Knowledge catalogue
arXiv:2602.04729v2 Announce Type: replace Abstract: We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilin
arXiv:2605.28994v1 Announce Type: new Abstract: AI tools to support real world decision making must be able to build simulation models that inform their recommendations and render them interpretable.
arXiv:2605.30318v1 Announce Type: cross Abstract: Portrait photography is largely decided before the shutter opens: the subject's pose, the camera configuration, and the lighting devices must be coord
arXiv:2605.28855v1 Announce Type: new Abstract: Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary co
arXiv:2605.28849v1 Announce Type: new Abstract: Gradient temporal-difference methods provide stable off-policy prediction with linear function approximation, but their practical performance is strongl
arXiv:2602.14307v3 Announce Type: replace Abstract: As frontier Large Language Models (LLMs) increasingly saturate new benchmarks shortly after they are published, benchmarking itself is at a juncture
arXiv:2605.29462v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has substantially expanded model capabilities beyond text-only understanding, enabling unified i
arXiv:2509.23571v3 Announce Type: replace-cross Abstract: As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect a
arXiv:2605.28830v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a c
arXiv:2605.29754v1 Announce Type: new Abstract: Electroencephalography (EEG) is a widely used non-invasive technique for measuring brain activity in brain-computer interface (BCI) applications. Superv
arXiv:2605.30339v1 Announce Type: new Abstract: Generative video-to-audio (V2A) models produce highly plausible soundtracks, but it remains unclear whether they capture the underlying physical process
arXiv:2605.29225v1 Announce Type: new Abstract: Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, lea
arXiv:2605.29168v1 Announce Type: new Abstract: Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operatio
arXiv:2605.30231v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) often struggle with robust 3D spatial reasoning. Prevailing methods that rely on fine-tuning with 3D visual question-ans
arXiv:2510.16060v2 Announce Type: replace-cross Abstract: The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of
arXiv:2605.29629v1 Announce Type: new Abstract: Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not ho
arXiv:2605.29414v1 Announce Type: cross Abstract: Recent studies have shown that code-switching data (CSD), in which multiple languages are mixed within the same context, can improve cross-lingual tra
arXiv:2605.29116v1 Announce Type: new Abstract: When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating
arXiv:2605.29667v1 Announce Type: new Abstract: When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break
arXiv:2605.30122v1 Announce Type: cross Abstract: Deep-learning precipitation nowcasting models are often optimized using pointwise losses such as mean squared error or mean absolute error, which can
arXiv:2602.12642v2 Announce Type: replace-cross Abstract: Reward-maximizing RL methods have shown to be capable of enhancing the reasoning performance of LLMs, but often lead to reduced generation div
arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f
arXiv:2605.29697v1 Announce Type: new Abstract: In Agentic Search, trajectory-level outcome rewards fail to quantify the behavioral contributions of individual steps, while existing step-level reward
arXiv:2602.08979v2 Announce Type: replace-cross Abstract: Audio chaptering, the task of segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures,
arXiv:2512.00283v3 Announce Type: replace-cross Abstract: Foundation models have revolutionized various fields such as natural language processing (NLP) and computer vision (CV). While efforts have be
arXiv:2605.30162v1 Announce Type: new Abstract: Biosecurity evaluations of language models typically ask whether models produce hazardous output. This paper asks a complementary question: when a model
arXiv:2605.29583v1 Announce Type: new Abstract: High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information (e.g., ownership, provenance, and authenticati
arXiv:2605.29705v1 Announce Type: new Abstract: Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large langua
arXiv:2605.29233v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to s
A rocket built by Jeff Bezos’ Blue Origin Enterprises LP exploded late Thursday ahead of a planned launch next week. The New Glenn heavy-lift vehicle was set to carry 48 of Amazon.com Inc.’s Leo satel
bold set of counterpredictions, from @scaling01: Cold take on what comes next: - OpenAI will flourish - Anthropic will continue to be profitable - Google will not catch up to Anthropic or OpenAI - no
arXiv:2605.30269v1 Announce Type: new Abstract: Over the past decades, numerous Image Quality Assessment (IQA) models have emerged, aiming to predict the perceptual quality of images. However, individ
arXiv:2605.30065v1 Announce Type: new Abstract: In this work, we focus on zero-shot 3D style transfer that can generate multi-view consistent stylized views of the 3D scene given an arbitrary style im
arXiv:2605.30226v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulat
arXiv:2605.29062v1 Announce Type: new Abstract: Communities can sustainably manage shared resources (commons) through self-governance and cooperative norms, a central finding of Ostrom's theory of sel
Boston Children's Hospital has implemented AI technology to improve diagnostic accuracy and identify rare or complex medical conditions in pediatric patients that might otherwise go undiagnosed. The a
Both men said “I can’t breathe”, but only one man’s death was covered relentlessly by the media. The only conclusion that can be drawn is that the legacy mainstream media is incredibly, hatefully raci
Dutch authorities dismantled a large Asocks botnet comprising at least 17 million compromised devices including computers, routers, tablets, smartphones, and smart security cameras. Investigators iden
arXiv:2605.29379v1 Announce Type: new Abstract: We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class whi
arXiv:2605.29588v1 Announce Type: cross Abstract: Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-
arXiv:2603.26668v2 Announce Type: replace-cross Abstract: As an important paradigm for enhancing the generation quality of Large Language Models (LLMs), retrieval-augmented generation (RAG) faces the
arXiv:2605.29108v1 Announce Type: new Abstract: Selecting efficient multi-step synthetic routes is a central challenge in organic synthesis, particularly in medicinal and process chemistry, where rout
arXiv:2601.21568v2 Announce Type: replace Abstract: We present a unified framework for quantifying the similarity between representations through the lens of extit{usable} information, offering a rigo
arXiv:2601.01162v3 Announce Type: replace-cross Abstract: Qualitative data are widespread in domains such as healthcare, marketing, and bioinformatics, where clustering offers a fundamental tool for p
arXiv:2605.29078v1 Announce Type: new Abstract: Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observe
arXiv:2605.29856v1 Announce Type: new Abstract: As a widespread form of informal settlements, urban villages present significant challenges for sustainable urban development and governance. Precise ma
arXiv:2605.29849v1 Announce Type: cross Abstract: Machine learning (ML) is increasingly used for data-driven modeling of buildings to enable downstream tasks such as fault detection and diagnosis, and
arXiv:2605.30235v1 Announce Type: new Abstract: We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575).
Bloomberg: BYD announces the Xuanji A3 chip, which it calls China's most powerful chip for ADAS and the centerpiece of its new laptop-sized central computing platform — BYD Co., the world's largest el
arXiv:2605.29155v1 Announce Type: cross Abstract: In the literature, actor-critic model predictive control (AC-MPC) integrates MPC with reinforcement learning to enable high-performance control of com
arXiv:2605.30188v1 Announce Type: cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibr
arXiv:2510.10020v4 Announce Type: replace-cross Abstract: Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a
arXiv:2601.08064v2 Announce Type: replace Abstract: Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing eval
arXiv:2504.06022v3 Announce Type: replace Abstract: Recently, image-to-video (I2V) diffusion models have demonstrated impressive scene understanding and generative quality, incorporating image conditi
arXiv:2605.30184v1 Announce Type: new Abstract: While AI weather models excel at short-to-medium range forecasts (up to 15 days), they frequently suffer from ill-defined 'instabilities' when rolled ou
arXiv:2605.29316v1 Announce Type: new Abstract: Audio-driven 3D facial animation aims to generate synchronized lip movements and vivid facial expressions from arbitrary audio clips. While existing met
CineStill 800T Night Film LoRA is a machine learning model addon for Stable Diffusion that applies a cinematic night aesthetic to AI-generated images, using the trigger word 'c1n3st1ll' at strength 0.
arXiv:2605.29365v1 Announce Type: new Abstract: Formality transfer is commonly framed as a symmetric bidirectional task between informal and formal registers. We argue that this framing conceals a sup
arXiv:2603.01311v2 Announce Type: replace Abstract: The discovery of novel catalysts tailored for particular applications is a major challenge for the twenty-first century. Traditional methods for thi
arXiv:2605.29008v1 Announce Type: new Abstract: Driving a system from one state to another through targeted interventions is a fundamental challenge in science, yet most predictive models offer limite