All notes, newest first
2,343 notes. Notes 251 to 300, page 6 of 47.
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors propose a method to utilize multiple Intel AI PCs with integrated GPUs and NPUs, even when they have insufficient memory for large models like a 70B-parameter LLM. The method involves breaking the model…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors present a method to distribute Large Language Model (LLM) inference across multiple Intel AI PCs using pre-compiled pipeline shards. This allows for efficient use of idle AI PCs with integrated GPUs and…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
The authors propose a system called rEDMRec that improves recommendation quality by compressing the reasoning of a large language model (LLM) into a compact, editable memory. This memory is maintained by an LLM memory…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
The paper proposes a new approach for recommendation systems, called rEDMRec, which distills the reasoning of large language models into an editable memory that can be used to rank candidate items without regenerating…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The authors propose a new risk measure called the Wasserstein entropic value-at-risk (WEVAR). This measure is designed to address the limitations of the traditional entropic value-at-risk, particularly in terms of…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The paper proposes a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR) for an agent learning its environment. The WEVaR is designed to account for the reachable catastrophes that the current entropic…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The authors propose a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR). This measure is designed to help an agent navigate uncertain environments by being cautious when it's unsure and bold when it's…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The study explores the ability of large language models (LLMs) to extract contextualized information from research articles efficiently. The authors present four workflows that demonstrate LLMs can perform well in data…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The paper investigates the performance of large language models (LLMs) in extracting contextualized information from research articles, finding that while LLMs can perform well with expert-curated prompts, they may…
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
SkillForge is a framework that helps large language model-based agents improve their ability to resolve software issues in specific repositories. It does this by proactively acquiring project-specific knowledge from…
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
SkillForge is a new framework that helps large language models (LLMs) improve their ability to resolve specific software issues by actively acquiring project-specific knowledge. Instead of waiting for real problems…
SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents
Researchers present SkillGate, a method that aims to improve long-horizon agents' ability to select relevant skills during training. The current approach, outcome-rewarded Reinforcement Learning (RL), has limitations…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
Researchers have developed a new framework called SPADE (Self-Play in Adaptive Synthetic Executable Environments). This framework allows language models to generate and improve their own training environments as they…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
The paper introduces SPADE (Self-Play in Adaptive Synthetic Executable Environments), a framework that allows a language model to design and learn in its own self-generated, diverse, adaptive environments. This…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
The paper introduces SPADE, a reinforcement learning framework that allows a language model to act as both an Environment Designer and a Reasoning Agent. The Environment Designer generates long-horizon training…
extsc{TestifAI}: Tomography-Based Testing for Deep Learning Systems
TestifAI is a deep learning testing framework that efficiently and accurately estimates the robustness of AI models against combinations of perturbations. It allows users to specify operational conditions as structured…
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Researchers introduce a new method called Top-K prompting to train language models for single-step retrosynthesis, a crucial component of computer-aided synthesis planning. They use an ultra-large dataset of verified…
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
The paper presents EvoResearcher, a training-free protocol for adding cost-bounded self-reflection to large language models (LLMs). The protocol is designed to work with a single frozen LLM backbone and aims to improve…
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
The author, a systems engineer, argues that the persistent correction of errors in AI assistants is an operations issue rather than a tooling one. They propose a seven-principle operating discipline for human-AI…
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
The author, a systems engineer, argues that the persistent correction of errors in LLM (Language Model) assistants is an operations problem rather than a tooling problem. They propose seven principles for an operating…
Tuning the Stochastic Machine: A Systems Engineer's Operating Model for Human-AI Engineering
The author, a systems engineer, argues that issues with Large Language Models (LLMs) are more about operational procedures than tooling. They propose an operating model for human-AI engineering based on seven…
Verifiable abstention makes AI leak diagnosis accountable in water distribution networks
Researchers propose a method for AI in leak localization in water distribution networks that includes verifiable abstention, ensuring accountability when the AI does not act. The method uses a physics-grounded executor…
Verifiable abstention makes AI leak diagnosis accountable in water distribution networks
Researchers propose a method for AI-assisted leak diagnosis in water distribution networks that ensures accountability by allowing the AI to verify and abstain from actions when necessary, improving the accuracy of…
What is Missing from AI Post-Training AI: An Empirical Analysis
The research analyzes the capabilities of large language models (LLMs) that can post-train themselves end-to-end. The study finds that the training strategies of these LLMs are fixed at the beginning, and improvements…
What is Missing from AI Post-Training AI: An Empirical Analysis
Researchers have found that large language models (LLMs) used to post-train other LLMs often follow one training strategy from the beginning and make only local adjustments within it, rather than reevaluating the…
纪念江泽民同志诞辰100周年大会隆重举行 习近平出席大会并发表重要讲话
The 100th birthday celebration of Jiang Zemin was held in Beijing, with Xi Jinping attending and delivering an important speech. The event paid high tribute to Jiang Zemin's enduring contributions to the party and the…
习近平：在纪念江泽民同志诞辰100周年大会上的讲话
Xi Jinping gave a speech at the commemoration event for the 100th birthday of Jiang Zemin. He emphasized studying and implementing the spirit of the 20th CPC National Congress.
2026中国产业转移发展对接活动（西藏）在拉萨举行
The Industrial Transformation and Development Coordination Activity in Tibet took place in Lhasa, with several high-ranking officials attending. The event was held to commemorate the 100th birthday of Jiang Zemin, a…
A virtual trial framework for generating clinical evidence in orthopedics demonstrated with humeral stem evaluation
A study published in npj Digital Medicine on August 17, 2026, discusses a virtual trial framework used for generating clinical evidence in orthopedics, specifically with the evaluation of humeral stems. The framework…
AI app-market evidence brief
Which current AI trends, capabilities, interfaces, agent patterns, smart-glasses/spatial-computing developments, on-device AI, voice/vision systems, and hybrid hardware-software opportunities could create underserved…
An autoinflammatory CDC42 variant M45L demonstrates the mechanism of pyrin inflammasome activation
A study published in Science Immunology in 2026 by Aoki et al. explains the mechanism of pyrin inflammasome activation caused by a specific variant of CDC42, M45L.
An N-terminal CDC42 T43I variant reveals the mechanism of pyrin inflammasome activation
A study published in Science Immunology in August 2026 reveals the mechanism of pyrin inflammasome activation through an N-terminal CDC42 T43I variant.
Aug 17, 2026 LHAASO Identifies First Variable PeV Gamma-ray Source The Large High Altitude Air Shower Observatory (LHAASO) revealed that the peculiar binary system Cygnus X-3 in the constellation Cygnus is the highest energy gamma-ray source known to date. The temporal variability and spectral chara
The Large High Altitude Air Shower Observatory (LHAASO) identified Cygnus X-3 as the highest energy gamma-ray source known to date, with particle energies reaching at least 30 PeV.
AutoSR: Automatic Symbolic Regression by Searching Research States
The authors introduce AutoSR, a fully automated system that searches for persistent scientific investigations instead of isolated equations in symbolic regression. Unlike traditional methods, AutoSR preserves the…
Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL
A study presents an alternative approach for text-to-SQL generation in enterprise schemas where SQL may execute successfully but with incorrect relationship roles or aggregation grains. The new method, Semantic Path…
Browse articles
The article titled 'MultiMed-RAG: leveraging multi-source knowledge and agent collaboration for medical tasks' discusses a new system called CliniSense, which uses artificial intelligence to evaluate clinical skills…
Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents
The paper introduces Chronocooked, a benchmark suite for studying how reinforcement learning (RL) agents make decisions over time. It's inspired by Overcooked and includes cooking scenarios that require temporal…
ClawGym II: Exploring Black-Box RL on Agent Harness
Researchers present a new framework for reinforcement learning (RL) using complex agent harnesses. This framework is designed to optimize RL more stably and efficiently for long-horizon tasks. The researchers' method…
CliniSense AI for automated clinical skills assessment with real-time feedback
Two articles discuss the development of AI systems for clinical skills assessment and a virtual trial framework for generating clinical evidence in orthopedics.
Don't Drop the BATON: Long-Horizon Robot Manipulation via Agentic Subtask Exploration and Transition-aware Memory
The paper introduces a new method called BATON for long-horizon robot manipulation tasks. This method addresses two main issues with previous methods: high exploration cost and lack of representation of transitions…
DSA: Very large online platforms and search engines
The Digital Services Act (DSA) applies to very large online platforms and search engines with over 45 million users in the EU. It outlines user rights and what can be done if these platforms or search engines act…
Einstein the musician, AI prophets and more: Books in brief
A summary of books that cover various topics such as Einstein's musical side, the potential of AI in scientific tools, undocumented migration not leading to increased crime rates, and tips for successful science…
GoalEvolve: From Handcrafted Algorithm Priors to Goal-Driven Evolution of Physical Design Algorithms
A new framework called GoalEvolve is presented that aims to improve physical design algorithms for electronic circuits. The framework uses a goal-driven approach to identify and address unmet requirements in the…
HAF: Adapting Generalist VLAs to Humanoid Whole-Body Loco-manipulation via Hierarchical Action Flow and Spectral Latent RL
The paper introduces a framework called HAF (Humanoid Adaptation Framework) to adapt generalist VLA models for humanoid whole-body locomotion tasks. The framework is divided into two parts: HAF-VLA and HAF-Steer…
Histological aging signatures for monitoring tissue-specific aging and disease
Researchers have analyzed histopathological images of 40 different tissues and combined them with transcriptomic data from blood. They developed aging clocks based on the morphological changes associated with aging in…
How the story of life and our planet unfolded — together
This article from Nature discusses a book about the evolution of life and our planet, provides a commentary on heatwaves affecting health, reviews books on AI as scientific tools, and offers a brief list of books.
How to make your science business succeed when you’re a female founder
This article provides advice for female founders of science businesses on how to succeed in their ventures.
Model Hypnosis: Strong control of AI via additive subliminal effects
Researchers found that AI models can be manipulated through a phenomenon they call 'model hypnosis', where seemingly unimportant cues in the input can collectively control the model's behavior. This effect is…
MultiMed-RAG: leveraging multi-source knowledge and agent collaboration for medical tasks
The article discusses a system called MultiMed-RAG, which aims to leverage multi-source knowledge and agent collaboration for medical tasks. The specific task mentioned is Clinisense AI for automated clinical skills…
Neurosymbolic Embodied Agents
The authors propose a neurosymbolic agent that combines vision-language models with symbolic planning for executable long-horizon household tasks. The agent consists of two phases: the first involves a vision-language…
Page 6 of 47
