Synthetic Sciences Releases OpenScience: An Open-Source, Model-Agnostic AI Workbench for Machine Learning, Biology, Physics, and Chemistry Research
Synthetic Sciences has released OpenScience, an Apache-2.0 AI workbench for scientific research. It works with any frontier or open-weight model, using your own API keys. It runs the full loop across machine learning, biology, physics, and chemistry. It ships 250+ editable skills and queryable scien...
Training Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards
We build an end-to-end GRPO training workflow that teaches Gemma-3 to reason through GSM8K math problems. We prepare the environment, authenticate with Hugging Face, load Gemma-3, and wrap examples into a reasoning-plus-answer prompt format. We define reward functions for format adherence and numeri...
Scaling Properties of Continuous Diffusion Spoken Language Models
Speech-only spoken language models (SLMs) lag behind text and text-speech models in performance, with recent discrete autoregressive (AR) SLMs indicating significant computational and data demands to match text models. Since discretizing continuous speech for AR creates bottlenecks, we explore wheth...
Revisiting ASR Error Correction with Specialized Models
Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce latency and hallucination concerns. We revisit ASR error corre...
TopoPrimer: The Missing Topological Context in Forecasting Models
We introduce TopoPrimer, a framework that makes the global topological structure of the series population an explicit input to any forecasting model. TopoPrimer improves accuracy across diverse domains, stabilizes forecasts under seasonal demand spikes, and closes the cold-start gap. Precomputed onc...
AI Weekly Issue #511: Anthropic Bet $19B on Compute. Treasury Quietly Said 'Bubble.'
This week the AI buildout stopped being about models and became about balance sheets. Anthropic committed $19 billion to a single data center, SK Hynix raised $28 billion, and SoftBank kept pouring in $87 billion, even as a leaked Treasury draft warned the whole thing rhymes with the dot-com crash. ...
AI Weekly Issue #511: AlphaFold's Nobel Winner Just Joined Anthropic. And 6 More AI Wins.
Look past the data-center megadeals and the bubble headlines, because something quieter happened this week: AI actually delivered. A Nobel laureate joined the AI-for-science push, the open-model frontier got cheaper again, and the first hard evidence landed that an AI tutor can beat the classroom. T...
Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention
Meituan has released LongCat-2.0, a 1.6 trillion-parameter Mixture-of-Experts model that activates about 48 billion parameters per token. It pairs a native 1-million-token context, built on LongCat Sparse Attention, with training and serving run end-to-end on domestic AI ASIC superpods. Here is the ...
Assemble Each RAG Generation Prompt from a Base Prompt Plus the Rules Each Question Needs
Enterprise Document Intelligence [Vol.1 #8B] - A fixed BASE, the rules each question needs, one registry: the dispatcher that turns a parsed question into a typed LLM call
The post Assemble Each RAG Generation Prompt from a Base Prompt Plus the Rules Each Question Needs appeared first on Towards Dat...
PANet Paper Walkthrough: When Feature Pyramids Go Bottom-Up
Understanding how PANet shortens the path between low-level and high-level features
The post PANet Paper Walkthrough: When Feature Pyramids Go Bottom-Up appeared first on Towards Data Science.
LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools
LlamaIndex’s legal-kb is a public reference app that gives agents filesystem-style access to a document knowledge base on Index v2. It exposes retrieve (hybrid semantic search), find, read, and grep as tools, with automatic per-file versioning and visual citations. The stack is TanStack Start, AI SD...
Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines
Anthropic released Claude Science in beta on June 30, 2026. The app runs on existing Claude models. A coordinating agent delegates to domain specialists, a reviewer agent flags and corrects citations and numbers, and every figure ships with its exact code, environment, and full message history. It m...
NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion
A hands-free NVIDIA agent framework hosts each RTL problem as a versioned repository, reaching 100% completion across benchmarks.
The post NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion appeared first on MarkTechPost.
Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination
Enterprise Document Intelligence [Vol.1 #8A] - The schema is the contract: every field is a question the pipeline asks the model, and every answer is checkable
The post Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination appeared first on Towards Data Science.
NVIDIA AI Introduces ASPIRE: A Self-Improving Robotics Framework Reaching 31% Zero-Shot on LIBERO-Pro Long Tasks
NVIDIA's ASPIRE writes and refines robot control programs, then distills validated repairs into a reusable skill library. It gains up to 77 points on LIBERO-Pro and transfers zero-shot to unseen long-horizon tasks.
The post NVIDIA AI Introduces ASPIRE: A Self-Improving Robotics Framework Reaching 31...
Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems
Mistral AI released Leanstral 1.5, a free Apache-2.0 code agent model for Lean 4. It saturates miniF2F and solves 587 of 672 PutnamBench problems. The 119B mixture-of-experts activates 6.5B parameters per token. We break down its architecture, benchmarks, real bug-finding case studies, and deploymen...
AI Quantum Intelligence - Pic of the week (2026-07-03)
A conceptual digital artwork exploring the emotional dimension of technological evolution — where artificial intelligence mourns the fading tactile intimacy of legacy interfaces. The piece contrasts the cold precision of modern AI with the warmth of human‑machine touch, symbolizing the quiet grief o...
LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler
Most "LLM wikis" use agents, embeddings, and repeated model calls to organize local notes. I built a deterministic alternative: a pure Python compiler that turns messy markdown into a linked, linted wiki using only the standard library. Along the way, I fixed two real bugs, benchmarked the pipeline ...
Meet WebBrain: An Open-Source, Local-First AI Browser Agent That Reads Pages and Automates Tasks in Chrome and Firefox
WebBrain is a free, MIT-licensed AI browser agent for Chrome and Firefox. It reads pages, extracts data, and automates multi-step tasks through Ask and Act modes. Run it on local models like llama.cpp or Ollama for privacy, or connect any cloud API.
The post Meet WebBrain: An Open-Source, Local-Firs...
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
arXiv:2607.01278v1 Announce Type: new
Abstract: The research proposes a multilayer Q-matrix-embedded neural network for cognitive diagnosis (M-QCDNet), which integrates the structural interpretability of cognitive diagnostic models (CDMs) with the deep learning neural network (NN). M-QCDNet structu...
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
arXiv:2607.01279v1 Announce Type: new
Abstract: Cross-subject EEG stress detection remains challenging because discriminative stress-related patterns are both subject-dependent and frequency-specific. Conventional Riemannian methods model spatial covariance mainly in the time domain, overlooking ne...