Knowledge catalogue
arXiv:2505.04310v2 Announce Type: replace-cross Abstract: Distributional Reinforcement Learning (DistRL) improves upon expectation-based methods by modeling full return distributions, but standard app
arXiv:2605.03105v1 Announce Type: new Abstract: This paper introduces the ensemble directional Kalman filter (EnDKF), an ensemble-based Kalman filtering approach for pose tracking that jointly estimat
arXiv:2605.02964v1 Announce Type: new Abstract: Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomou
arXiv:2605.03226v1 Announce Type: new Abstract: Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's diff
arXiv:2605.03258v1 Announce Type: cross Abstract: Large language models often fail at simple counting tasks, even when the items to count are explicitly present in the prompt. We investigate whether t
The AI era demands a fundamental shift in security, and that includes identity and access management (IAM). Traditional controls simply aren’t built for autonomous AI agents that interact with sensiti
arXiv:2605.03096v1 Announce Type: cross Abstract: In classification tasks, models may rely on confounding variables to achieve strong in-distribution performance, capturing spurious features that fail
arXiv:2605.00903v1 Announce Type: new Abstract: Agriculture is a key sector of the economies of developing countries. It serves as a primary source of income and employment for rural populations. Howe
arXiv:2605.01741v1 Announce Type: new Abstract: Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry. However, the development of robust AI models for volumetric anal
arXiv:2605.02317v1 Announce Type: cross Abstract: Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However,
arXiv:2605.00943v1 Announce Type: new Abstract: Foundational models have advanced social robotics, enabling richer perception and communicative interaction with users. However, current systems still s
arXiv:2605.01188v1 Announce Type: new Abstract: Scaling laws enable the optimal selection of data amount and language model size, yet the impact of the data unit, the token, on this relationship remai
arXiv:2605.01372v1 Announce Type: new Abstract: Large language models (LLMs) have been widely explored for embedding generation. While recent studies show that in-context learning (ICL) effectively en
Building AI agents that work well in a demo is one thing, but running them in production requires serious infrastructure. At Google Cloud Next '26, we introduced Gemini Enterprise Agent Platform to he
arXiv:2605.02292v1 Announce Type: new Abstract: Chest X-ray classification suffers from severe class imbalance where gradient updates bias toward majority classes, causing feature drift and poor perfo
arXiv:2605.02871v1 Announce Type: cross Abstract: Composite materials exhibit strongly hierarchical and anisotropic properties governed by coupled mechanisms spanning constituents, plies, laminates, s
arXiv:2605.01219v1 Announce Type: cross Abstract: Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortion
arXiv:2605.01357v1 Announce Type: new Abstract: Large Language Models (LLMs) excel at long-context understanding but exhibit significant limitations in long-form generation. Existing studies primarily
arXiv:2605.01945v1 Announce Type: new Abstract: Tandem mass spectrometry provides a high-throughput framework for identifying and quantifying proteins in complex biological samples. In computational p
arXiv:2605.01339v1 Announce Type: new Abstract: Learning-based approaches to verifying unknown Markov decision processes (MDPs) often employ uncertain MDPs. These models use, for example, confidence i
arXiv:2605.01496v1 Announce Type: new Abstract: This report presents the results and findings of the first edition of the Short-Films 20K (SF20K) Competition, held in conjunction with the SLoMO Worksh
arXiv:2605.02860v1 Announce Type: cross Abstract: Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little
Subquadratic, a company developing a novel generative artificial intelligence model, launched today with 29 million in seed funding. The new large language model, dubbed SubQ, uses what the company ca
arXiv:2605.02398v1 Announce Type: cross Abstract: As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability -- knowing what they do not kn
arXiv:2605.02427v1 Announce Type: cross Abstract: A recurring pattern in 'reasoning without training' is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the
arXiv:2605.00826v1 Announce Type: cross Abstract: Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with
arXiv:2605.00251v1 Announce Type: cross Abstract: Existing voice deepfake detection and localization models rely heavily on representations extracted from speech foundation models (SFMs). However, dow
arXiv:2605.00292v1 Announce Type: new Abstract: The scalability of Large Language Models to long sequences is hindered by the quadratic cost of attention and the limitations of positional encodings. T
arXiv:2605.00677v1 Announce Type: new Abstract: While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results ste
arXiv:2605.00645v1 Announce Type: new Abstract: Clinical time-series forecasting is increasingly studied for decision support, yet standard aggregate metrics can obscure whether a model is actually us
arXiv:2604.04567v2 Announce Type: replace-cross Abstract: The prevalence of missing values in data science poses a substantial risk to any further analyses. Despite a wealth of research, principled no
This post documents a 10-day project to build a local AI system using open-source tools and models, specifically combining Ollama (a local LLM framework), Gemma 4 (a language model), Claude Cowork 3P,
arXiv:2605.00393v1 Announce Type: new Abstract: Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms re
This Databricks blog post discusses how organizations can achieve AI scalability through unified infrastructure and organizational alignment, emphasizing the importance of consolidating teams, platfor
This post benchmarks three Qwen3.6 model variants against gpt-oss:120b when running on Apple Silicon hardware, evaluating their performance characteristics and practical usability. It documents both t
arXiv:2510.01712v2 Announce Type: replace Abstract: The use of accurate and reliable open-source human activity recognition (HAR) models on passively collected wrist-accelerometer data is essential in
arXiv:2604.27006v1 Announce Type: cross Abstract: Context: Study screening in systematic literature reviews is costly, inconsistency-prone, and risk-asymmetric, since false negatives can compromise va
arXiv:2604.28082v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) on narrowly misaligned data generalizes to broadly misaligned behavior, a phenomenon termed emergent misalignme
arXiv:2601.05052v2 Announce Type: replace Abstract: Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenge
arXiv:2603.09881v2 Announce Type: replace Abstract: Speech Large Language Models (SLLMs) have rapidly expanded, supporting a wide range of tasks. These models are typically evaluated using text prompt
arXiv:2604.27143v1 Announce Type: cross Abstract: Recent research has demonstrated the potential of Large Language Models (LLMs) for autonomous penetration testing, particularly when using cloud-based
arXiv:2604.27393v1 Announce Type: new Abstract: Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming inter
arXiv:2407.08668v3 Announce Type: replace-cross Abstract: In this work, we propose a simulation-based estimation approach using generative neural networks to determine dependencies of precipitation ma
arXiv:2604.27637v1 Announce Type: new Abstract: Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from t
arXiv:2604.27401v1 Announce Type: new Abstract: Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backp
arXiv:2512.07703v2 Announce Type: replace Abstract: Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning su
arXiv:2601.14289v2 Announce Type: replace-cross Abstract: Understanding research papers remains challenging for foundation models due to specialized scientific discourse and complex figures and tables
arXiv:2604.27780v1 Announce Type: cross Abstract: Large Language Models (LLMs) have rapidly improved in performance across code-related tasks, making their integration into Register Transfer Level (RT
arXiv:2604.28039v1 Announce Type: new Abstract: Spectra are a prevalent yet highly information-dense form of scientific imagery, presenting substantial challenges to multimodal large language models (
arXiv:2409.06624v4 Announce Type: replace-cross Abstract: Large Language Models (LLM) often need to be Continual Pre-Trained (CPT) to obtain unfamiliar language skills or adapt to new domains. The hug
arXiv:2604.26319v1 Announce Type: new Abstract: Stance detection identifies the attitude of a text author toward a given target. Recent studies have explored various LLM-based strategies for this task
In this post, we introduce a systematic framework for LLM migration or upgrade in generative AI production, encompassing essential tools, methodologies, and best practices. The framework facilitates t
> be me > 'the internet is polluted by ai slop, we need low-background tokens' > 'wouldnt it be cool if we could time travel and see what our ancestors 100 years ago would say to us' > all the existin
arXiv:2604.26169v1 Announce Type: new Abstract: Treatment allocation under budget constraints is a central challenge in digital advertising: advertisers must decide which users to show ads to while sp
arXiv:2604.26378v1 Announce Type: new Abstract: Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-p
arXiv:2604.26866v1 Announce Type: new Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of
arXiv:2602.11731v2 Announce Type: replace Abstract: Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision para
arXiv:2604.26313v1 Announce Type: cross Abstract: We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Synta
arXiv:2510.17548v2 Announce Type: replace Abstract: Language models are often evaluated with scalar metrics like accuracy, but such measures fail to capture how models internally represent ambiguity,
arXiv:2604.25249v1 Announce Type: new Abstract: Detecting sandbagging--the deliberate underperformance on capability evaluations--is an open problem in AI safety. We tested whether symptom validity te