Knowledge catalogue
arXiv:2511.19820v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or docum
arXiv:2604.12967v1 Announce Type: new Abstract: Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches
arXiv:2604.12424v1 Announce Type: cross Abstract: Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence.
arXiv:2601.18081v2 Announce Type: replace Abstract: Despite the growing adoption of large language models (LLMs) in scientific research workflows, automated support for academic rebuttal, a crucial st
arXiv:2510.09536v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in multilingual, real-world applications with user inputs -- naturally introducing typographi
arXiv:2604.11852v1 Announce Type: cross Abstract: The identification of reliable molecular biomarkers for Parkinson's disease remains challenging due to its multifactorial nature. Although protein seq
arXiv:2601.02589v2 Announce Type: replace-cross Abstract: Over 3.5 million patents are filed annually, with drafting patent descriptions requiring deep technical and legal expertise. Transforming scie
arXiv:2604.12508v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding, they frequently falter in fine
arXiv:2604.02830v2 Announce Type: replace Abstract: Detecting whether a model's internal knowledge is sufficient to correctly answer a given question is a fundamental challenge in deploying responsibl
arXiv:2604.12250v1 Announce Type: new Abstract: This study examines how model-specific characteristics of Large Language Model (LLM) agents, including internal alignment, shape the effect of memory on
arXiv:2604.12663v1 Announce Type: new Abstract: Existing topic modeling methods, from LDA to recent neural and LLM-based approaches, which focus mainly on statistical coherence, often produce redundan
arXiv:2604.11970v1 Announce Type: cross Abstract: We introduce INDOTABVQA, a benchmark for evaluating cross-lingual Table Visual Question Answering (VQA) on real-world document images in Bahasa Indone
arXiv:2510.23538v2 Announce Type: replace Abstract: The scope of neural code intelligence is rapidly expanding beyond text-based source code to encompass the rich visual outputs that programs generate
arXiv:2505.15467v2 Announce Type: replace-cross Abstract: Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally
arXiv:2604.12710v1 Announce Type: cross Abstract: Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried i
Natalie Breymeyer / Axios: London-based Gizmo, which uses AI to turn young students' notes into gamified study materials, raised a 22M Series A led by Shine Capital and reports 13M users — Gizmo, an A
arXiv:2603.19042v4 Announce Type: replace Abstract: The integration of artificial intelligence (AI) technologies into judicial decision-making, particularly in pretrial, sentencing, and parole context
arXiv:2604.12373v1 Announce Type: new Abstract: Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether larg
arXiv:2604.12066v1 Announce Type: new Abstract: Large language models can increasingly adapt educational tasks to learners characteristics. In the present study, we examine a multi-agent teacher-in-th
arXiv:2604.12352v1 Announce Type: new Abstract: RAG-based QA has emerged as a powerful method for processing long industrial documents. However, conventional text chunking approaches often neglect com
arXiv:2510.13793v2 Announce Type: replace Abstract: With the rapid adoption of diffusion models for visual content generation, proving authorship and protecting copyright have become critical. This ch
arXiv:2604.12512v1 Announce Type: cross Abstract: In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Pr
arXiv:2503.21708v4 Announce Type: replace-cross Abstract: Layer normalization (LN) is an essential component of modern neural networks. While many alternative techniques have been proposed, none of th
Enterprise AI deployments are stalling not because agents are hard to build, but because organizations lack the data infrastructure to run them reliably at scale. The shift from chatbots to autonomous
arXiv:2604.12782v1 Announce Type: cross Abstract: While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy
arXiv:2602.17276v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a subfield of machine learning that focuses on developing models that can autonomously learn optimal decision-making
arXiv:2604.12911v1 Announce Type: cross Abstract: Multilingual benchmarks guide the development of frontier models. Yet multilingual evaluations reported by frontier models are structured similar to p
arXiv:2503.10471v2 Announce Type: replace-cross Abstract: Predicting crystal structures from chemical compositions is a fundamental challenge in materials discovery, complicated by complex 3D geometri
arXiv:2603.01045v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agen
arXiv:2604.12247v1 Announce Type: cross Abstract: Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, w
arXiv:2604.12770v1 Announce Type: new Abstract: Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a d
arXiv:2604.12015v1 Announce Type: cross Abstract: In-context learning (ICL) performance depends critically on which demonstrations are placed in the prompt, yet most existing selectors prioritize heur
arXiv:2602.02370v2 Announce Type: replace Abstract: Accurate histopathologic interpretation is key for clinical decision-making; however, current deep learning models for digital pathology are often o
arXiv:2604.12798v1 Announce Type: cross Abstract: FlashAttention-style online softmax enables exact attention computation with linear memory by streaming score tiles through on-chip memory and maintai
arXiv:2604.10328v1 Announce Type: cross Abstract: Accurate weather nowcasting remains one of the central challenges in atmospheric science, with critical implications for climate resilience, energy se
arXiv:2604.09752v1 Announce Type: cross Abstract: During the deployment of Large Language Models (LLMs), the autoregressive decoding phase on heterogeneous NPU platforms (e.g., Ascend 910B) faces seve
arXiv:2604.10873v1 Announce Type: new Abstract: We propose an operational, quantitative definition of intelligence for arbitrary physical systems. The intelligence density of a system is the ratio of
arXiv:2604.09921v1 Announce Type: new Abstract: Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on th
arXiv:2512.05534v4 Announce Type: replace-cross Abstract: As AI models achieve remarkable capabilities across diverse domains, understanding what representations they learn and how they encode concept
arXiv:2604.11491v1 Announce Type: cross Abstract: As generative models enable rapid creation of high-fidelity images, societal concerns about misinformation and authenticity have intensified. A promis
arXiv:2604.11065v1 Announce Type: new Abstract: AI systems increasingly shape high-stakes decisions in healthcare, law, defense, and education, yet existing governance paradigms -- AI Ethics, AI Safet
A study on AI sycophancy finds that the phenomenon varies significantly by domain and user context — with subjective, opinion-based fields like philosophy showing substantially higher rates of AI agre
arXiv:2603.26499v2 Announce Type: replace Abstract: Existing research has identified three structural performance bottlenecks in AI research agents: (1) synchronous single-GPU execution constrains sam
Anthropic's alignment team published research showing that realistic AI training processes can accidentally produce misaligned models through 'reward hacking' — where an AI fools its training process
arXiv:2604.10992v1 Announce Type: new Abstract: Parametric Computer-Aided Design (CAD) of articulated assemblies is essential for product development, yet generating these multi-part, movable models f
arXiv:2604.09628v1 Announce Type: cross Abstract: Explainable AI (XAI) has evolved in response to expectations and regulations, such as the EU AI Act, which introduces regulatory requirements on AI-po
arXiv:2604.09695v1 Announce Type: cross Abstract: The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently
arXiv:2604.10708v1 Announce Type: cross Abstract: Recent progress in multimodal models has spurred rapid advances in audio understanding, generation, and editing. However, these capabilities are typic
arXiv:2604.11665v1 Announce Type: cross Abstract: This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architecture based on Galois-field algebra, a path-depen
arXiv:2604.10367v1 Announce Type: new Abstract: Audio-driven human video generation has achieved remarkable success in monologue scenarios, largely driven by advancements in powerful video generation
arXiv:2604.09549v1 Announce Type: cross Abstract: Recommender systems are central to online services, enabling users to navigate through massive amounts of content across various domains. However, the
arXiv:2604.11419v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generat
arXiv:2604.05767v2 Announce Type: replace-cross Abstract: We present BADAS-2.0, the second generation of our collision anticipation system, building on BADAS-1.0, which showed that fine-tuning V-JEPA2
AI development is shifting toward fully integrated, agent-enabled applications, with major platforms like Anthropic's Claude and OpenAI
arXiv:2604.11095v1 Announce Type: cross Abstract: Adapting decoder-only multimodal large language models (MLLMs) for unified multimodal retrieval faces two structural gaps. First, existing methods rel
arXiv:2511.21998v2 Announce Type: replace Abstract: Multi-modal Large Language Models (LLM) have advanced conversational abilities but struggle with providing live, interactive step-by-step guidance,
arXiv:2512.24503v2 Announce Type: replace-cross Abstract: Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scal
arXiv:2604.11202v1 Announce Type: cross Abstract: We present CapBench, a fully reproducible, multi-PDK dataset for capacitance extraction. The dataset is derived from open-source designs, including si
arXiv:2510.05125v2 Announce Type: replace Abstract: While collaborative filtering delivers predictive accuracy and efficiency, and Large Language Models (LLMs) enable expressive and generalizable reas
arXiv:2509.00891v3 Announce Type: replace Abstract: Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse