Knowledge catalogue
arXiv:2605.18815v1 Announce Type: new Abstract: Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape t
arXiv:2605.18908v1 Announce Type: cross Abstract: Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data,
arXiv:2603.03140v3 Announce Type: replace-cross Abstract: AI agents are increasingly active on social media platforms, generating content and interacting with one another at scale. Yet the behavioral
arXiv:2603.29183v2 Announce Type: replace-cross Abstract: Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to id
arXiv:2411.08982v3 Announce Type: replace Abstract: Selective parameter activation provided by Mixture-of-Expert (MoE) models have made them a popular choice in modern foundational models. However, Mo
arXiv:2605.19328v1 Announce Type: cross Abstract: Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platfo
arXiv:2605.18797v1 Announce Type: cross Abstract: Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same
arXiv:2605.18800v1 Announce Type: cross Abstract: Post-training quantization has emerged as a widely adopted technique for compressing and accelerating the inference of Large Language Models (LLMs). T
arXiv:2605.19289v1 Announce Type: new Abstract: Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern dif
arXiv:2605.18083v1 Announce Type: new Abstract: Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignm
arXiv:2605.16902v1 Announce Type: new Abstract: Scientific artifacts such as models and datasets are foundations for research. With the rapid growth of platforms like HuggingFace, researchers now have
arXiv:2605.17971v1 Announce Type: cross Abstract: Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuri
arXiv:2505.03631v4 Announce Type: replace Abstract: Video quality assessment (VQA) is essential for quantifying perceptual quality in various video processing workflows, spanning from camera capture s
arXiv:2605.18226v1 Announce Type: cross Abstract: Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While pref
arXiv:2508.04227v2 Announce Type: replace Abstract: Vision-language models (VLMs) and the recent surge of Multimodal Large Language Models (MLLMs) have revolutionized artificial intelligence with unpr
arXiv:2605.16444v1 Announce Type: cross Abstract: Accurate intraoperative and postoperative diagnosis of spread through air spaces (STAS) is essential for guiding surgical decisions and postoperative
arXiv:2605.16776v1 Announce Type: cross Abstract: Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowl
arXiv:2605.18554v1 Announce Type: new Abstract: Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight
Gemini 3.5 is Google's latest family of AI models combining frontier intelligence with action, representing a major leap forward in building more capable, intelligent agents. The first model in the se
Google LLC today introduced two new generative artificial intelligence models that push its Gemini family further into AI agents and multimodal creation: Gemini 3.5 Flash, a fast reasoning model desig
arXiv:2605.18387v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) and Graph Transformers (GTs) are now a fundamental paradigm for graph learning, combining the representation-learning cap
arXiv:2605.17856v1 Announce Type: new Abstract: Process-based simulation models encode decades of scientific understanding across the Earth sciences, yet the communities most exposed to climate risk a
arXiv:2605.18541v1 Announce Type: new Abstract: Modeling hyperspectral imagery (HSI) across different sensors presents a fundamental challenge due to variations in wavelength coverage, band sampling,
arXiv:2605.16786v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly needed for interactive mobile applications, but high-quality models exceed the limited DRAM available on s
arXiv:2605.18449v1 Announce Type: cross Abstract: Understanding customer movement within retail spaces is essential for optimizing store layouts. Real-world trajectory data can provide highly accurate
arXiv:2509.02351v3 Announce Type: replace-cross Abstract: Labeled data is a fundamental component in training supervised deep learning models for computer vision tasks. However, the labeling process,
arXiv:2605.17916v1 Announce Type: new Abstract: Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence
arXiv:2605.18464v1 Announce Type: new Abstract: Contrastively trained vision-language models such as CLIP provide strong zero-shot transfer by aligning images and text in a shared embedding space. How
arXiv:2605.18474v1 Announce Type: cross Abstract: The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing
arXiv:2512.19134v2 Announce Type: replace Abstract: Dynamic Retrieval-Augmented Generation adaptively determines when to retrieve during generation to mitigate hallucinations in large language models
arXiv:2605.16874v1 Announce Type: new Abstract: Large reasoning models (LRMs) substantially outperform their base LLM counterparts on challenging reasoning benchmarks, yet it remains poorly understood
arXiv:2603.11276v2 Announce Type: replace-cross Abstract: Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. Ho
arXiv:2605.17522v1 Announce Type: new Abstract: Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predicti
arXiv:2605.17710v1 Announce Type: new Abstract: Although modern multilingual Automatic Speech Recognition (ASR) systems support several Nigerian languages, their performance consistently lags behind h
arXiv:2605.18063v1 Announce Type: new Abstract: Object counting is a foundational vision task with over a decade of dedicated research, yet state-of-the-art models still fail systematically in the mix
arXiv:2605.16547v1 Announce Type: new Abstract: Semantic communication has emerged as a promising paradigm for enabling goal-oriented networking. However, most existing semantic communication solution
I cannot provide an accurate summary of this entry as the title appears to be truncated mid-sentence and lacks sufficient context. Based on the incomplete title, it likely discusses how software speci
arXiv:2605.15217v1 Announce Type: new Abstract: Instruction-tuned language models exhibit behavioural fairness in high-stakes decisions while retaining biased associations in their internal representa
arXiv:2605.15290v1 Announce Type: cross Abstract: Hyperparameter transfer across model architectures dramatically reduces the amount of compute necessary for tuning large language models (LLMs). The m
arXiv:2605.15464v1 Announce Type: cross Abstract: Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critic
arXiv:2605.16048v1 Announce Type: cross Abstract: State Space Models (SSMs) are inherently recurrent along the sequence dimension, yet depth-recurrence - reusing the same block repeatedly across layer
arXiv:2605.15227v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) have attracted increasing attention as a means of accelerating scientific discovery; however, developing SDL software r
arXiv:2508.08431v3 Announce Type: replace-cross Abstract: Spectral variability significantly impacts the accuracy and convergence of hyperspectral unmixing algorithms. Many methods address complex spe
arXiv:2605.15508v1 Announce Type: cross Abstract: The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is p
Claude Code's product lead addresses how Anthropic tunes the 'harness' (the structural layer around the model) for each new model release to optimize performance and reduce verbosity. The company comm
arXiv:2605.14362v1 Announce Type: cross Abstract: Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models deg
arXiv:2510.04682v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely applied in real world scenarios, yet fine-tuning them comes with significant computational and storage
arXiv:2605.13200v1 Announce Type: new Abstract: Accurate state of charge estimation is critical for the success of electric vehicle battery management strategies, but it is well known that conventiona
arXiv:2605.13646v1 Announce Type: cross Abstract: End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recentl
arXiv:2605.12857v1 Announce Type: cross Abstract: Existing API-based agentic systems for RTL code generation are fundamentally misaligned with industrial practice: they assume a golden testbench is av
arXiv:2511.00839v2 Announce Type: replace-cross Abstract: Current benchmarks for coding evaluate language models (LMs) on concrete, well-specified tasks such as fixing specific bugs or writing targete
arXiv:2605.13151v1 Announce Type: new Abstract: Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support exampl
arXiv:2506.11274v2 Announce Type: replace-cross Abstract: Test-time scaling has emerged as an effective approach for improving language model performance by utilizing additional compute at inference t
arXiv:2605.13713v1 Announce Type: new Abstract: Volumetric Modulated Arc Therapy (VMAT) is a cornerstone of modern radiation therapy, enabling highly conformal tumor irradiation and healthy-tissue spa
arXiv:2605.13412v1 Announce Type: cross Abstract: Off-the-shelf large language models (LLMs) are increasingly used to automate text annotation, yet their effectiveness remains underexplored for underr
arXiv:2512.16767v2 Announce Type: replace Abstract: Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-c
arXiv:2605.13225v1 Announce Type: new Abstract: For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many tim
arXiv:2605.12506v1 Announce Type: cross Abstract: Realizing on-device ML-based gesture detection under tight real-time performance, energy and memory constraints is challenging, especially when consid
arXiv:2605.13737v1 Announce Type: new Abstract: When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perc
arXiv:2505.12415v3 Announce Type: replace-cross Abstract: Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for