Multimodal LLMs under Pairwise Modalities
arXiv:2605.21059v1 Announce Type: new Abstract: Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data,
Knowledge catalogue
arXiv:2605.21059v1 Announce Type: new Abstract: Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data,
arXiv:2602.24138v2 Announce Type: replace Abstract: Automated recognition of surgical phases and steps is a fundamental capability for intraoperative decision support, workflow automation, and skill a
arXiv:2605.21081v1 Announce Type: cross Abstract: This study aims to enhance the quality of music generation using Transformers by incorporating meta-information. While Transformer-based approaches ar
arXiv:2605.20209v1 Announce Type: cross Abstract: Achieving precise, versatile whole-body character control in physics-based animation remains challenging. Recent diffusion-based policies generate ric
arXiv:2605.20879v1 Announce Type: new Abstract: Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain 'one-for-all' detection, but existing GGAD methods pred
arXiv:2605.20302v1 Announce Type: cross Abstract: Supervised classification has a theoretical optimum, Neural Collapse (NC), yet neither of its two dominant paradigms reaches it in practice. Cross ent
arXiv:2605.20187v1 Announce Type: new Abstract: Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these mode
arXiv:2605.21437v1 Announce Type: cross Abstract: Standard approaches to forecasting the weekly number of earthquakes on a spatial grid rely on the Poisson distribution with a single global dispersion
arXiv:2605.20525v1 Announce Type: cross Abstract: We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,9
arXiv:2605.20389v1 Announce Type: new Abstract: Functional MRI data exhibit high-dimensional spatiotemporal structure, making both prediction and decoding challenging. In this work, we investigate neu
arXiv:2605.21263v1 Announce Type: new Abstract: Firms increasingly rely on dynamic pricing to respond to evolving customer demand, yet in many applications they observe only the revenue generated by a
arXiv:2605.21343v1 Announce Type: new Abstract: Recent layout-to-image models have achieved remarkable progress in spatial controllability. However, they still struggle with inter-object occlusion. Wh
arXiv:2605.21226v1 Announce Type: new Abstract: The key-value (KV) cache dominates memory bandwidth and footprint in long-context autoregressive inference. Recent rotation-preconditioned codecs (Turbo
arXiv:2605.20804v1 Announce Type: new Abstract: We present a set of improvements to the OlmoEarth family. These improvements allow us to cut compute costs during training (1.7 imes reduction in GPU ho
arXiv:2605.20276v1 Announce Type: new Abstract: The global deployment of edge intelligence operates across heterogeneous legal frameworks. While some regions permit centralized learning (CL) via cloud
arXiv:2605.21260v1 Announce Type: new Abstract: We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain ru
arXiv:2605.20668v1 Announce Type: new Abstract: With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remai
arXiv:2605.21388v1 Announce Type: new Abstract: Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largel
arXiv:2312.01386v2 Announce Type: replace Abstract: Gaussian process upper confidence bound (GP-UCB) is widely used for sequential optimization of expensive black-box functions. Although many upper bo
arXiv:2603.01406v2 Announce Type: replace Abstract: Neural PDE solvers are often described as learning solution operators that map problem data to PDE solutions. In this work, we argue that this inter
arXiv:2605.21484v1 Announce Type: new Abstract: Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass th
arXiv:2509.09946v2 Announce Type: replace Abstract: Multi-Target Multi-Camera Tracking (MTMC) is an essential computer vision task for automating large-scale surveillance. With camera calibration and
arXiv:2605.20515v1 Announce Type: new Abstract: Modern artificial intelligence systems require calibrated uncertainty estimates that remain reliable in sequential and non-stationary environments. Onli
arXiv:2605.20539v1 Announce Type: new Abstract: The advent of machine learning (ML) and computer vision has significantly accelerated seismic inversion workflows by reducing the computational cost of
arXiv:2410.15761v4 Announce Type: replace Abstract: Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection, particularly in extractive question answeri
arXiv:2409.04777v4 Announce Type: replace Abstract: Large Language Models have driven significant AI advancements, yet their training is resource-intensive and highly sensitive to hyper-parameter sele
arXiv:2605.21322v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without centralizing data. However, real-world deployments must simultaneously address stat
arXiv:2605.20479v1 Announce Type: new Abstract: Hyperparameter prediction is a critical practical bottleneck for model-based image denoisers, ranging from classical TV/TGV variational solvers to moder
arXiv:2605.21417v1 Announce Type: new Abstract: Blended emotion recognition is challenging because emotions are often expressed as mixtures of subtle and overlapping multimodal cues rather than a sing
arXiv:2605.20818v1 Announce Type: new Abstract: In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 20
arXiv:2605.20751v1 Announce Type: new Abstract: Effective diabetes management requires continuous monitoring of glycemic levels. Clinically, glycemic control is assessed using metrics such as Time in
arXiv:2605.20941v1 Announce Type: new Abstract: We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on e
arXiv:2605.20194v1 Announce Type: new Abstract: Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when ana
arXiv:2602.06862v2 Announce Type: replace Abstract: Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to
arXiv:2605.20342v1 Announce Type: new Abstract: Training large multimodal models (LMMs) via reinforcement learning (RL) to natively invoke video-processing tools (e.g., cropping) has become a promisin
arXiv:2605.20640v1 Announce Type: new Abstract: Text-to-image diffusion models often face a severe trilemma in human portrait generation: text-image alignment, photorealism, and human-perceived aesthe
arXiv:2605.21053v1 Announce Type: new Abstract: Addressing the global caregiver shortage through socially assistive robots necessitates a deep understanding of their psychological and physiological im
arXiv:2602.04876v2 Announce Type: replace Abstract: We introduce PerpetualWonder, a hybrid generative simulator that enables long-horizon, action-conditioned 4D scene generation from a single image. C
arXiv:2409.08700v2 Announce Type: replace Abstract: Early detection of chronic and Non-Communicable Diseases (NCDs) is crucial for effective treatment during the initial stages. This study explores th
arXiv:2605.21207v1 Announce Type: new Abstract: The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained
arXiv:2605.20250v1 Announce Type: new Abstract: Accurate simulation of fluid flow in porous media is challenging due to complex pore-space geometries and the computational cost of solving the Navier-S
arXiv:2605.20459v1 Announce Type: new Abstract: In recent years, there has been a notable increase in the level of attention that is given to algorithms based on deep learning in the context of medica
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:2605.20496v1 Announce Type: cross Abstract: The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively
arXiv:2605.21006v1 Announce Type: cross Abstract: We study the effect of different persona on extbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation,
arXiv:2605.20863v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has recently unlocked strong reasoning capabilities in large language models (LLMs), triggering
arXiv:2605.20289v1 Announce Type: new Abstract: ANN-to-SNN conversion offers a practical, training-free route to spiking large language models. However, current pipelines primarily focus on spike-driv
arXiv:2605.20978v1 Announce Type: new Abstract: Graph Network Simulators (GNSs) have emerged as powerful surrogates for complex physics-based simulation, offering inherent differentiability and orders
arXiv:2605.21414v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation by leveraging large pretrained vision-languag
arXiv:2605.21428v1 Announce Type: new Abstract: We study the task of agnostic learning of multiclass linear classifiers under the Gaussian distribution. Given labeled examples (x, y) from a distributi
arXiv:2605.21391v1 Announce Type: new Abstract: Metaphor requires a language model to resolve a token whose contextual meaning diverges from its basic literal sense. Understanding how transformer mode
arXiv:2603.23890v2 Announce Type: replace-cross Abstract: As the modern microservice architecture for cloud applications grows in popularity, cloud services are becoming increasingly complex and more
arXiv:2205.13524v4 Announce Type: replace Abstract: We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant bord
arXiv:2605.21422v1 Announce Type: new Abstract: As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by a
arXiv:2605.21225v1 Announce Type: new Abstract: We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it f
arXiv:2603.10726v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previousl
arXiv:2605.20961v1 Announce Type: new Abstract: Existing 4D-driven video diffusion models primarily target plausible generation, but faithful 4D editing requires preserving source-observed regions whi
arXiv:2510.21583v2 Announce Type: replace Abstract: Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated st
arXiv:2605.20245v1 Announce Type: cross Abstract: We introduce extbf{Prism}, a framework for structural symmetry diagnosis in complex networks. Given a graph Laplacian L and a duality operator P (a sy
arXiv:2605.20867v1 Announce Type: cross Abstract: Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analy