Knowledge catalogue
arXiv:2604.10326v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks -- inputs designed to bypass safety mechanisms and elicit harmful responses -- despite ad
arXiv:2604.11246v1 Announce Type: new Abstract: Evaluating the quality of model responses remains challenging in generative tasks with long-form answers, as the expected answers usually contain multip
arXiv:2604.09922v1 Announce Type: cross Abstract: Subsurface stratigraphy contains important spatio-temporal information about accumulation, deformation, and layer formation in polar ice sheets. In pa
arXiv:2604.11011v1 Announce Type: cross Abstract: We present this as a negative result with an explanatory mechanism, not as a formal upper bound. Predictive coding networks (PCNs) admit a K-way energ
arXiv:2508.20567v2 Announce Type: replace Abstract: Multi-hop question answering faces substantial challenges due to data sparsity, which increases the likelihood of language models learning spurious
arXiv:2604.09800v1 Announce Type: new Abstract: This paper presents an analytical framework to study the geometry arising when a soft continuum arm grasps a planar object. Both the arm centerline and
arXiv:2506.23471v2 Announce Type: replace-cross Abstract: The global fashion e-commerce industry has become integral to people's daily lives, leveraging technological advancements to offer personalize
arXiv:2604.11744v1 Announce Type: new Abstract: Kullback-Leibler (KL) divergence is a fundamental concept in information theory that quantifies the discrepancy between two probability distributions. I
arXiv:2604.10580v1 Announce Type: new Abstract: Spoken meaning often depends not only on what is said, but also on which word is emphasized. The same sentence can convey correction, contrast, or clari
arXiv:2602.09667v2 Announce Type: replace Abstract: Integrating domain knowledge into neural networks is a central challenge in scientific machine learning. Three paradigms have emerged -- data-driven
arXiv:2604.11066v1 Announce Type: new Abstract: We present KS-PRET-5M, the largest publicly available pretraining dataset for the Kashmiri language, comprising 5,090,244 (5.09M) words, 27,692,959 (27.
arXiv:2509.20128v2 Announce Type: replace-cross Abstract: Audio-driven facial animation has made significant progress in multimedia applications, with diffusion models showing strong potential for tal
arXiv:2604.09554v1 Announce Type: new Abstract: Optimism for accelerating scientific discovery with AI continues to grow. Current applications of AI in scientific research range from training dedicate
arXiv:2506.06248v2 Announce Type: replace Abstract: Equilibrium Propagation (EP) is a learning algorithm for training Energy-based Models (EBMs) on static inputs which leverages the variational descri
arXiv:2406.13621v2 Announce Type: replace Abstract: Commonsense reasoning often requires both textual and visual knowledge, yet Large Language Models (LLMs) trained solely on text lack visual groundin
arXiv:2604.11748v1 Announce Type: new Abstract: Continuous diffusion models have achieved strong performance across domains such as images. However, in language modeling, prior continuous diffusion la
arXiv:2604.10637v1 Announce Type: new Abstract: Object detection in hazy environments is challenging because degraded objects are nearly invisible and their semantics are weakened by environmental noi
arXiv:2405.11597v2 Announce Type: replace-cross Abstract: Many recent studies have shown that the perception of speech can be decoded from brain signals and subsequently reconstructed as continuous la
arXiv:2507.14800v2 Announce Type: replace-cross Abstract: With the advanced reasoning, contextual understanding, and information synthesis capabilities of large language models (LLMs), a novel paradig
arXiv:2502.13166v3 Announce Type: replace-cross Abstract: In the era of noisy intermediate-scale quantum (NISQ) computing, Quantum Neural Networks (QNNs) have emerged as a promising approach for vario
arXiv:2603.10079v2 Announce Type: replace Abstract: Large loss spikes in stochastic gradient descent are studied through a rigorous large-deviations analysis for a shallow, fully connected network in
arXiv:2604.11689v1 Announce Type: new Abstract: While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A
arXiv:2604.10417v1 Announce Type: new Abstract: In recent years, aspect-based sentiment analysis (ABSA) has made rapid progress and shown strong practical value. However, existing research and benchma
arXiv:2604.09909v1 Announce Type: new Abstract: We study last-iterate convergence of SGD with greedy step size over smooth quadratics in the interpolation regime, a setting which captures the classica
arXiv:2604.09712v1 Announce Type: cross Abstract: Spatial reasoning is a cornerstone capability for intelligent systems to perceive and interact with the physical world. However, multimodal large lang
arXiv:2603.02028v2 Announce Type: replace Abstract: Vision transformers have shown outstanding performance in image generation, yet their adoption in fluid dynamics remains limited. We introduce the L
arXiv:2604.10403v1 Announce Type: new Abstract: We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when give
arXiv:2604.07382v2 Announce Type: replace-cross Abstract: The geometric structure of latent representations in large language models (LLMs) is an active area of research, driven in part by its implica
arXiv:2509.21042v3 Announce Type: replace Abstract: Causal self-attention provides positional information to Transformer decoders. Prior work has shown that stacks of causal self-attention layers alon
arXiv:2604.11613v1 Announce Type: cross Abstract: Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class
arXiv:2604.11091v1 Announce Type: new Abstract: Prompt-based class-incremental learning methods typically construct a prompt pool consisting of multiple trainable key-prompts and perform instance-leve
arXiv:2512.20563v2 Announce Type: replace-cross Abstract: Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust close
arXiv:2604.11355v1 Announce Type: new Abstract: LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-bas
arXiv:2604.09955v1 Announce Type: new Abstract: Video Unsupervised Domain Adaptation (VUDA) poses a significant challenge in action recognition, requiring the adaptation of a model from a labeled sour
arXiv:2604.10573v1 Announce Type: new Abstract: Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied
arXiv:2509.21879v2 Announce Type: replace Abstract: Despite Neural Ordinary Differential Equations (Neural ODEs) exhibiting intrinsic robustness, existing methods often impose Lyapunov stability for f
arXiv:2604.10667v1 Announce Type: cross Abstract: Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limit
arXiv:2604.11311v1 Announce Type: new Abstract: Diffusion-based models on continuous spaces have seen substantial recent progress through the mathematical framework of gradient flows, leveraging the W
arXiv:2604.11365v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain ineffici
arXiv:2604.10150v1 Announce Type: new Abstract: Generative listwise reranking leverages global context for superior retrieval but is plagued by intrinsic position bias, where models exhibit structural
arXiv:2505.24665v2 Announce Type: replace Abstract: Real world data often lie on low-dimensional Riemannian manifolds embedded in high-dimensional spaces. This motivates learning degenerate normalizin
arXiv:2604.10075v1 Announce Type: new Abstract: Text-to-CAD code generation is a long-horizon task that translates textual instructions into long sequences of interdependent operations. Existing metho
arXiv:2604.11473v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures offer a scalable path for Graph Neural Networks (GNNs) in node classification tasks but typically rely on static
arXiv:2604.11737v1 Announce Type: new Abstract: Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scen
arXiv:2604.09664v1 Announce Type: cross Abstract: The non-equilibrium dynamics of mesoscale phase transitions are fundamentally shaped by thermal fluctuations, which not only seed instabilities but ac
arXiv:2604.10783v1 Announce Type: new Abstract: Designing reward functions remains a central challenge in reinforcement learning (RL) for healthcare, where outcomes are sparse, delayed, and difficult
arXiv:2604.11349v1 Announce Type: new Abstract: Accurate dynamic models for racket-ball bounces are essential for reliable control in robotic table tennis. Existing models typically assume simple line
arXiv:2604.11590v1 Announce Type: new Abstract: Nowadays, pretrained models are increasingly used as general-purpose backbones and adapted at test-time to downstream environments where target data are
arXiv:2604.10946v1 Announce Type: new Abstract: Transformer models have become foundational across a wide range of scientific and engineering domains due to their strong empirical performance. A key c
arXiv:2603.11346v2 Announce Type: replace Abstract: Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking w
arXiv:2603.27494v2 Announce Type: replace-cross Abstract: To enhance the perception and reasoning capabilities of multimodal large language models in complex visual scenes, recent research has introdu
arXiv:2604.05165v2 Announce Type: replace Abstract: Reconfigurable Intelligent Surfaces (RIS) has a potential to engineer smart radio environments for next-generation millimeter-wave (mmWave) networks
arXiv:2604.11306v1 Announce Type: cross Abstract: Robots must verbalize their past experiences when users ask 'Where did you put my keys?' or 'Why did the task fail?' Yet maintaining life-long episodi
arXiv:2503.15481v3 Announce Type: replace-cross Abstract: Towards the grand challenge of achieving human-level manipulation in robots, playing piano is a compelling testbed that requires strategic, pr
arXiv:2604.10967v1 Announce Type: new Abstract: Many safety-critical scientific and engineering systems evolve according to differential-algebraic equations (DAEs), where dynamical behavior is constra
arXiv:2603.11164v2 Announce Type: replace-cross Abstract: We present a new self-supervised machine learning approach for symbolic simplification of complex mathematical expressions. Training data is g
arXiv:2511.18322v3 Announce Type: replace-cross Abstract: Learning soft continuum robot (SCR) dynamics from video offers flexibility but existing methods lack interpretability or rely on prior assumpt
arXiv:2604.09787v1 Announce Type: cross Abstract: Data collected from the physical world is always a combination of multiple sources: an underlying signal from the physical process of interest and a s
arXiv:2510.14884v3 Announce Type: replace-cross Abstract: In high-stakes AI applications, even a single action can cause irreparable damage. However, nearly all of sequential decision-making theory as
arXiv:2505.21996v3 Announce Type: replace-cross Abstract: Foundational world models must be both interactive and preserve spatiotemporal coherence for effective future planning with action choices. Ho