🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
Python MIT License UpdatedNov 2, 2025
{{ message }}