🔬 Research Pulse
Daily Digest
September 29, 2026
🤖 AI
🧠 LLMs
1. Can LLMs Value the Right Evidence? Evidence-Value Misalignment in Dynamic Medical Diagnosis
Authors: Kehua Feng, Yunsheng Lu, Yitong Qiao... Published: 2026-09-28 | Citations: 0 arXiv | PDF
👁️ Vision
1. FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching
Authors: Thanh-Long V. Le, Steven Walton, Seunghyun Yoon... Published: 2026-09-28 | Citations: 0 arXiv | PDF
2. FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References and Proactive Agent Planning
Authors: Ziyao Huang, Zhengkun Rong, Shiyang Qin... Published: 2026-09-28 | Citations: 0 arXiv | PDF
💻 COMPUTE
1. A Si-on-SiC Platform for Interfacing with Vanadium Dopants in the Telecom O-Band
Authors: Timothy Draher, Nolan Bitner, Vasileios Niaouris... Published: 2026-09-28 | Citations: 0 arXiv | PDF
2. Electrothermal behavior of superconducting nanowires buried in a commercial CMOS process
Authors: Mohamed Gharib, Leonid Popryho, Salma Abdelzaher... Published: 2026-09-28 | Citations: 0 arXiv | PDF
3. Induced Coherence in Quantum and Classical Interferometry: Origin and Control
Authors: Balakrishnan Viswanathan, Ravi Kamal Pandey, Devendra Kumar Mishra... Published: 2026-09-28 | Citations: 0 arXiv | PDF
🔬 MATERIALS
1. Improving the critical current density of the $\mathrm{V}{0.59}\mathrm{Ti}{0.40}\mathrm{Ce}_{0.01}$ alloy superconductor through successive cold-working and annealing at different temperatures
Authors: Asi Khandelwal, SK. Ramjan, Basudev Padhi... Published: 2026-09-28 | Citations: 0 arXiv | PDF
2. Pressure-induced s,p-d electron redistribution accompanies structural transformation in amorphous Zr-Cu alloy under compression
Authors: P. Dziegielewski, J. Antonowicz, K. Georgarakis... Published: 2026-09-28 | Citations: 0 arXiv | PDF
3. Pyroelectric thermo-wave probing of BaZr0.2Ti0.8O3 ceramics
Authors: Nicholas V. Morozovsky, Yuriy O. Zagorodniy, Mykola Yelisieiev... Published: 2026-09-28 | Citations: 0 arXiv | PDF
🔥 GitHub Trending
1. NandhaKishorM/laya
⭐ 28195 stars | Python
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per reque
calibration classification decision-model huggingface jev modernbert
2. hypit-ai/hypit
⭐ 17450 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
3. trailhq/Graft
⭐ 9395 stars | TypeScript
Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.
ai-agents anthropic claude-code cli code-graph codex
4. FareedKhan-dev/kimi-k3-in-c
⭐ 8792 stars | C
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
avx2 c99 cpu-inference deep-learning from-scratch inference-engine
5. deeplethe/utopia
⭐ 7980 stars | Rust
World's first open-source enterprise world model.
agent-memory bitemporal graphrag knowledge-base knowledge-graph llm
6. Human-Agent-Society/reef
⭐ 7223 stars | Python
Infrastructure for continually self‑improving agents
agent-infrastructure ai-agents continual-learning inference llm llm-training
7. jev-chat/jev-chat-jarvis
⭐ 7071 stars | Kotlin
装在手机上的对话副驾：在 QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。
accessibility-service android chat-assistant llm qq
8. drumih/turbo-fieldfare
⭐ 6841 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
9. mizorewww/laya-mlx
⭐ 6615 stars | Python
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
apple-silicon decision-model inference laya local-ai machine-learning
10. bojieli/ai-infra-book
⭐ 5603 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
11. kirodotdev/KiroCrew
⭐ 4197 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
12. synthetic-sciences/openscience
⭐ 3836 stars | TypeScript
The open-source AI workbench for scientific research
agent ai ai-agent ai-scientist bioinformatics bun
13. syv-ai/HyperQwen
⭐ 1759 stars | Python
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 1
consumer-gpu cuda inference-optimization kv-cache llm-inference local-llm
14. Tencent-Hunyuan/AuK
⭐ 1407 stars | Python
AuK: An Open-Source Foundational Model for Speech Generation and Editing
deep-learning foundation-models python pytorch separation speaker-extraction
15. datawhalechina/zero-to-sglang
⭐ 1335 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
Generated by Research Pulse on 2026-09-29 06:11