Knowledge catalogue
arXiv:2602.01553v2 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While
arXiv:2605.30824v1 Announce Type: new Abstract: Deep research tasks require LLMs to plan what to investigate, retrieve evidence, and synthesize long-form answers across multiple branches of inquiry. E
arXiv:2502.12119v4 Announce Type: replace-cross Abstract: Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications
arXiv:2605.31204v1 Announce Type: new Abstract: Accurate weather forecasts are essential across various domains and are safety-critical in extreme weather conditions. Compared to simulation-based fore
arXiv:2602.11216v2 Announce Type: replace Abstract: Molecular dynamics (MD) is a central computational tool in physics, chemistry, and biology, enabling quantitative prediction of experimental observa
arXiv:2605.30358v1 Announce Type: new Abstract: Quantum computing remains in the Noisy Intermediate-Scale Quantum (NISQ) era, where the performance is highly constrained to noise. Addressing the limit
arXiv:2602.12192v3 Announce Type: replace Abstract: Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to es
arXiv:2605.31124v1 Announce Type: new Abstract: Estimating 3D attributes directly from images has advanced rapidly with the Visual Geometry Grounded Transformer (VGGT), which predicts camera parameter
arXiv:2605.31535v1 Announce Type: cross Abstract: Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of traini
arXiv:2603.17145v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known a
arXiv:2605.30587v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has significantly improved the reasoning ability of large vision-language models (LVLMs) by verbalizing intermediate re
arXiv:2605.31048v1 Announce Type: new Abstract: Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, a
arXiv:2605.31176v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems typically rely on a single retriever and a single set of hyperparameters, despite facing highly heterogeneo
arXiv:2605.30597v1 Announce Type: new Abstract: Nonlinear dimensionality-reduction methods such as UMAP and PaCMAP adaptively normalize local distances during graph construction, erasing neighborhood
arXiv:2605.31469v1 Announce Type: cross Abstract: Conversational automatic speech recognition in Hungarian is constrained by the limited amount of publicly available dialogue-style training data. The
arXiv:2511.03100v2 Announce Type: replace-cross Abstract: The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performa
arXiv:2605.31238v1 Announce Type: new Abstract: Endowing large language models with compositional reasoning over specialized documents requires multi-hop training data at scale, where such data rarely
arXiv:2602.13110v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as scalable judges in pairwise evaluation, but they remain prone to miscalibration and bias
arXiv:2605.30698v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spo
arXiv:2605.30557v1 Announce Type: cross Abstract: Spatial reasoning is a fundamental capability for vision-language models (VLMs) deployed in real-world environments. However, visual observations are
arXiv:2510.02919v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation
arXiv:2605.31550v1 Announce Type: new Abstract: Table question answering requires models to recover semantic relations encoded implicitly by two-dimensional layout, merged cells, and hierarchical head
arXiv:2605.30729v1 Announce Type: new Abstract: Schema matching is a fundamental step in integrating heterogeneous data sources. While Pre-trained Language Models (PLMs) have revolutionized this task
arXiv:2601.05134v2 Announce Type: replace Abstract: Certified unlearning based on differential privacy offers strong guarantees but remains largely impractical: the noisy fine-tuning approaches propos
arXiv:2506.08255v4 Announce Type: replace-cross Abstract: Continual learning under adversarial conditions remains an open problem, as existing methods often compromise either robustness, scalability,
arXiv:2605.30832v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models have significantly improved chain-of-thought (CoT) capabilities via reinforcement learning (RL). However, gene
arXiv:2605.30396v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) is a promising neural scene representation for real-time rendering, but trained models often suffer from large memory foo
arXiv:2605.30789v1 Announce Type: cross Abstract: We identify a new dimension for enhancing rollout diversity in Group Relative Policy Optimization (GRPO) for LLMs. While GRPO relies on diverse rollou
arXiv:2605.31148v1 Announce Type: cross Abstract: Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into ac
arXiv:2605.30662v1 Announce Type: new Abstract: Spatio-temporal graph-based models have typically been used to forecast new cases of infectious diseases such as COVID-19 and chickenpox outbreaks. Howe
arXiv:2602.06161v2 Announce Type: replace-cross Abstract: Parallel diffusion decoding can accelerate diffusion language model inference by unmasking multiple tokens per step, but aggressive parallelis
arXiv:2605.30383v1 Announce Type: cross Abstract: Scaling individual robot capabilities is common but costly. Here we investigate a system-level design question in real-world multi-robot coordination:
arXiv:2605.31111v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs) learn compact latent world models by predicting future embeddings, but no single coordinate of the late
arXiv:2605.31577v1 Announce Type: new Abstract: Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still exhibi
arXiv:2605.31273v1 Announce Type: new Abstract: While self-supervised Contrastive Reinforcement Learning (CRL) has shown remarkable depth-scaling capabilities, successfully using networks over 64 laye
arXiv:2505.17607v3 Announce Type: replace Abstract: Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret
arXiv:2511.11440v3 Announce Type: replace-cross Abstract: Performance gains of Vision Language Models (VLMs) obtained by fine-tuning are generally based on ad hoc data collection and annotation of rea
arXiv:2503.21168v3 Announce Type: replace Abstract: Robots navigating human-populated environments must avoid collisions while respecting the social structure of crowds, particularly the implicit boun
arXiv:2605.30601v1 Announce Type: new Abstract: Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due to excessive or poorly structured input sensitivit
arXiv:2601.09633v2 Announce Type: replace Abstract: Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce and semantic se
arXiv:2605.30888v1 Announce Type: new Abstract: Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference
arXiv:2603.00068v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined eve
arXiv:2602.04031v2 Announce Type: replace Abstract: Tabular Language Models (TLMs) have been claimed to achieve strong generalization for tabular prediction. We conduct a systematic re-evaluation of T
arXiv:2605.31192v1 Announce Type: new Abstract: Recently, thanks to the advent of Multimodal-LLMs, deepfake detectors are striving not only to be generalizable but also interpretable. We propose that
arXiv:2605.31025v1 Announce Type: new Abstract: In real-world deployment, LLMs are often adapted continually across tasks to keep LLMs up-to-date in production, where new fine-tuning should preserve p
arXiv:2605.30693v1 Announce Type: cross Abstract: Building robust safety guardrails is essential for deploying Large Language Models across diverse real-world applications. However, this goal remains
arXiv:2605.31590v1 Announce Type: cross Abstract: Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intri
arXiv:2502.04554v2 Announce Type: replace Abstract: Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection
arXiv:2510.15710v3 Announce Type: replace Abstract: Medical workflows routinely combine reading images with producing visual and textual outputs, making both image understanding and generation central
arXiv:2509.24901v4 Announce Type: replace-cross Abstract: Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursu
arXiv:2602.03639v2 Announce Type: replace Abstract: Sampling-based controllers, such as Model Predictive Path Integral (MPPI) methods, offer substantial flexibility but often suffer from high variance
arXiv:2605.31100v1 Announce Type: new Abstract: We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model ob
arXiv:2605.30451v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision
arXiv:2508.20478v2 Announce Type: replace Abstract: Long-form video understanding, characterized by long-range temporal dependencies and multiple events, remains a challenge. Existing methods often re
arXiv:2512.11561v2 Announce Type: replace Abstract: Generalizing pretrained models to unseen datasets without retraining is a central challenge toward foundation models. Achieving fully inductive infe
arXiv:2605.31226v1 Announce Type: cross Abstract: Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static
arXiv:2605.30911v1 Announce Type: cross Abstract: Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinat
arXiv:2603.10422v2 Announce Type: replace Abstract: World Models (WMs) offer a promising mechanism for post-training Vision-Language-Action (VLA) policies by providing dynamics priors that improve gen
arXiv:2605.30671v1 Announce Type: new Abstract: Recovering ego-camera orientation from manipulation video is a prerequisite for disentangling hand motion from camera motion, a key step in imitation le
arXiv:2605.31429v1 Announce Type: new Abstract: Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard