🔬 Research Pulse
Daily Digest
September 15, 2026
🦾 ROBOTICS
1. ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids
Authors: Gechen Qu, Tong Zhang, Bike Zhang... Published: 2026-09-14 | Citations: 0 arXiv | PDF
2. Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Hands
Authors: Zhenjie Yang, Yideng Zhang, Dongjie Zhang... Published: 2026-09-14 | Citations: 0 arXiv | PDF
3. Touch2Trace: Tactile-Driven Imitation Learning for Dexterous Cable Tracing
Authors: Matteo Grimaldi, David Klee, Ziling Chen... Published: 2026-09-14 | Citations: 0 arXiv | PDF
🏥 HEALTHCARE
1. K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversations
Authors: Laura M. Vowels, Matthew J. Vowels, Shivali Sharma... Published: 2026-09-14 | Citations: 0 arXiv | PDF
2. LongAgent: History-Guided Agentic Search for Longitudinal Outcome Prediction
Authors: Siyao Wang, Florian Guitton, Shuojie Fu... Published: 2026-09-14 | Citations: 0 arXiv | PDF
3. Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale
Authors: Aman Priyanshu, Supriti Vijay, Kimia Majd... Published: 2026-09-14 | Citations: 0 arXiv | PDF
🔥 GitHub Trending
1. lidge-jun/opencodex
⭐ 14717 stars | TypeScript
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
ai-gateway ai-tools anthropic chatgpt claude claude-code
2. drumih/turbo-fieldfare
⭐ 6731 stars | Swift
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
apple-silicon gemma gemma4 gemma4-26b-a4b gpgpu llm
3. kirodotdev/KiroCrew
⭐ 3922 stars | Python
A persistent workspace for development work that self-improves and continues beyond one session.
agent agentic-ai agents ai-agent ai-agents automation
4. datawhalechina/zero-to-sglang
⭐ 908 stars | Python
Official SGLang x Datawhale course on LLM inference: understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. Available in English and Chinese.
cuda datawhale inference-engine infra kv-cache llm
5. TrenTorch/TrenTorch
⭐ 245 stars | Python
Learn PyTorch by building your own. (inspired from Harvard's TinyTorch)
cli deep-learning education engineering from-scratch machine-learning
6. Extraltodeus/J-Wash
⭐ 230 stars | Python
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
abliteration ai anthropic artificial-intelligence huggingface interpretability
7. Code-Amadeus/Amadeus
⭐ 219 stars | Python
Real-time multimodal desktop agent evolving toward a persistent AI OS interface (0.1 α).
ai-agent auip cuda desktop-agent electron gpt-sovits
8. seoan1024/Korean-llm-v3
⭐ 114 stars | Python
PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트
1b ai deep-learning from-scratch korean korean-nlp
9. gittensor-ai-lab/sparkinfer
⭐ 78 stars | C++
Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.
agentic-ai bittensor blackwell cuda edge-ai gittensor
10. FRS2003/hands-on-llm
⭐ 72 stars | Python
动手学大模型全栈：CS336 中文精讲 · PyTorch 手搓 Transformer · 单卡复现 Pretrain/SFT/LoRA/DPO/GRPO/RLVR · PEFT/Agent/RAG 落地（含真实实验、曲线与复现脚本）
cs336 deep-learning dpo from-scratch grpo hands-on
Generated by Research Pulse on 2026-09-15 06:06