🔬 Research Pulse
Daily Digest
September 16, 2026
🤖 AI
🧠 LLMs
1. Verifiable Social Reasoning for LLM Assistants
Authors: Amir Taubenfeld, Zorik Gekhman, Avigail Grinstein-Dabush... Published: 2026-09-15 | Citations: 0 arXiv | PDF
🤖 Agents
1. Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems
Authors: Deepak Akkil, Tamer Abuelsaad, Karthik Vikram... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. Mo' Models, Mo' Problems: How to best select model pools when designing Multi-Agent Systems
Authors: Sara Vera Marjanović, Jiacheng Xu, Aleksandr Laptev... Published: 2026-09-15 | Citations: 0 arXiv | PDF
🦾 ROBOTICS
1. XPACE: Joint World and Action Modeling from Heterogeneous Experience
Authors: Jiacheng Wei, Jerry Bai, Xiaoyu Yue... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. Residual Fault Adaptation for Dexterous In-Hand Manipulation Under Runtime Joint Faults
Authors: Linan Deng, Xing Liu, Lin Hong... Published: 2026-09-15 | Citations: 0 arXiv | PDF
3. FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence
Authors: Yinhao Li, Weixin Mao, Zihan Lan... Published: 2026-09-15 | Citations: 0 arXiv | PDF
💻 COMPUTE
1. FlashVector: Agent for Hierarchical Model Serving Stack Optimization
Authors: Qi Wu, Lohan Lemire, Kai Meng... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. Quantum Compiler Design for Fault-Tolerant Quantum Computing
Authors: Chenghong Zhu, Jiahan Chen, Keming He... Published: 2026-09-15 | Citations: 0 arXiv | PDF
3. OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design
Authors: Jiangrui Yu, Ye Yu, Si Chen... Published: 2026-09-15 | Citations: 0 arXiv | PDF
⚡ ENERGY
1. Bridging powder and multi-crystal diffraction with basis-adaptive texture tomography
Authors: Martin Sæbye Carøe, Mads Allerup Carlsen, Felix Tristan Frankus... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. Probabilistic Deep Learning Framework for Phase Transformation Forecasting aided by In Situ High temperature Microscopy
Authors: Ioannis Kouroudis, Niki Balestrieri, Stefan Rotzsche... Published: 2026-09-15 | Citations: 0 arXiv | PDF
3. Higher order anharmonicity and polymorphism in the lattice thermal conductivity of transition metal dichalcogenides
Authors: Marta Loletti, Qi Ren, Zhuyao Chang... Published: 2026-09-15 | Citations: 0 arXiv | PDF
🏥 HEALTHCARE
1. CareMirror: Bringing Caregiver Wellbeing into the Dementia Care Ecosystem
Authors: Jiayue Melissa Shi, Ethan Nguyen, Drishti Goel... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. GPCR Ligand Bioactivity Prediction with Physics-Informed Dual-State Query Learning
Authors: Shuo Zhang, Huifeng Zhang, Rongqi Hong... Published: 2026-09-15 | Citations: 0 arXiv | PDF
3. SaltyMeta: a curated benchmark and protein language model-informed web tool for salty peptide prediction
Authors: Wanchao Chen, Wen Li, Yanan He... Published: 2026-09-15 | Citations: 0 arXiv | PDF
🔬 MATERIALS
1. Designing Homogeneous Ti-Nb-Fe-Sn $β$ Titanium Alloys by PBF-LB: A Pre-Alloyed Powder Blend Strategy
Authors: João Felipe Queiroz Rodrigues, Kristína Bartha, Mariano Casas-Luna... Published: 2026-09-15 | Citations: 0 arXiv | PDF
2. Enhanced thermal stability of SiGeSn by suppressing surface-mediated degradation
Authors: Anis Attiaoui, Sebastien Koelling, Lu Luo... Published: 2026-09-15 | Citations: 0 arXiv | PDF
3. Probing proximity-induced superconductivity in bilayer graphene using gate-defined quantum dots
Authors: Philipp Schmidt, Mathies Funke, Till Tenger... Published: 2026-09-14 | Citations: 0 arXiv | PDF
🔥 GitHub Trending
1. hypit-ai/hypit
⭐ 5597 stars | TypeScript
Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
agentic-ai ai ai-agents ai-video compiler dsl
2. bojieli/ai-infra-book
⭐ 3808 stars | Python
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
accelerator ai-infra ai-infrastructure book datacenter-network deepseek
3. Leonxlnx/unlazy
⭐ 3396 stars | JavaScript
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded
ai-agents claude claude-code llm productivity prompt-engineering
4. truespar/paddock
⭐ 91 stars | Rust
Native Rust inference server for open models on NVIDIA GPUs. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio
ai aimodels blackwell cuda inference inference-engine
5. JakeATX/llamAmpere
⭐ 85 stars | C++
llama.cpp fork for significantly improved performance on Ampere (especially RTX 3090 / 3090 Ti): TurboQuant KV cache, MTP speculative decoding with a 64K draft-vocabulary shortlist, custom SM86 + Qwen
ampere consumer-gpu cuda ggml gguf kv-cache-quantization
Generated by Research Pulse on 2026-09-16 06:14