Knowledge catalogue
arXiv:2604.15086v1 Announce Type: cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained cont
arXiv:2604.14451v1 Announce Type: cross Abstract: Weak gravitational lensing, the correlated distortion of background galaxy shapes by foreground structures, is a powerful probe of the matter distribu
Grok 4.3 Beta is insanely good and now comes with powerful new tools that are super helpful for everyday use: • Create clean slides, graphs, images and dashboards • Pull real-time data and images dire
arXiv:2604.15273v1 Announce Type: new Abstract: Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, spl
arXiv:2604.15148v1 Announce Type: cross Abstract: Reinforcement learning has emerged as an effective paradigm for training large language models to perform search-augmented reasoning. However, existin
arXiv:2604.14180v1 Announce Type: new Abstract: We train a 318M-parameter Transformer language model from scratch on a curated corpus of 1.56 billion tokens of pure Classical Chinese, with zero Englis
arXiv:2604.05158v2 Announce Type: replace Abstract: Large language models encode extensive world knowledge valuable for zero-shot named entity recognition. However, their causal attention mechanism, w
arXiv:2604.14799v1 Announce Type: new Abstract: Effective abstention (EA), recognizing evidence insufficiency and refraining from answering, is critical for reliable multimodal systems. Yet existing e
arXiv:2510.05486v2 Announce Type: replace Abstract: LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning doma
arXiv:2604.15210v1 Announce Type: cross Abstract: Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer right. While recent work evaluates hum
arXiv:2604.14198v1 Announce Type: cross Abstract: Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains large
arXiv:2604.14643v1 Announce Type: new Abstract: Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods r
arXiv:2604.14616v1 Announce Type: new Abstract: Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a clinical concept -- is a recurring bottlene
arXiv:2507.15066v5 Announce Type: replace Abstract: Time series anomaly detection (TSAD) has traditionally focused on binary classification and often lacks the fine-grained categorization and explanat
arXiv:2505.20291v4 Announce Type: replace-cross Abstract: Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting
arXiv:2604.14548v1 Announce Type: cross Abstract: As speech language models (SLMs) transition from personal devices into shared, multi-user environments, their responses must account for far more than
arXiv:2604.14749v1 Announce Type: new Abstract: Large language models still struggle with faithfulness and hallucinations despite their remarkable reasoning abilities. In Knowledge Graph Question Answ
arXiv:2604.13251v1 Announce Type: new Abstract: Analog optical computers promise large efficiency gains for machine learning inference, yet no demonstration has moved beyond small-scale image benchmar
arXiv:2507.16005v2 Announce Type: replace-cross Abstract: Alloy discovery is constrained by vast compositional spaces, competing objectives, and prohibitive experimental costs. Although simulations an
arXiv:2604.13452v1 Announce Type: new Abstract: Long-form visual storytelling requires maintaining continuity across shots, including consistent characters, stable environments, and smooth scene trans
arXiv:2604.14121v1 Announce Type: new Abstract: LLM reasoning traces suffer from complex flaws -- *Step Internal Flaws* (logical errors, hallucinations, etc.) and *Step-wise Flaws* (overthinking, unde
arXiv:2604.13076v1 Announce Type: new Abstract: We investigate the robustness of value alignment via finetuning with synthetic documents, using animal compassion as a value that is both important in i
arXiv:2604.13278v1 Announce Type: new Abstract: Aerial object detection in UAV imagery presents unique challenges due to the high prevalence of tiny objects, adverse environmental conditions, and stri
arXiv:2604.13071v1 Announce Type: new Abstract: We introduce Earth Virtual Expert (EVE), the first open-source, end-to-end initiative for developing and deploying domain-specialized LLMs for Earth Int
arXiv:2405.20836v3 Announce Type: replace-cross Abstract: Solving time-dependent Partial Differential Equations (PDEs) is one of the most critical problems in computational science. While Physics-Info
arXiv:2602.23636v3 Announce Type: replace Abstract: Ensuring the safety of LLM-generated content is essential for real-world deployment. Most existing guardrail models formulate moderation as a fixed
arXiv:2604.13981v1 Announce Type: new Abstract: Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degr
arXiv:2604.14125v1 Announce Type: new Abstract: While end-to-end Vision-Language-Action (VLA) models offer a promising paradigm for robotic manipulation, fine-tuning them on narrow control data often
arXiv:2604.14111v1 Announce Type: new Abstract: Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such a
arXiv:2604.13979v1 Announce Type: new Abstract: Open-world Question Answering (OW-QA) over knowledge graphs (KGs) aims to answer questions over incomplete or evolving KGs. Traditional KGQA assumes a c
arXiv:2604.14016v1 Announce Type: new Abstract: Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely r
arXiv:2604.13853v1 Announce Type: new Abstract: Safe and explainable motion planning remains a central challenge in autonomous driving. While rule-based planners offer predictable and explainable beha
arXiv:2604.14073v1 Announce Type: new Abstract: Resolving and rewriting references is fundamental in programming languages. Motivated by a real-world decompilation task, we abstract reference rewritin
arXiv:2604.05096v2 Announce Type: replace Abstract: Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptati
arXiv:2604.13993v1 Announce Type: cross Abstract: Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even st
arXiv:2604.14147v1 Announce Type: new Abstract: Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to thei
arXiv:2604.13622v1 Announce Type: new Abstract: Self-Organizing Maps (SOM) are a classical method for unsupervised learning, vector quantization, and topographic mapping of high-dimensional data. Howe
arXiv:2604.14144v1 Announce Type: cross Abstract: Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked
arXiv:2511.17792v2 Announce Type: replace Abstract: While recent video world models can generate highly realistic videos, their ability to perform semantic reasoning and planning remains unclear and u
arXiv:2604.13759v1 Announce Type: cross Abstract: Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Cu
arXiv:2511.23332v2 Announce Type: replace Abstract: Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applicati
arXiv:2604.06484v2 Announce Type: replace Abstract: Cultural values are expressed not only through language but also through visual scenes and everyday social practices. Yet existing evaluations of cu
arXiv:2604.13349v1 Announce Type: new Abstract: Communication in Large Language Model (LLM)-based multi-agent systems is moving beyond discrete tokens to preserve richer context. Recent work such as L
arXiv:2503.23137v2 Announce Type: replace-cross Abstract: Understanding humor-particularly when it involves complex, contradictory narratives that require comparative reasoning-remains a significant c
arXiv:2604.13776v1 Announce Type: cross Abstract: Watermarking is becoming the default mechanism for AI content authentication, with governance policies and frameworks referencing it as infrastructure
arXiv:2604.12765v1 Announce Type: new Abstract: Marker-based motion capture (MoCap) systems have long been the gold standard for accurate 4D human modeling, yet their reliance on specialized hardware
arXiv:2603.24626v2 Announce Type: replace-cross Abstract: Background: Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at cellular resolution but is inherently affected by spar
arXiv:2604.12904v1 Announce Type: new Abstract: Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image, and a relative caption that specifies the
arXiv:2603.10652v2 Announce Type: replace-cross Abstract: In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion. Under such condit
arXiv:2603.08819v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems combine document retrieval with a generative model to address complex information seeking tasks l
arXiv:2604.13013v1 Announce Type: new Abstract: This paper tackles the Electric Capacitated Vehicle Routing Problem (E-CVRP) through a bilevel optimization framework that handles routing and charging
arXiv:2604.12491v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed for tabular question answering, yet calibration on structured data is largely unstudied. This pap
arXiv:2604.12292v1 Announce Type: cross Abstract: Movie dubbing aims to synthesize speech that preserves the vocal identity of a reference audio while synchronizing with the lip movements in a target
arXiv:2604.12486v1 Announce Type: new Abstract: Long-horizon collaborative vision-language navigation (VLN) is critical for multi-robot systems to accomplish complex tasks beyond the capability of a s
arXiv:2604.12778v1 Announce Type: cross Abstract: Purpose: Accurate dose calculation is essential in radiotherapy for precise tumor irradiation while sparing healthy tissue. With the growing adoption
arXiv:2603.22607v2 Announce Type: replace Abstract: Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruct
arXiv:2604.12047v1 Announce Type: new Abstract: PDF files are primarily intended for human reading rather than automated processing. In addition, the heterogeneous content of PDFs, such as text, table
arXiv:2604.12666v1 Announce Type: cross Abstract: Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy
arXiv:2510.07285v3 Announce Type: replace-cross Abstract: The escalating complexity of network threats and the inherent class imbalance in traffic data present formidable challenges for modern Intrusi
arXiv:2604.12596v1 Announce Type: cross Abstract: We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fi