Knowledge catalogue
arXiv:2605.18847v1 Announce Type: cross Abstract: Do transformers, when trained on sequential reasoning traces, build internal models of the underlying task? And if so, does the structure of those int
arXiv:2605.19839v1 Announce Type: new Abstract: Preference alignment aims to guide generative models by learning from comparisons between preferred and non-preferred samples. In practice, most existin
arXiv:2605.19662v1 Announce Type: new Abstract: Tabular foundation models based on pretrained prior-data fitted networks~(PFNs) have shown strong generalization on diverse tabular tasks, but they are
arXiv:2510.10140v2 Announce Type: replace Abstract: Deep learning-based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of do
arXiv:2605.17310v1 Announce Type: cross Abstract: Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiven
arXiv:2605.17370v1 Announce Type: new Abstract: Cognitive behavioural therapy is widely used to help patients understand and manage psychological distress. It is often delivered through spoken convers
arXiv:2602.17684v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based f
arXiv:2605.18413v1 Announce Type: new Abstract: Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed
arXiv:2605.16342v1 Announce Type: cross Abstract: Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps
arXiv:2605.18635v1 Announce Type: cross Abstract: Credit default prediction is a tabular learning problem with severe class imbalance, heterogeneous features, and tight latency budgets. Tabular Founda
arXiv:2605.17527v1 Announce Type: new Abstract: Street-view imagery (SVI) is widely used to quantify key indicators of urban environment, such as green- ery, sky, or road view indices. However, existi
arXiv:2605.17489v1 Announce Type: new Abstract: Face Image Quality Assessment (FIQA) is a crucial control step in biometric pipelines. It ensures only reliable samples are processed to maintain system
arXiv:2509.06984v3 Announce Type: replace-cross Abstract: Federated Learning with LoRA fine-tuning offers an efficient and privacy-aware solution for institutions to collaboratively leverage their lar
arXiv:2605.16864v1 Announce Type: cross Abstract: Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-awa
arXiv:2602.06694v2 Announce Type: replace Abstract: Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to effi
arXiv:2605.16395v1 Announce Type: cross Abstract: We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence
arXiv:2605.16410v1 Announce Type: new Abstract: Test-time scaling (TTS) methods have proven highly effective for LLMs, yet their application to vision-language models (VLMs) remains relatively underex
arXiv:2603.04161v2 Announce Type: replace Abstract: The False Belief Test (FBT) has been the main method for assessing Theory of Mind (ToM) and related socio-cognitive competencies. For Large Language
arXiv:2605.17938v1 Announce Type: cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current
arXiv:2605.18390v1 Announce Type: new Abstract: In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (
arXiv:2605.17471v1 Announce Type: new Abstract: Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized mo
arXiv:2605.15687v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Ex
arXiv:2605.16077v1 Announce Type: new Abstract: Accurate assessment of cognitive decline from spontaneous speech remains challenging due to limited dataset size and class imbalance. In this work, we p
arXiv:2601.21798v2 Announce Type: replace Abstract: Large Language Models(LLMs) have revolutionized text generation and multimodal perception,but their capabilities in 3D content generation remain und
arXiv:2605.15477v1 Announce Type: new Abstract: Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited avail
arXiv:2605.15680v1 Announce Type: new Abstract: Online patient inquiries are often informal, incomplete, and written before professional assessment, yet they must still be routed to an appropriate lev
arXiv:2602.12262v3 Announce Type: replace Abstract: Diffusion large language models (DLLMs) have emerged as powerful generative models with the promise of fast text generation through parallel decodin
arXiv:2504.08300v5 Announce Type: replace-cross Abstract: Benchmark-based evaluation, e.g., multiple-choice questions (MCQs) and open-ended questions (OEQs), is widely used for evaluating Large Langua
arXiv:2407.02039v3 Announce Type: replace Abstract: Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a g
arXiv:2605.15467v1 Announce Type: cross Abstract: Conversational nurse-patient transcripts contain actionable observations, but converting these transcripts into structured representations at scale re
arXiv:2605.15961v1 Announce Type: new Abstract: Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these m
arXiv:2605.15996v1 Announce Type: cross Abstract: We consider the problem of testing properties of graphs underlying high-dimensional graphical models. We adopt the model of covariance queries introdu
💯. Way too much focus on language models. Fei-Fei Li warns that AI may be staring too hard at language models. The world is not just text on a screen. It is physical, visual, spatial, and always chang
arXiv:2601.03969v2 Announce Type: replace Abstract: Large reasoning models enhanced by reinforcement learning with verifiable rewards have achieved significant performance gains by extending their cha
arXiv:2506.05762v5 Announce Type: replace Abstract: Recent advances in offline Reinforcement Learning (RL) have proven that effective policy learning can benefit from imposing conservative constraints
arXiv:2601.21174v2 Announce Type: replace Abstract: Entity alignment (EA) is critical for knowledge graph (KG) fusion. Existing EA models lack transferability and are incapable of aligning unseen KGs
arXiv:2605.14544v1 Announce Type: new Abstract: Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this lab
arXiv:2605.14036v1 Announce Type: new Abstract: In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, ther
arXiv:2602.06718v2 Announce Type: replace-cross Abstract: Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Larg
arXiv:2605.14667v1 Announce Type: new Abstract: A main barrier for the deployment of AI radiomic systems in clinical routine is their drop in performance under heterogeneous multicentre acquisition pr
arXiv:2605.14828v1 Announce Type: cross Abstract: Existing clustering methods for functional data often prioritize partitioning accuracy over interpretability, making it challenging to extract meaning
arXiv:2605.14087v1 Announce Type: new Abstract: Large Language Models (LLMs), when trained on web-scale corpora, inherently absorb toxic patterns from their training data. This leads to ``toxic degene
arXiv:2605.14530v1 Announce Type: new Abstract: Large diffusion vision-language models (LDVLMs) have recently emerged as a promising alternative to autoregressive models, enabling parallel decoding fo
arXiv:2603.23129v2 Announce Type: replace Abstract: Godel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We intro
arXiv:2605.14075v1 Announce Type: cross Abstract: Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more i
arXiv:2605.11410v2 Announce Type: replace Abstract: Clinical electroencephalogram (EEG) analysis rests on a hand-crafted feature catalog refined over decades, e.g., band power, connectivity, complexit
arXiv:2605.12522v1 Announce Type: cross Abstract: Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated
arXiv:2605.13122v1 Announce Type: new Abstract: Instruction-based image editing (IIE) models have recently demonstrated strong capability in modifying specific image regions according to natural langu
arXiv:2505.18604v3 Announce Type: replace Abstract: State-Space Models (SSMs) excel at capturing long-range dependencies with structured recurrence, making them well-suited for sequence modeling. Howe
arXiv:2605.13632v1 Announce Type: cross Abstract: In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied
arXiv:2602.11202v3 Announce Type: replace-cross Abstract: Reasoning models produce long traces of intermediate decisions and tool calls, making test-time verification important for ensuring correctnes
arXiv:2605.12725v1 Announce Type: new Abstract: Recent video anomaly detection research has expanded rapidly with an emphasis on general models of normality intended to work across many different scen
arXiv:2601.21975v2 Announce Type: replace Abstract: Recent work identifies a stated-revealed (SvR) preference gap in language models (LMs): a mismatch between the values models endorse and the choices
arXiv:2605.13297v1 Announce Type: new Abstract: Periodic crystals repeatedly instantiate similar local coordination motifs across translated cells and chemically related structures, but current equiva
arXiv:2511.14056v2 Announce Type: replace-cross Abstract: We study the base distribution in chart-based generative models on Riemannian manifolds. Standard methods sample in Euclidean tangent space an
Do AI models really learn physics, or just learn what physics looks like? Flatiron's @_helenqu, with @PolymathicAI & CDS researchers including @ylecun, finds that models predicting in latent space rec
arXiv:2605.12358v1 Announce Type: new Abstract: Message-passing based approaches form the default backbone of most learning architectures on graph-structured data. However, the rapid progress of moder
arXiv:2605.12327v1 Announce Type: new Abstract: A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scal
arXiv:2605.06440v2 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier input
arXiv:2510.17062v2 Announce Type: replace Abstract: While reasoning-based large language models excel at complex tasks through an internal, structured thinking process, a concerning phenomenon has eme