Knowledge catalogue
arXiv:2605.29446v1 Announce Type: new Abstract: Miller-index identification from powder XRD patterns requires capabilities untested by existing multimodal benchmarks: the model must read a narrow peak
arXiv:2511.11505v3 Announce Type: replace Abstract: Blocking communication presents a major hurdle in running MoEs efficiently in distributed settings. To address this, we present FarSkip-Collective w
arXiv:2605.29459v1 Announce Type: new Abstract: Large language models route every input through a learned embedding table of shape |V| x d_model, consuming hundreds of millions to billions of trainabl
arXiv:2605.29714v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting rem
arXiv:2605.30263v1 Announce Type: new Abstract: Recent video diffusion foundation models have achieved remarkable progress in high-quality video generation, yet turning them into real-time interactive
arXiv:2603.23971v2 Announce Type: replace-cross Abstract: Developers and consumers increasingly choose reasoning models (RMs) based on their listed API prices. However, how accurately do these prices
arXiv:2605.28070v1 Announce Type: new Abstract: We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified
arXiv:2605.27764v1 Announce Type: cross Abstract: Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instruc
arXiv:2605.27773v1 Announce Type: cross Abstract: When a language model sees a document contradicting its training knowledge, it must choose: follow the document or trust itself. Prior work proved thi
arXiv:2601.01627v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) are increasingly deployed in healthcare field, it becomes essential to carefully evaluate their medical safety
models being conscious would be harmful for humanity. it would encroach on our status and dignity. it would limit the type of things we can do with them and use them for. it would vastly accelerate hu
arXiv:2603.17218v2 Announce Type: replace-cross Abstract: Post-training alignment optimizes language models to match human preference signals, but this objective is not equivalent to modeling observed
arXiv:2605.26937v1 Announce Type: cross Abstract: Parametric knowledge in large language models (LLMs) is a cornerstone of their success, yet remains poorly understood. Existing knowledge benchmarks t
arXiv:2605.26292v1 Announce Type: cross Abstract: Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing
arXiv:2605.24045v1 Announce Type: cross Abstract: Protein-ligand modeling underpins computational drug discovery and molecular design. Existing protein-ligand benchmarks typically evaluate whether a p
arXiv:2605.26038v1 Announce Type: cross Abstract: Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objec
arXiv:2605.24686v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly integrated into emotionally sensitive domains, the structural integrity of their emotional intelligence
arXiv:2502.11167v5 Announce Type: replace-cross Abstract: Neural surrogate models are powerful and efficient tools in data mining. Meanwhile, large language models (LLMs) have demonstrated remarkable
arXiv:2605.25601v1 Announce Type: cross Abstract: Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language model
arXiv:2509.04445v2 Announce Type: replace Abstract: Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using stand
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM
arXiv:2502.17119v2 Announce Type: replace-cross Abstract: Deep generative models have made rapid progress in image, text, audio, and video generation, and are increasingly being applied to structured
arXiv:2605.22826v1 Announce Type: cross Abstract: Quantifying the deceptive potential of Large Language Models (LLMs) is critical for AI safety, yet difficult to achieve in uncontrolled environments.
arXiv:2605.22537v1 Announce Type: new Abstract: Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, models produce completions to a set of prompts, wh
arXiv:2510.08759v2 Announce Type: replace Abstract: Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, exi
arXiv:2602.02112v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality dep
arXiv:2510.00520v2 Announce Type: replace Abstract: Foundation models are reshaping medical imaging, yet their application in echocardiography remains limited, hindered by a heavy reliance on private
arXiv:2602.02304v2 Announce Type: replace-cross Abstract: Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning w
arXiv:2605.20345v1 Announce Type: cross Abstract: Latent Gaussian models (LGMs) are a popular class of Bayesian hierarchical models that include Gaussian processes, as well as certain spatial models a
arXiv:2605.20523v1 Announce Type: new Abstract: Advanced fibrosis is a major determinant of liver-related morbidity in metabolic dysfunction-associated steatotic liver disease (MASLD). FIB-4 is widely
arXiv:2605.20873v1 Announce Type: cross Abstract: Planning is a fundamental capability for large language models (LLMs) because such complex tasks require models to coordinate goals, constraints, reso
arXiv:2504.13109v2 Announce Type: replace Abstract: Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are
arXiv:2602.18532v2 Announce Type: replace Abstract: Following the rise of large foundation models, Vision-Language-Action models (VLAs) emerged, leveraging strong visual and language understanding fro
arXiv:2601.16823v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genu
Model swaps look like configuration changes, but they behave more like product migrations. A new model may be cheaper, faster, easier to get capacity for, or stronger on public benchmarks.... The post
arXiv:2601.11895v3 Announce Type: replace-cross Abstract: DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,8
arXiv:2605.17070v1 Announce Type: new Abstract: While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, existing benchmarks often rely on que
arXiv:2605.18663v1 Announce Type: new Abstract: As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or remo
I remember when people were saying 'It's useless to open-source big models because nobody will be able to run them fast'.... Cerebras is now running Kimi K2.6 – a trillion parameter model – in enterpr
arXiv:2605.18253v1 Announce Type: cross Abstract: Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models
arXiv:2605.17932v1 Announce Type: cross Abstract: Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive archite
arXiv:2605.17985v1 Announce Type: cross Abstract: We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential
arXiv:2605.18160v1 Announce Type: cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrati
arXiv:2505.21698v3 Announce Type: replace Abstract: Vision-language foundation models achieve promising performance in natural image classification, yet their direct application to medical imaging is
arXiv:2602.20207v3 Announce Type: replace-cross Abstract: Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserv
arXiv:2605.15618v1 Announce Type: cross Abstract: Self-supervised video models are increasingly framed as world models, yet their evaluation remains largely confined to a single top-1 accuracy score o
arXiv:2505.18134v3 Announce Type: replace Abstract: Vision-language models (VLMs) have achieved strong results on coding and math benchmarks that are challenging for humans, yet their ability to perfo
arXiv:2605.14698v1 Announce Type: cross Abstract: Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including
arXiv:2501.05465v2 Announce Type: replace Abstract: As foundation AI models continue to increase in size, an important question arises - is massive scale the only path forward? This survey of about 16
arXiv:2605.12746v1 Announce Type: cross Abstract: Monitoring the chain-of-thought (CoT) of reasoning models is a promising approach for detecting covert misbehavior (i.e., hidden objectives) in code g
arXiv:2605.13276v1 Announce Type: new Abstract: The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applyi
arXiv:2605.12920v1 Announce Type: cross Abstract: Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's e
arXiv:2605.12835v1 Announce Type: new Abstract: Large language models can extract local causal claims from text, but those claims become more useful when organized as persistent, navigable world model
arXiv:2605.13369v1 Announce Type: cross Abstract: Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often improved by allocating more computation at i
arXiv:2605.13302v1 Announce Type: new Abstract: This paper extends safety guarantees for multi-task Bayesian optimization with uncertain correlation matrices from intrinsic co-reginalization models to
arXiv:2605.12684v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of thes
arXiv:2602.22347v2 Announce Type: replace Abstract: Foundation models for computational pathology are expected to facilitate the development of high-performing, generalisable deep learning systems. Ho
arXiv:2601.16836v3 Announce Type: replace-cross Abstract: Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to a
arXiv:2605.08942v1 Announce Type: new Abstract: Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies
arXiv:2410.02543v3 Announce Type: replace-cross Abstract: In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms. By considering evolution as a d