Knowledge catalogue
arXiv:2608.27397v1 Announce Type: cross Abstract: Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g.,
arXiv:2508.06753v3 Announce Type: replace Abstract: The advent of ultra-low-bit LLM models, approaching the perplexity and task accuracy of their full precision counterparts, is ushering in a new era
arXiv:2608.26872v1 Announce Type: new Abstract: On-policy distillation (OPD), which leverages a pre-trained, specialized teacher model to provide dense supervisory signals, has achieved significant su
arXiv:2608.27147v1 Announce Type: new Abstract: The development of frontier models is commonly perceived to be the exclusive remit of a small number of heavily funded players, creating an information,
arXiv:2608.25572v1 Announce Type: new Abstract: Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors u
arXiv:2608.24934v1 Announce Type: new Abstract: Accurate field plant disease diagnosis requires reliable fusion of uncertain and conflicting perceptual evidence. We present the Hybrid Hierarchical Mul
arXiv:2509.02855v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to produce open-ended, interpretive annotations, yet there is no validated, scalable measure of i
arXiv:2608.25231v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-
arXiv:2608.25485v1 Announce Type: new Abstract: Vision-language models like CLIP have shown sig- nificant potential in handling natural images, yet their perfor- mance is often limited by the distinct
arXiv:2608.24885v1 Announce Type: cross Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an
arXiv:2608.24192v1 Announce Type: new Abstract: Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastro
arXiv:2608.24500v1 Announce Type: cross Abstract: The STAR (Student-Teacher Achievement Ratio) experiment (1985, Tennessee, USA) is a landmark hierarchical dataset designed to assess the impact of cla
arXiv:2608.21480v1 Announce Type: cross Abstract: A Markov chain is a widely used stochastic process modelling random events over time. These models are built on subsets of the entire dataset, referre
arXiv:2506.20073v2 Announce Type: replace-cross Abstract: Spatio-temporal data mining plays a pivotal role in informed decision making across diverse domains. However, existing models are often restri
arXiv:2608.21880v1 Announce Type: new Abstract: Bangla large language model (LLM) safety is difficult to evaluate with English-centric or standard-script benchmarks because Bangla users routinely writ
arXiv:2608.22294v1 Announce Type: new Abstract: World models for physical interaction are typically trained to predict future observations or latent features; however, a planning-oriented model must a
arXiv:2608.21740v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are typically trained with behavior cloning (BC) on expert demonstrations. However, BC provides only positive superv
arXiv:2608.21584v1 Announce Type: new Abstract: We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By
arXiv:2606.17904v2 Announce Type: replace Abstract: Language models increasingly serve as advisory systems in maintenance operations. To prevent hallucination, recent systems ground these models in pr
arXiv:2608.21803v1 Announce Type: cross Abstract: As machine learning (ML) models are increasingly deployed in high-stakes environments, explainable AI (XAI) methods like SHAP and LIME have become ess
arXiv:2608.23486v1 Announce Type: new Abstract: World action models (WAMs) have recently gained increasing attention as a framework for jointly modeling scene evolution and ego actions in autonomous d
arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image i
arXiv:2608.22138v1 Announce Type: new Abstract: Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present
arXiv:2608.22323v1 Announce Type: new Abstract: The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus
arXiv:2608.22154v1 Announce Type: new Abstract: Researchers must often choose between Bayesian or neural network models of behavior, two paradigms with complementary strengths and weaknesses. An ideal
arXiv:2608.21487v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) exhibit strong zero-shot capabilities, making them an attractive solution for continual learning across diverse tasks. H
// There Is No Neutral Harness // Great work discussing some of the issues in harness evaluation. Twelve open-weight models answer the same 3,679 items from ARC, HellaSwag, MMLU, and TruthfulQA under
Top open models by use case 👇 chat - Kimi K3, Qwen3.8 2.4T A95B reasoning - Kimi K3, DeepSeek V4 Pro coding agents - Kimi K3, DeepSeek V4 Flash, GLM 5.2 small + fast - Qwen3.8 27B, gpt-oss 20B mid-siz
arXiv:2608.22948v1 Announce Type: cross Abstract: Large language models are increasingly used to propose research ideas, yet the prevailing ways of judging such ideas supply no shared decision rule: f
arXiv:2608.22421v1 Announce Type: new Abstract: World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic pre
arXiv:2608.20960v1 Announce Type: new Abstract: Language models (LMs) are trained on static scientific corpora, whereas scientific knowledge continuously evolves through correction and revision. Scien
arXiv:2608.21107v1 Announce Type: new Abstract: Large Language Models (LLMs) are moving from code completion toward repository-scale agents that retrieve context, edit files, execute tools, and partic
arXiv:2608.21100v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) extend model capabilities beyond text, they also make safety alignment increasingly challenging. Multimod
arXiv:2608.20414v1 Announce Type: new Abstract: Vision-language models are increasingly used for multimodal question answering, yet their ability to reconstruct latent spatial structure from a single
It is not inherently bad to publish research on the impact of AI that only refers to older models, but it requires a very careful discussion and has to be very clear to non-technical readers. If you s
arXiv:2608.19804v1 Announce Type: new Abstract: Buildings account for roughly one-third of global energy consumption and CO_2 emissions. Optimizing indoor climate systems plays a critical role for urb
arXiv:2608.19299v1 Announce Type: new Abstract: Air traffic control (ATC) communication is a safety-critical dialogue that remains largely human-driven even as other parts of air traffic management ha
arXiv:2606.15910v2 Announce Type: replace Abstract: A vision-language model can answer a question about a chest radiograph or a pathology slide fluently and confidently while barely using the image, r
arXiv:2608.20319v1 Announce Type: cross Abstract: Naturalistic computer-use traces, passively recorded screenshots and mouse or keyboard actions, are a valuable resource for deriving symbolic, auditab
arXiv:2607.14497v2 Announce Type: replace Abstract: Egocentric Visual Question Answering (VQA) has attracted widespread attention as an important task for enabling Multimodal Large Language Models (ML
arXiv:2608.19737v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and im
arXiv:2608.18103v1 Announce Type: cross Abstract: Background: Mechanistic elucidation of traditional Chinese medicine (TCM) compound formulas remains a central challenge in the modernization of TCM. C
arXiv:2512.05092v2 Announce Type: replace-cross Abstract: Although diffusion models now occupy a central place in generative modeling, introductory treatments commonly assume Euclidean data and seldom
arXiv:2608.18849v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and
GLM-5.3 (Max) by @Zai_org has shifted the Pareto frontier for Code Arena: WebDev! GLM-5.3 (Max) would sit at #2 among open models (upon open weights release, and #8 overall) with 1597 pts in the Code
arXiv:2608.18171v1 Announce Type: new Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We stu
arXiv:2608.18631v1 Announce Type: new Abstract: As large language models evolve into decision-making agents, the ability to reason over preferences becomes fundamental to alignment, coordination, and
arXiv:2608.18237v1 Announce Type: cross Abstract: Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise natur
arXiv:2608.18144v1 Announce Type: cross Abstract: Modal auxiliaries such as must, should, and have to mark necessity and obligation within the contexts of speaker authority and interpersonal stance. W
arXiv:2608.18940v1 Announce Type: cross Abstract: Single-step retrosynthesis is a central component of computer-aided synthesis planning, yet its intrinsically one-to-many nature is poorly captured by
arXiv:2608.18671v1 Announce Type: new Abstract: Egocentric video captures activities from the wearer's perspective, providing a direct view of human attention, hand--object interaction, and goal-direc
arXiv:2608.17895v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) have made significant strides in visual comprehension, their ability to reason about text-dense, profes
arXiv:2608.17796v1 Announce Type: cross Abstract: Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which
arXiv:2608.17516v1 Announce Type: new Abstract: Gender bias or other social biases in large language models (LLMs) are frequently evaluated with question answering or survey benchmarks where the LLM n
arXiv:2608.17600v1 Announce Type: new Abstract: Visual cues are increasingly adopted to guide robot learning, but whether Vision-Language-Action (VLA) models can reliably follow authorized cues while
arXiv:2608.17695v1 Announce Type: new Abstract: Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact
Sovereign AI models lagging behind cutting‑edge systems risk significant disadvantages when applied to frontier tasks such as cyber defence. Ethan Mollick highlights that this penalty is most pronounc
arXiv:2608.16614v1 Announce Type: new Abstract: Geospatial Foundation Models (GeoFMs) are most commonly ranked and selected by accuracy on standard benchmark conditions via averaged ranks. We show tha
arXiv:2608.16829v1 Announce Type: cross Abstract: Video world models approximate the stochastic distribution of physical outcomes through generative sampling, but existing benchmarks score individual
arXiv:2608.15507v1 Announce Type: new Abstract: A consistent concept of the current time is important for temporal reasoning, yet how language models represent the current time is not well understood.