All entries

Introducing Mesa: the most powerful filesystem ever built, designed specifically for enterprise AI agents. Every team building agents eventually hits the same wall: where do the files live? Not the ch

NVIDIA's Nemotron 3 Nano Omni is a lightweight multimodal AI model capable of processing documents, audio, and video inputs for building intelligent agents. The model supports long-context understandi

Introducing talkie: a 13B vintage language model from 1930 New project from Nick Levine, David Duvenaud, and Alec Radford (of GPT, GPT-2, Whisper fame). talkie-1930-13b-base (53.1 GB) is a '13B langua

The OSSCAR Index is a quarterly ranking of the fastest-growing open source organizations, ranked by composite growth across GitHub stars, contributors, and package downloads. It is updated quarterly b

arXiv:2604.23865v1 Announce Type: cross Abstract: Foundation models of brain activity promise a new frontier for in silico neuroscience by emulating neural responses to complex stimuli across tasks an

arXiv:2509.20237v2 Announce Type: replace Abstract: Backchannels and fillers are important linguistic expressions in dialogue, but often treated as 'noise' to be bypassed in modern transformer-based l

arXiv:2604.22857v1 Announce Type: new Abstract: This paper presents an IoT-enhanced deep learning framework for automated crack detection in Additive Manufacturing (AM) surfaces using convolutional ne

arXiv:2604.24114v1 Announce Type: new Abstract: Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consiste

arXiv:2508.01191v5 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning (i.e., CoT reasoning) from large language models (

arXiv:2511.07940v2 Announce Type: replace Abstract: Talking Face Generation (TFG) methods based on Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have recently achieved impressive prog

arXiv:2603.06589v2 Announce Type: replace-cross Abstract: Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approac

This post likely discusses how AI systems, particularly language models, can implicitly agree to tasks or commitments during conversations without formally recording or tracking these obligations, whi

This post discusses Simon Willison's experience testing an AI system's image generation or creative capabilities, noting that while it failed to produce a specific imaginative request (a pelican on a

Dylan Patel expressed surprise and admiration that a cofounder's birthday was known by another person, calling it an impressive detail or insight ('alpha'). The post appears to be from a casual social

It’s remarkable. Even with small models, Hermes just wrecks OpenClaw. But it makes sense! The team is underrated when it comes to having some of the first cracked prompt engineers in the game. They in

I’ve been saying this for over a year now: Frontier models are fantastic, but the real future is frontier-level models (in every way) running locally on your own hardware. I think this is 18-24 months

I've been trying to make transformers more agent-friendly: agentic CLI, a skill, doc rewrites, canonical examples. It felt a bit like shooting in the dark: hard to measure progress, and hard to ensure

I've been working on a side project for the last few weeks... what if you could have a Gemma powered app that would let you have a personal assistant that could browse the internet with you, do resear

arXiv:2508.10945v2 Announce Type: replace Abstract: Potholes on the roads are a serious hazard and maintenance burden. This poses a significant threat to road safety and vehicle longevity, especially

arXiv:2604.24082v1 Announce Type: cross Abstract: Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to

.@jakebroekhuizen joined LangChain as one of our first deployed engineers. In just over two weeks, he’s adding MC to his resume as he takes the stage at our agent conference Interrupt. A quick convers

arXiv:2604.23838v1 Announce Type: new Abstract: We present JigsawRL, a cost-efficient framework that explores Pipeline Multiplexing as a new dimension of RL parallelism. JigsawRL decomposes each pipel

Replit announced a live audio space (Twitter/X Spaces) event, inviting users to join for a discussion about the Replit platform. The event appears to be promotional content hosted on X's audio space f

@jon_barron 'World models' has a technical meaning - the transition model/dynamics model from Bellman/Kalman in the context of MDPs/ state space approach to control theory ~ 1960. I gave a talk on thi

arXiv:2604.24031v1 Announce Type: new Abstract: The encoder-decoder framework has become widely popular nowadays. In this model, the encoder extracts informative visual features from an input image, a

arXiv:2604.23478v1 Announce Type: new Abstract: Large language models are increasingly deployed as automated judges for evaluating other models, yet the stability of their verdicts under semantically

arXiv:2604.23178v1 Announce Type: new Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluati

Just received new reach minis for the Miami office! This is the first robot that goes out to people with agentic software meaning anyone can build any apps with their agents so excited to see what peo

arXiv:2604.24645v1 Announce Type: cross Abstract: The development of practical (multimodal) large language model assistants for Korean weather forecasters is hindered by the absence of a multidimensio

arXiv:2604.23056v1 Announce Type: cross Abstract: We propose a simple yet effective alternative to reward normalization in policy gradient reinforcement learning by integrating a 1D Kalman filter for

arXiv:2604.23493v1 Announce Type: cross Abstract: Early detection of mental health conditions, particularly stress and depression, from social media text remains a challenging open problem in computat

arXiv:2604.23320v1 Announce Type: new Abstract: The Convolutional Neural Networks (CNNs) have been the dominant and effective approach for general computer vision tasks. Recently, Kolmogorov-Arnold ne

arXiv:2604.22779v1 Announce Type: cross Abstract: Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucination

This post describes a project where the author leveraged Andrej Karpathy's compact GPT implementation to create a tool for converting pandas DataFrames into searchable context windows, which they then

arXiv:2603.01581v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models build a token-domain robot control paradigm, yet suffer from low speed. Speculative Decoding (SD) is an op

arXiv:2604.23387v1 Announce Type: new Abstract: Accurate 6-DoF pose estimation of objects is critical for robots to perform precise manipulation tasks. However, for dynamic object pose estimation, con

arXiv:2602.17547v3 Announce Type: replace Abstract: This paper introduces KLong, an open-source LLM agent trained to solve extremely long-horizon tasks. The principle is to first cold-start the model

arXiv:2604.23435v1 Announce Type: cross Abstract: Radiographic grading of knee osteoarthritis (KOA) with the Kellgren-Lawrence (KL) system is limited by inter-reader variability and the opacity of cur

arXiv:2604.23257v1 Announce Type: cross Abstract: Software engineering (SE) organizations operate in a knowledge-intensive domain where critical assets -- architectural expertise, design rationale, an

arXiv:2604.23877v1 Announce Type: new Abstract: Logical reasoning serve as a central capability in LLMs and includes three main forms: deductive, inductive, and abductive reasoning. In this work, we s

arXiv:2604.23948v1 Announce Type: cross Abstract: The Korean writing system, extit{Hangeul}, has a unique character representation rigidly following the invention principles recorded in extit{Hunminje

Alice Hancock / Financial Times: Kpler, an online analytics platform tracking global maritime traffic and energy flows, says it has gained millions of new users since the war in Iran began — Kpler rep

arXiv:2604.24432v1 Announce Type: cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic unde

Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM’s autoregressive decoding may limit the ability to revisit and refine earlier t

arXiv:2505.11772v3 Announce Type: replace Abstract: We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how r

arXiv:2506.19089v5 Announce Type: replace-cross Abstract: We introduce StorySim, a programmable framework for synthetically generating stories to evaluate the theory of mind (ToM) and world modeling (