Knowledge catalogue
arXiv:2604.11841v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models (LLMs), but its strictly linear structure fund
arXiv:2604.12113v1 Announce Type: cross Abstract: Visual Foundation Models (VFMs) such as the Segment Anything Model (SAM) have significantly advanced broad use of image segmentation. However, SAM and
arXiv:2604.12384v1 Announce Type: new Abstract: Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal
arXiv:2604.12068v1 Announce Type: new Abstract: Visual localization is the task of estimating the camera pose of an image relative to a scene representation. In practice, visual localization systems a
arXiv:2504.00890v2 Announce Type: replace-cross Abstract: Modern applications increasingly involve highly sensitive network data, where raw edges cannot be shared due to privacy constraints. We propos
arXiv:2601.09152v2 Announce Type: replace Abstract: Prior work on LLM-based privacy focuses on norm judgment over synthetic vignettes, rather than how people think about a specific data practice and f
arXiv:2604.12348v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training without sharing raw data, offering a promising path toward privacy preserving artificial in
arXiv:2604.12970v1 Announce Type: cross Abstract: Multimodal federated learning enables privacy-preserving collaborative model training across healthcare institutions. However, a fundamental challenge
arXiv:2604.11943v1 Announce Type: cross Abstract: An OS kernel that runs LLM inference internally can read logit distributions before any text is generated -- and act on them as a governance primitive
arXiv:2511.17097v2 Announce Type: replace Abstract: Vision-Language Navigation requires agents to act coherently over long horizons by understanding not only local visual context but also how far they
arXiv:2305.16347v2 Announce Type: replace-cross Abstract: Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with genera
arXiv:2604.12652v1 Announce Type: cross Abstract: Reinforcement learning (RL) can improve the prompt following capability of text-to-image (T2I) models, yet obtaining high-quality reward signals remai
arXiv:2603.17361v2 Announce Type: replace-cross Abstract: Proper citation of relevant literature is essential for contextualising and validating scientific contributions. While current citation recomm
arXiv:2604.12160v1 Announce Type: new Abstract: Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic appl
arXiv:2604.11817v1 Announce Type: cross Abstract: Hybrid quantum-classical models offer a promising route for learning from complex data; however, their application to multi-band remote sensing imager
arXiv:2603.29977v2 Announce Type: replace-cross Abstract: Multimodal deep learning for cancer prognosis is commonly assumed to benefit from synergistic cross-modal interactions, yet this assumption ha
arXiv:2511.11973v2 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables policy learning from fixed datasets without further environment interaction, making it particularly valu
arXiv:2604.12867v1 Announce Type: new Abstract: As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this
arXiv:2604.12418v1 Announce Type: cross Abstract: Autonomous vehicles are increasingly deployed in safety-critical applications, where sensing failures or cyberphysical attacks can lead to unsafe oper
arXiv:2604.12918v1 Announce Type: new Abstract: Bird's-eye-view (BEV) representations are the dominant paradigm for 3D perception in autonomous driving, providing a unified spatial canvas where detect
arXiv:2511.19996v2 Announce Type: replace Abstract: We propose RankOOD, a rank-based Out-of-Distribution (OOD) detection approach based on training a model with the Placket-Luce loss, which is now ext
arXiv:2604.12834v1 Announce Type: cross Abstract: Radio frequency fingerprints (RFFs) enable secure wireless authentication but struggle in open-set scenarios with unknown devices and varying channels
arXiv:2604.12371v1 Announce Type: new Abstract: We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms
arXiv:2511.10453v3 Announce Type: replace-cross Abstract: Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safet
arXiv:2604.12378v1 Announce Type: new Abstract: Despite advances in multilingual capabilities, most large language models (LLMs) remain English-centric in their training and, crucially, in their produ
arXiv:2512.00412v4 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical
arXiv:2604.12175v1 Announce Type: new Abstract: Recent advances in image editing have heightened the need for reliable Image Editing Quality Assessment (IEQA). Unlike traditional methods, IEQA require
arXiv:2604.11992v1 Announce Type: cross Abstract: 3D Gaussian Splatting is a powerful visual representation, providing high-quality and efficient 3D scene reconstruction, but it is crucially dependent
arXiv:2604.11820v1 Announce Type: cross Abstract: As data-privacy regulations tighten and statistical models are increasingly deployed on sensitive human-sourced data, privacy-preserving linear regres
arXiv:2604.12357v1 Announce Type: new Abstract: Detailed image captioning demands both factual grounding and fine-grained coverage, yet existing methods have struggled to achieve them simultaneously.
arXiv:2501.17518v3 Announce Type: replace-cross Abstract: Hierarchical data is common in many domains like life sciences and e-commerce, and its embeddings often play a critical role. While hyperbolic
arXiv:2411.05481v5 Announce Type: replace Abstract: This article studies the problem of distributed formation control for multiple robots by using onboard ultra wide band (UWB) distance and inertial o
arXiv:2604.12582v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capability in video understanding, yet they still suffer from hallucinations. E
arXiv:2604.12753v1 Announce Type: new Abstract: Specular glare on reflective floors and glass surfaces frequently corrupts RGB-D depth measurements, producing holes and spikes that accumulate as persi
arXiv:2604.12820v1 Announce Type: new Abstract: Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with
arXiv:2509.08660v3 Announce Type: replace Abstract: Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work
arXiv:2604.13021v1 Announce Type: cross Abstract: Computed tomography (CT) enterography is a primary imaging modality for assessing inflammatory bowel disease (IBD), yet the representational choices t
arXiv:2604.12894v1 Announce Type: new Abstract: We present CUBE (Control-based Unified B-spline Encoding), a new geometric representation for human faces that combines B-spline volumes with learned fe
arXiv:2604.12195v1 Announce Type: new Abstract: Work in cognitive science and artificial intelligence has suggested that exposing learning agents to traces of interaction between multiple individuals
arXiv:2604.11947v1 Announce Type: cross Abstract: Unlocking large-scale low-bandwidth decentralized training has the potential to utilize otherwise untapped compute resources. In centralized settings,
arXiv:2604.13016v1 Announce Type: cross Abstract: On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly unders
arXiv:2604.12807v1 Announce Type: cross Abstract: Satellite image restoration aims to improve image quality by compensating for degradations (e.g., noise and blur) introduced by the imaging system and
arXiv:2604.12768v1 Announce Type: new Abstract: Federated learning (FL) is a distributed paradigm that coordinates massive local clients to collaboratively train a global model via stage-wise local tr
arXiv:2511.09803v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves factuality but retrieving for every query often hurts quality while inflating tokens and latency. We p
arXiv:2501.13340v4 Announce Type: replace Abstract: Diffusion models (DMs) have recently demonstrated remarkable generation capability. However, their training generally requires huge computational re
arXiv:2512.14754v2 Announce Type: replace-cross Abstract: Advanced LLMs have achieved near-ceiling instruction-following accuracy on benchmarks such as IFEval. However, these impressive scores do not
arXiv:2604.12219v1 Announce Type: cross Abstract: Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. Wh
arXiv:2604.12693v1 Announce Type: new Abstract: Deep learning models often achieve expert-level accuracy in medical image classification but suffer from a critical flaw: semantic incoherence. These hi
arXiv:2602.17276v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a subfield of machine learning that focuses on developing models that can autonomously learn optimal decision-making
arXiv:2604.12942v1 Announce Type: new Abstract: Real-time 3D Gaussian splatting (3DGS)-based Simultaneous Localization and Mapping (SLAM) in large-scale real-world environments remains challenging, as
arXiv:2604.12908v1 Announce Type: new Abstract: At its core, robotic manipulation is a problem of vision-to-geometry mapping (f(v) rightarrow G). Physical actions are fundamentally defined by geometri
arXiv:2604.12169v1 Announce Type: new Abstract: We present a screw geometry-based manipulation planning framework for the robotic automation of solution-based synthesis, exemplified through the prepar
arXiv:2604.12069v1 Announce Type: cross Abstract: Robust explanations are increasingly required for user trust in enterprise NLP, yet pre-deployment validation is difficult in the common case of black
arXiv:2510.00310v3 Announce Type: replace Abstract: Federated inference, in the form of one-shot federated learning, edge ensembles, or federated ensembles, has emerged as an attractive solution to co
arXiv:2511.21211v3 Announce Type: replace Abstract: Gene prioritization (identifying genes potentially associated with a biological process) is increasingly tackled with Artificial Intelligence. Howev
arXiv:2604.12086v1 Announce Type: new Abstract: Designing robust reinforcement learning (RL) agents in the presence of imperfect reward signals remains a core challenge. In practice, agents are often
arXiv:2604.12079v1 Announce Type: cross Abstract: Traditional machine learning depends on high-precision arithmetic and near-ideal hardware assumptions, which is increasingly challenged by variability
arXiv:2604.12655v1 Announce Type: new Abstract: Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-w
arXiv:2604.12271v1 Announce Type: new Abstract: Multimodal attributed graphs (MAGs) combine multimodal node attributes with structured relations. However, existing methods usually perform shared messa
arXiv:2604.12988v1 Announce Type: cross Abstract: Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasing