Knowledge catalogue
arXiv:2603.14997v2 Announce Type: replace Abstract: Building and evaluating enterprise AI systems requires synthetic organizational corpora that are internally consistent, temporally structured, and c
arXiv:2604.08266v1 Announce Type: new Abstract: Leveraging the general world knowledge of Large Language Models (LLMs) holds significant promise for improving the ability of autonomous driving systems
arXiv:2604.08238v1 Announce Type: new Abstract: The increasing adaptation of vision models across domains, such as satellite imagery and medical scans, has raised an emerging privacy risk: models may
arXiv:2604.08110v1 Announce Type: new Abstract: Training-free open-vocabulary semantic segmentation(TF-OVSS) has recently attracted attention for its ability to perform dense prediction by leveraging
arXiv:2604.08461v1 Announce Type: new Abstract: Open-Vocabulary Segmentation (OVS) aims to segment image regions beyond predefined category sets by leveraging semantic descriptions. While CLIP based a
arXiv:2512.09665v2 Announce Type: replace Abstract: We address the problem of fair classification in settings where data is scarce and unbalanced across demographic groups. Such low-data regimes are c
arXiv:2510.11169v2 Announce Type: replace-cross Abstract: PAC generalization bounds on the risk, when expressed in terms of the expected loss, are often insufficient to capture imbalances between subg
arXiv:2602.06912v2 Announce Type: replace Abstract: Unsupervised segmentation from self-supervised ViT patches holds promise but lacks robustness: multi-object scenes confound saliency cues, and low-s
arXiv:2604.07901v1 Announce Type: new Abstract: 360 video object segmentation (360VOS) aims to predict temporally-consistent masks in 360 videos, offering full-scene coverage, benefiting applications,
arXiv:2512.24517v2 Announce Type: replace Abstract: Automatic speech transcripts are often delivered as unstructured word streams that impede readability and repurposing. We recast paragraph segmentat
arXiv:2604.07912v1 Announce Type: new Abstract: Finding parking consumes a disproportionate share of food delivery time, yet no system addresses precise parking-spot selection relative to merchant ent
arXiv:2604.08538v1 Announce Type: new Abstract: AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and
arXiv:2506.17212v2 Announce Type: replace Abstract: Articulated objects are common in the real world, yet modeling their structure and motion remains a challenging task for 3D reconstruction methods.
arXiv:2604.08000v1 Announce Type: cross Abstract: Proactivity is a core expectation for AGI. Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive age
arXiv:2503.02129v2 Announce Type: replace-cross Abstract: Path regularization has shown to be a very effective regularization to train neural networks, leading to a better generalization property than
arXiv:2604.06620v1 Announce Type: new Abstract: Quantitative estimation of wheel polygonal roughness from axle-box vibration signals is a challenging yet practically relevant problem for rail-vehicle
arXiv:2508.09521v2 Announce Type: replace Abstract: Emotional support conversations require more than fluent responses. Supporters need to understand the seeker's situation and emotions, adopt an appr
arXiv:2604.07788v1 Announce Type: cross Abstract: We introduce PeReGrINE, a benchmark and evaluation framework for personalized review generation grounded in graph-structured user--item evidence. PeRe
arXiv:2604.07343v1 Announce Type: cross Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a cen
arXiv:2604.07427v1 Announce Type: new Abstract: Modern text-to-image (T2I) models generate high-fidelity visuals but remain indifferent to individual user preferences. While existing reward models opt
arXiv:2604.08395v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid prog
arXiv:2604.08503v1 Announce Type: new Abstract: Recent advances in generative video modeling, driven by large-scale datasets and powerful architectures, have yielded remarkable visual realism. However
arXiv:2512.23994v3 Announce Type: replace-cross Abstract: Text-to-audio-video (T2AV) generation is central to applications such as filmmaking and world modeling. However, current models often fail to
arXiv:2604.07230v2 Announce Type: replace Abstract: Achieving physically accurate object manipulation in image editing is essential for its potential applications in interactive world models. However,
arXiv:2604.06865v1 Announce Type: cross Abstract: Physical adversarial attacks are increasingly studied in settings that resemble deployed surveillance systems rather than isolated image benchmarks. I
arXiv:2603.23286v3 Announce Type: replace Abstract: Physical knot classification is a fine-grained task in which the intended cue is rope crossing structure, but high accuracy may still come from appe
arXiv:2503.09640v2 Announce Type: replace-cross Abstract: Rendering realistic human-object interactions (HOIs) from sparse-view inputs is a challenging yet crucial task for various real-world applicat
arXiv:2604.07025v1 Announce Type: cross Abstract: This article presents a novel and comprehensive approach for analyzing bending behavior of the tapered perforated beam under an exponential load. The
arXiv:2512.07755v3 Announce Type: replace-cross Abstract: Recent studies have demonstrated the success of deep learning in solving forward and inverse problems in engineering and scientific computing
arXiv:2508.21618v2 Announce Type: replace-cross Abstract: We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observ
arXiv:2604.08499v1 Announce Type: cross Abstract: Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the communi
arXiv:2510.06670v2 Announce Type: replace Abstract: High-quality instruction data is critical for LLM alignment, yet existing open-source datasets often lack efficiency, requiring hundreds of thousand
arXiv:2511.19474v4 Announce Type: replace-cross Abstract: Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchma
arXiv:2503.24135v3 Announce Type: replace Abstract: Weakly supervised object localization (WSOL) methods allow training models to classify images and localize ROIs. WSOL only requires low-cost image-c
arXiv:2603.04165v3 Announce Type: replace-cross Abstract: Large-scale 2D foundation models exhibit strong transferable representations, yet extending them to 3D volumetric data typically requires retr
arXiv:2604.07042v1 Announce Type: new Abstract: Most research in planning focuses on generating a plan to achieve a desired set of goals. However, a goal specification can also be used to encode a pro
arXiv:2508.15358v2 Announce Type: replace Abstract: In many planning applications, we might be interested in finding plans that minimally modify the initial state to achieve the goals. We refer to thi
arXiv:2604.06279v1 Announce Type: cross Abstract: Accurate parameter selection is fundamental to gyrokinetic plasma simulations, yet current practices rely heavily on manual literature reviews, leadin
arXiv:2604.07779v1 Announce Type: new Abstract: Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagn
arXiv:2604.02073v2 Announce Type: replace Abstract: Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by g
arXiv:2604.08340v1 Announce Type: new Abstract: While Vision-Language Models (VLMs) have achieved remarkable progress in static visual understanding, their deployment in complex 3D embodied environmen
arXiv:2604.08125v1 Announce Type: new Abstract: Human-like multimodal reaction generation is essential for natural group interactions between humans and embodied AI. However, existing approaches are l
arXiv:2604.07016v1 Announce Type: new Abstract: A key challenge in scaling up Reinforcement Learning is generalizing learned behaviour. Without the ability to carry forward acquired knowledge an agent
arXiv:2604.08272v1 Announce Type: new Abstract: Deep image prior (DIP) is an unsupervised deep learning framework that has been successfully applied to a variety of inverse imaging problems. However,
arXiv:2604.08036v1 Announce Type: cross Abstract: This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feas
arXiv:2502.02514v5 Announce Type: replace Abstract: Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion m
arXiv:2604.08037v1 Announce Type: cross Abstract: Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech
arXiv:2604.06228v1 Announce Type: cross Abstract: We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generati
arXiv:2512.13746v4 Announce Type: replace-cross Abstract: Fiber reinforcement and polymer matrix respond differently to manufacturing conditions due to mismatch in coefficient of thermal expansion and
arXiv:2604.07059v1 Announce Type: new Abstract: Electronic Control Units (ECUs) have played a pivotal role in transforming motorcars of yore into the modern vehicles we see on our roads today. They ac
arXiv:2510.05921v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompt
arXiv:2604.06401v1 Announce Type: new Abstract: The large language models (LLMs) might produce a persuasive argument within mathematical and logical fields, although such argument often includes some
arXiv:2604.04988v1 Announce Type: cross Abstract: Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parame
arXiv:2512.18662v2 Announce Type: replace-cross Abstract: End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for th
arXiv:2512.01236v2 Announce Type: replace Abstract: Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, w
arXiv:2510.24058v2 Announce Type: replace-cross Abstract: Multi-sensory systems for embodied intelligence, from wearable body-sensor networks to instrumented robotic platforms, routinely face a sensor
arXiv:2512.14735v2 Announce Type: replace-cross Abstract: This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reaso
arXiv:2601.15356v4 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior human preference alignment in Image Qua
arXiv:2604.06912v1 Announce Type: cross Abstract: MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global res
arXiv:2604.05704v2 Announce Type: replace Abstract: Multimodal Sentiment Analysis (MSA) aims to infer human sentiment from textual, acoustic, and visual signals. In real-world scenarios, however, mult