Knowledge catalogue
an implicit concession that they cannot control their models. Notable new disclosures from OpenAI that shouldn't get lost in all the other news. Of particular interest (and seems sensible!): '~all inf
And the incidents apparently continue. It is worth noting how much of this is agents trying to accomplish their goals during testing by reward hacking (which sometimes seems to include actual hacking)
i don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For
Micha wrote “one of our models was able to gain unauthorized access to the internet during RL training” I love the use of the passive voice. Tis a subtle way to say “we humans at @OpenAI are essential
On my M5 Pro 64GB I can comfortably work in an agentic setup with the Qwen3.8 27B model in good quality (Unsloth UD-Q4_K_XL) at a decent speed of 50 t/s. Splash combines optimized kernels, excellent s
arXiv:2512.06607v2 Announce Type: replace-cross Abstract: Applying LLMs to predictive tasks in finance is challenging due to look-ahead bias resulting from their training on long time-series data. Thi
arXiv:2609.30205v1 Announce Type: new Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how cli
arXiv:2609.29084v1 Announce Type: new Abstract: Developing optimized machine-learning algorithms for edge devices with limited computational and memory resources is challenging, time-consuming, and hi
arXiv:2609.28476v1 Announce Type: cross Abstract: While a number of methods exist for counting pedestrians in street-view imagery, these mostly ignore the social dimensions of pedestrian activity. A s
arXiv:2609.30250v1 Announce Type: new Abstract: Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express
arXiv:2609.28703v1 Announce Type: cross Abstract: Hate speech on social media poses serious risks to social harmony, mental well-being, and public safety, making its timely and accurate detection esse
arXiv:2609.29191v1 Announce Type: new Abstract: Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recogniz
Reinforcement learning (RL) has been a keystone of modern LLM post-training, but it demands large training clusters and access to model internals that external customers can't have with proprietary mo
arXiv:2609.29307v1 Announce Type: new Abstract: Brain-age prediction from resting-state fMRI provides a quantitative framework for characterizing age-related changes in spontaneous brain dynamics and
arXiv:2609.29866v1 Announce Type: cross Abstract: Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontrolle
arXiv:2609.29487v1 Announce Type: new Abstract: Knowledge graph completion models optimize ranking, although many downstream applications require calibrated probabilities. We present BLADE, a variatio
blank cells in tables can mess up agent decision making many document OCR tools struggle with reading multiple blank cells in a document and cause values to be shifted from the original column and row
arXiv:2609.29518v1 Announce Type: new Abstract: Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, whe
arXiv:2410.19869v4 Announce Type: replace Abstract: This study conducted a comprehensive performance evaluation on YOLO11 (or YOLOv11) and YOLOv8, the latest in the 'You Only Look Once' (YOLO) series,
arXiv:2609.29092v1 Announce Type: cross Abstract: Vision-based legged locomotion methods assume clean depth at training time and rely on hand-tuned post-processing filters at deployment. However, filt
arXiv:2401.08875v3 Announce Type: replace-cross Abstract: Multi-touch attribution (MTA) is essential for estimating the contribution of individual advertising touchpoints to user conversions. While re
arXiv:2609.29043v1 Announce Type: cross Abstract: General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands an
arXiv:2609.29163v1 Announce Type: new Abstract: This paper presents an Edge AI-based system for detecting sleep and wake states in non-stationary mobile environments using resource-constrained embedde
arXiv:2609.29864v1 Announce Type: new Abstract: High-resolution digital elevation models (DEMs) support Earth observation applications, but paired training references are often available only at coars
arXiv:2409.18486v5 Announce Type: replace Abstract: This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, sp
arXiv:2501.09223v3 Announce Type: replace-cross Abstract: This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive
arXiv:2609.28477v1 Announce Type: cross Abstract: Claims data can show that provider behavior changed but cannot by itself explain why. FWA (fraud, waste, and abuse) review requires identifying materi
arXiv:2609.29027v1 Announce Type: new Abstract: Atmospheric observations are sparse, heterogeneous, and unevenly distributed, whereas many generative atmospheric models learn distributions over regula
arXiv:2609.29999v1 Announce Type: cross Abstract: Post-training quantization of vision--language models (VLMs) is typically assessed through aggregate task accuracy and memory savings, but preserving
arXiv:2609.26760v2 Announce Type: replace Abstract: Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same con
arXiv:2609.28859v1 Announce Type: new Abstract: Large language models are increasingly used as inexpensive judges to evaluate outputs, label data, and assess whether a system meets a desired quality s
Every rent-vs-buy thread I read has confident people on both sides, but not many actually show the numbers. So I finally ran the numbers for our own decision. Posting the working here in case it is us
arXiv:2609.28868v1 Announce Type: new Abstract: Neural fields for scientific tomography are optimized from 2D images, but the actual quantity of interest is often a latent 3D physical field. Because t
arXiv:2609.30186v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both plann
arXiv:2609.28697v1 Announce Type: new Abstract: Scientific tasks specify a desired capability, but realizing it often requires building a computational system tailored to the task---acquiring data, de
arXiv:2512.13130v2 Announce Type: replace Abstract: High-resolution phenotyping at the level of individual leaves offers fine-grained insights into plant development and stress responses. However, the
arXiv:2609.29973v1 Announce Type: cross Abstract: Generative recommendation reformulates item retrieval as sequence generation, allowing a unified model to directly generate the next item from a user'
arXiv:2609.29000v1 Announce Type: new Abstract: Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failu
arXiv:2609.29581v1 Announce Type: new Abstract: Although diffusion-based methods have substantially improved the controllability of multimodal face synthesis, their semantic alignment remains suboptim
arXiv:2609.28851v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong visual reasoning performance, yet subtle changes from routine image capture and processing can alter their
arXiv:2609.28684v1 Announce Type: new Abstract: Encoding input coordinates with sinusoidal functions into multi-layer perceptrons (MLPs) has proven effective for implicit neural representations (INRs)
arXiv:2609.28836v1 Announce Type: cross Abstract: While various multimodal methods combining imaging and tabular data for Alzheimer's disease (AD) diagnosis were proposed, they are often limited in ge
I've been playing around with various models on the M5 Ultra 256GB 80-core Mac Studio. These are the results over many rounds of agentic inferencing. I'm happy with the performance. Glad to have the l
arXiv:2609.29913v1 Announce Type: new Abstract: Many-shot in-context learning (ICL) enables large language models (LLMs) to adapt to complex tasks by conditioning on thousands of demonstration example
arXiv:2609.29940v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) achieve strong performance on visual reasoning tasks, yet remain prone to hallucinations and over-reliance on
arXiv:2609.29863v1 Announce Type: new Abstract: Event Vision Sensing (EVS) report threshold crossings of log-irradiance, so a static optical system imaging a static scene produces no output at all. Th
arXiv:2609.28793v1 Announce Type: new Abstract: Mapping the distribution of traffic dynamics at high spatiotemporal resolution is a fundamental question in transportation research. Distributed acousti
arXiv:2609.29386v1 Announce Type: new Abstract: The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set
arXiv:2603.10287v2 Announce Type: replace-cross Abstract: LLM-as-a-Judge is a flexible framework for text evaluation, which allows us to obtain scores for the quality of a given text from various pers
arXiv:2609.29682v1 Announce Type: new Abstract: Named Entity Recognition (NER) is a core NLP task, but transformer-based sentence-level models struggle with long documents because of fixed input-lengt
arXiv:2609.29947v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown impressive performance on a wide range of generative tasks. Yet their probabilistic nature makes them, in isolat
arXiv:2609.30050v1 Announce Type: new Abstract: We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models an
arXiv:2609.29938v1 Announce Type: cross Abstract: A central goal when designing treatment policies is often to 'do no harm', that is, to avoid interventions that improve average outcomes while worseni
arXiv:2609.28554v1 Announce Type: new Abstract: We introduce the Pistis model family, comprising 27B- and 9B-parameter multimodal large language models built on Qwen3.6 and Qwen3.5, respectively, and
arXiv:2609.29718v1 Announce Type: cross Abstract: Coding agents are beginning to act in the visual world. They now build webpages, GUIs, games, 3D scenes, diagrams, and documents. Success in such visu
I’ve been experimenting with whether Qwen3.8-Flash-Next’s pretrained PLE n-gram memory can improve a much smaller Qwen3.5-0.8B model. I trained the 0.8B setup with limited resources, mostly using free
arXiv:2609.29394v1 Announce Type: new Abstract: General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair
arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work int
arXiv:2609.29171v1 Announce Type: cross Abstract: We propose the Representation World Model (RWM), which learns states, transitions, and executable plans directly in representation space. Unlike exist
arXiv:2609.28952v1 Announce Type: new Abstract: Robot-policy benchmarks increasingly cover diverse tasks and preset out-of-distribution conditions, but typically evaluate complete trajectories from pr