Xberg v1 is out
Hi all, I'm happy to announce that Xberg v1 is out. Xberg is the successor to Kreuzberg, equivalent to what would have been Kreuzberg v5. It's a content intelligence framework that handles a very wide
Knowledge catalogue
Hi all, I'm happy to announce that Xberg v1 is out. Xberg is the successor to Kreuzberg, equivalent to what would have been Kreuzberg v5. It's a content intelligence framework that handles a very wide
among ai leaders i seem to be in the minority in that i am STILL actively using /loop and /goal.... ... and i think all of u guys who stopped using it are wrong - not wrong forever, just giving up on
“Stochastic parrots” is not my term (it’s @emilymbender’s). But a lot of people today commenting on it are confused. To some extent (though I don’t think it’s a perfect metaphor, and have said that be
Ten advances in mathematics and theoretical computer science A few days ago it was Anthropic discovering cryptographic weaknesses with Claude using Mythos Preview, spending 100,000 on tokens and with
arXiv:2607.26069v1 Announce Type: cross Abstract: As AI systems are rapidly integrated into critical economic, governmental, and national security functions, the gap between AI adoption and AI securit
arXiv:2607.17219v2 Announce Type: replace Abstract: Question-order effects in human survey data have been reported to approximately satisfy the QQ (quantum question) equality, a parameter-free predict
arXiv:2607.27953v1 Announce Type: new Abstract: Combinatorial optimization problems (COPs) underpin many real-world decisions, but their exponentially large search spaces make high-quality solutions c
arXiv:2607.27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years. Computationa
arXiv:2607.28496v1 Announce Type: new Abstract: Financial sentiment analysis has become a standard component in news-driven stock prediction, yet it reduces rich, multi-dimensional news articles to a
arXiv:2607.27595v1 Announce Type: new Abstract: Computational approaches to intertextuality have advanced from string matching to neural retrieval, yet their outputs, similarity scores and parallel-pa
arXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanit
The article shows that dense‑attention performance in long‑context inference is governed by group size (query heads per KV head), head dimension, and sequence length, with prefill being compute‑bound
arXiv:2607.26236v1 Announce Type: cross Abstract: AI-generated counterspeech offers a scalable and effective strategy to mitigate online toxicity by promoting more constructive dialogue. Yet, existing
arXiv:2607.28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Se
Release: datasette-agent 0.4a0 New await context.browser_task() mechanism allowing agent tools to run code directly in the user's browser. #33 This is an exciting new capability: it makes it easy for
arXiv:2504.04128v3 Announce Type: replace Abstract: In decision-level fusion tasks involving heterogeneous sources with unequal precision and potential anomalies, evidence deviating from the majority
arXiv:2511.14117v2 Announce Type: replace Abstract: Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotator
arXiv:2607.27248v1 Announce Type: cross Abstract: While large language models excel in reasoning, these generalists often lack knowledge for specialized scientific domains. Conversely, domain models~(
arXiv:2512.03661v2 Announce Type: replace Abstract: Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigat
arXiv:2607.28229v1 Announce Type: new Abstract: The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines
arXiv:2603.05950v2 Announce Type: replace Abstract: Visual token reduction is critical for accelerating Vision-Language Models (VLMs), since visual inputs are represented as token sequences that intro
arXiv:2607.27914v1 Announce Type: new Abstract: Multi-zone variable-air-volume control must balance thermal comfort, indoor air quality, and electricity use across several continuous actuators. Model
arXiv:2607.26076v1 Announce Type: cross Abstract: Retrieval-augmented generation services over mutable enterprise documents repeatedly execute semantically equivalent analysis requests. Answer reuse c
arXiv:2607.28022v1 Announce Type: new Abstract: Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. C
arXiv:2607.27654v1 Announce Type: new Abstract: Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of do
arXiv:2607.28076v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only co
arXiv:2607.27652v1 Announce Type: new Abstract: Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions u
arXiv:2512.01557v3 Announce Type: replace Abstract: This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We evalua
arXiv:2607.27919v1 Announce Type: new Abstract: Decoder-only language models entangle long-term memory and reasoning in a single parameter set, making it difficult to scale memory capacity independent
arXiv:2607.27637v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or sh
arXiv:2607.28312v1 Announce Type: new Abstract: Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches prima
arXiv:2607.28545v1 Announce Type: new Abstract: Large language models can write, patch, and search code, but oncall root cause analysis (RCA) demands something different: reasoning over noisy metrics,
arXiv:2607.27265v1 Announce Type: new Abstract: Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Pla
arXiv:2607.27574v1 Announce Type: new Abstract: Activation steering has emerged in large language models as a lightweight alternative for dynamically changing a model's behavior at inference time. How
arXiv:2607.28227v1 Announce Type: cross Abstract: GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision a
arXiv:2607.27692v1 Announce Type: new Abstract: Top-K sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries. However, identi
arXiv:2602.04635v2 Announce Type: replace Abstract: Robots are finding wider adoption in human environments, increasing the need for natural human-robot interaction. However, understanding a natural l
arXiv:2607.28008v1 Announce Type: new Abstract: Representation engineering reads and steers capability directions in large language models, yet methods are typically evaluated on paper-specific synthe
arXiv:2607.28525v1 Announce Type: new Abstract: Many real-world graphs support multiple predictive tasks over the same underlying structure, creating an opportunity to reuse supervision across node cl
arXiv:2607.28098v1 Announce Type: cross Abstract: Scientific datasets are commonly organized as hierarchical repositories containing heterogeneous and interdependent files, making their inspection, in
arXiv:2607.27955v1 Announce Type: cross Abstract: Scientific processes are often described in heterogeneous article discourse, with details needed for comparison, reproducibility, reuse, and automatio
arXiv:2607.27790v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) aims to interpret complex human emotions by integrating natural language with non-verbal modalities. Non-verbal moda
smevals - a small eval suite for evaluating models, prompts, and harnesses I've been working with Jesse Vincent's Prime Radiant applied AI research lab building out this evals framework to help answer
arXiv:2607.27536v1 Announce Type: cross Abstract: Learning a strategic task changes more than what is directly taught: fine-tuning on one game can either enhance or degrade an agent's ability to reaso
arXiv:2607.28498v1 Announce Type: cross Abstract: Scientific hypothesis generation for AI for Science typically involves Scientific Inspiration Retrieval (SIR) followed by hypothesis composition. Exis
arXiv:2607.27528v1 Announce Type: cross Abstract: Threat modeling is essential for secure software development, yet manual analysis of cloud-native architectures is slow and demands scarce security ex
arXiv:2505.12507v2 Announce Type: replace Abstract: Despite the success of machine-generated text detectors, the black-box nature remains a critical limitation. Traditional explainability methods rely
arXiv:2607.28263v1 Announce Type: new Abstract: Transformer depth is not used uniformly: lower and middle layers build semantic representations, while upper layers increasingly specialize them for pre
arXiv:2607.27292v1 Announce Type: new Abstract: The rise of powerful, accessible image-editing models such as FLUX.2 has brought high-fidelity editing within broad reach. Their capabilities now extend
arXiv:2607.26935v1 Announce Type: new Abstract: Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation,
arXiv:2607.26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation mod
Hi, I'm trying to replicate a thing locally, that I can do on ChatGPT. What I want is to give a local AI two reference images (a face and a background item) and a prompt about the composition of the p
Hello together I decided to go with 2× Radeon AI PRO R9700 GPUs (64 GB total VRAM) for my local AI server. However, I keep reading that AMD/ROCm is still not as mature as NVIDIA/CUDA when it comes to
Advancing the price-performance frontier with GPT‑5.6 Huge price drop from OpenAI today: GPT-5.6 Terra got a 20% reduction, and GPT-5.6 Luna got a massive 80% drop. OpenAI credit 5.6 Sol with enabling
arXiv:2510.20535v2 Announce Type: replace Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Co
arXiv:2607.26596v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified tran
arXiv:2603.07131v4 Announce Type: replace Abstract: Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hinde
arXiv:2607.26178v1 Announce Type: new Abstract: Turn-taking is a central component of full-duplex interaction. Which turn-taking behaviors are appropriate varies with the scenario, yet current models
arXiv:2607.26490v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance
arXiv:2607.26618v1 Announce Type: cross Abstract: Federated PEFT enables LLMs to collaboratively adapt to decentralized private data without sharing raw examples. However, task heterogeneity across cl