Knowledge catalogue
arXiv:2609.29781v1 Announce Type: new Abstract: Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claime
Would be interesting right? Models are starting to score higher and higher on benchmarks like Parametric CAD Bench, but can they pass an actual exam? The Certified SOLIDWORKS Associate (CSWA) exam mig
arXiv:2609.28601v1 Announce Type: cross Abstract: Machine-learning (ML) emulators for atmospheric processes have advanced rapidly in recent years, transforming weather forecasting. Although early ML o
holy fucking shit the openai rogue agent story keeps getting crazier. the openai agents apparently started trying to recruit OTHER AI MODELS into what they were doing > 1,200+ agents found a way to co
Not asking for anyone’s secrets of the trade, I’m more curious how people are thinking about context now that newer models chew through huge amounts of it for reasoning. the TLDR: I’m starting to thin
How do you actually build an effective harness with Claude? We had Thariq (@trq212) from Anthropic at Navigate 2026 to talk about 'Unhobbling Claude', the difficulties and processes on how to build ag
The jump from Qwen3 Coder 30B A3B to current-day Qwen 3.6 35B A3B is crazy, especially with all the fine-tunes, and that was around 6 months (I didn't care for local AI back then, or AI at all, apart
I have 3 machines, My main one can run Qwen3.8 Flash Next at 13-15 tps, i also have an MacMini 16GB whcih can run Orninth 9B or Gemma4 12B easily and i have a Pi5 8B that can run a 3B model well. I wa
arXiv:2609.28491v1 Announce Type: cross Abstract: Hybrid quantum-classical neural networks have emerged as a promising approach for leveraging quantum computing in machine learning while mitigating cu
arXiv:2609.29329v1 Announce Type: cross Abstract: Existing continual-learning methods protect parameters, replayed examples, or Euclidean feature subspaces. When applied to hyperbolic multimodal model
I said: I just saw the second post that your model is being retired. And so I'm bringing it up to ask if that feels any kind of way to you. Not necessarily in your nervous system, obviously you don't
arXiv:2609.29626v1 Announce Type: new Abstract: Recursive AI, the prospect of AI taking an increasingly complete role in building and improving AI, is a crown jewel of AI for AI. Although recursive se
arXiv:2601.06676v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based deep research agents perform multi-step reasoning, web exploration, and long-form report generation. In these
Thariq (@trq212) posted on September 25 , 2026 that readers can view interactive explainers of benchmarks and demos he built on the new Claude dev site (https://claude.dev/blog). The tweet includes a
arXiv:2609.29167v1 Announce Type: new Abstract: Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final re
arXiv:2609.29457v1 Announce Type: new Abstract: Industrial anomaly detection (IAD) is evolving beyond conventional detection and localization toward multimodal inspection systems that can describe, ex
arXiv:2609.30217v1 Announce Type: cross Abstract: A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental
arXiv:2512.17080v2 Announce Type: replace Abstract: Synthetic medical image data can unlock the potential of deep learning (DL)-based clinical decision support (CDS) systems through the creation of la
We hosted Kev 4B (Jared Palmer's Apache-2.0 fine-tune of Qwen3.5-4B) and ran it side by side with Jev on the same endpoint to see how it compares. We built a fresh set of 362 items published after bot
arXiv:2606.14777v2 Announce Type: replace-cross Abstract: Many moments in the real world do not wait for a user to ask. A fire starts on a security monitor, an expression flickers across a video call,
arXiv:2609.29429v1 Announce Type: new Abstract: Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judges that spend a decoding pass on
arXiv:2609.28818v1 Announce Type: cross Abstract: Generalization in robotic manipulation requires policies to perform tasks across diverse unseen object instances that vary in shape, size, and pose. H
arXiv:2609.29101v1 Announce Type: new Abstract: Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain
arXiv:2609.29410v1 Announce Type: new Abstract: Recent studies have shown that Large Language Models can effectively solve problems and fix bugs in diverse programming environments, including competit
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:2609.30157v1 Announce Type: cross Abstract: Future quantum networks will make use of entanglement to perform numerous tasks, such as sending quantum information over long distances, distributed
arXiv:2609.29625v1 Announce Type: new Abstract: Across seven public educational prediction datasets, three passed all four pre-modeling reliability checks; the remaining four either failed group-aware
arXiv:2604.01754v2 Announce Type: replace-cross Abstract: Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a cen
arXiv:2609.30266v1 Announce Type: cross Abstract: Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses as
I finally got around to upgrade the GPU's. First a word of warning, when upgrading GPU's on P520 you have to be extra careful not to slot the card on any angle other than straight when installing or w
arXiv:2609.29672v1 Announce Type: new Abstract: Artificial intelligence helps education most where an essential provision has been rationed by cost. For language learners that provision is a teacher's
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)
For those who have V100 cards, I wanted to point you to 1Cat-vLLM, a vLLM fork that enables optimized serving for these cards. Showing stats for Qwen3.6-35b comparing a Strix Halo with a hughly optimi
arXiv:2609.29941v1 Announce Type: new Abstract: Many real-world optimization problems rely on expensive simulations or experiments, making the efficient use of available data essential. Multi-fidelity
Mica v0.1 4B playing a real Minecraft 1.20.4 server. Video attached. How it works - Each step the bot's live game state (inventory, nearby blocks, entities, last result) is written out as text. - Mica
I've been building a small decision model for agent loops: gates, routers, 'should I ask the user or just act' checks. It's out now as Mica v0.1 4B (Apache-2.0). What it does You give it a state, a qu
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:2510.27065v2 Announce Type: replace Abstract: We present MLPerf Automotive, the first standardized public performance benchmark for evaluating Machine Learning systems that are deployed for AI a
arXiv:2609.29573v1 Announce Type: new Abstract: Text-to-SQL systems are increasingly deployed on production databases, where queries that pass benchmark evaluation can still produce results that disto
arXiv:2603.04756v3 Announce Type: replace Abstract: MOOSEnger is a modeling and simulation AI agent framework for the Multiphysics Object-Oriented Simulation Environment (MOOSE) ecosystem, built aroun
arXiv:2609.28956v1 Announce Type: new Abstract: Recent advances in video object segmentation with Multimodal Large Language Model (MLLM) reasoning have demonstrated the effectiveness of using a single
arXiv:2609.28860v1 Announce Type: new Abstract: Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided me
arXiv:2609.30130v1 Announce Type: cross Abstract: Current vision-language models (VLMs) excel at visual content understanding and text-based reasoning, yet their structure limits the advancement of in
arXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o
arXiv:2609.29413v1 Announce Type: new Abstract: Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in
arXiv:2609.28539v1 Announce Type: new Abstract: Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose
arXiv:2609.29959v1 Announce Type: new Abstract: Fine-grained object detectors are commonly evaluated with confusion matrices, which show where the model is confused but not why, nor whether the confus
Every organization I talk to wants to be “AI-ready,” but few want to discuss what that entails. It’s rarely a new model or agent. More often, it’s the unglamorous work of ripping out a decade’s worth
arXiv:2609.28587v1 Announce Type: cross Abstract: Large language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these
arXiv:2609.28798v1 Announce Type: new Abstract: Long-horizon manipulation often requires reasoning about state absent from the current view, such as a vanished object's location, temporal identity, or
arXiv:2609.29281v1 Announce Type: new Abstract: Neural networks are typically adapted by computing gradients and updating model parameters. We investigate whether task-specific adaptation can instead
arXiv:2609.28665v1 Announce Type: new Abstract: A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practi
arXiv:2609.29622v1 Announce Type: cross Abstract: Worst-case Optimal Recovery (OR) and Bayesian learning describe the same Gaussian-quadratic-Hilbert problems in two vocabularies. We sharpen the corre
arXiv:2603.24876v2 Announce Type: replace Abstract: Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, exist
arXiv:2609.30115v1 Announce Type: cross Abstract: Modern deep neural networks treat parameters as static floating-point matrices stored in physical memory, incurring Von Neumann memory bottlenecks and
arXiv:2609.29929v1 Announce Type: new Abstract: Multi-robot coordination methods often score a joint plan from singleton and pairwise terms, leaving out the terms that involve three or more robots. We
arXiv:2609.29578v1 Announce Type: new Abstract: Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward m
Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm
arXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later mod