Knowledge catalogue
arXiv:2604.17215v1 Announce Type: new Abstract: Large language models require continuous adaptation to new tasks while preserving safety alignment. However, fine-tuning on even benign data often compr
arXiv:2604.16580v1 Announce Type: new Abstract: Accurate assessment of lithium-ion battery ageing is challenged by cell-to-cell variability, heterogeneous cycling protocols, and limited transferabilit
arXiv:2604.18197v1 Announce Type: cross Abstract: Qualitative methods are important to use alongside quantitative methods to improve Human-Robot Interaction (HRI), yet they are often applied in static
arXiv:2604.16801v1 Announce Type: new Abstract: While modern representation learning relies heavily on global error signals, decentralized algorithms driven by local interactions offer a fundamental d
arXiv:2604.17548v1 Announce Type: new Abstract: Persistent homology (PH) encodes global information, such as cycles, and is thus increasingly integrated into graph neural networks (GNNs). PH methods i
arXiv:2604.17398v1 Announce Type: new Abstract: We present a methodological framework to discover linguistic and discursive patterns associated to different social groups through contrastive synthetic
arXiv:2604.17761v1 Announce Type: cross Abstract: Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or t
arXiv:2510.08878v3 Announce Type: replace-cross Abstract: Text-to-audio (TTA) generation with fine-grained control signals, e.g., precise timing control or intelligible speech content, has been explor
arXiv:2604.16975v1 Announce Type: cross Abstract: Recent work has shown that parameterizing and optimizing coordinate transformations using normalizing flows, i.e., invertible neural networks, can sig
arXiv:2604.16412v1 Announce Type: cross Abstract: This paper studies semi-supervised tabular classification in the extreme low-label regime using lightweight base learners. The paper proposes a cooper
arXiv:2604.18170v1 Announce Type: new Abstract: LLMs edit text and code by autoregressively regenerating the full output, even when most tokens appear verbatim in the input. We study Copy-as-Decode, a
arXiv:2604.17633v1 Announce Type: new Abstract: Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse
arXiv:2404.03191v3 Announce Type: replace Abstract: Numerous roadside perception datasets have been introduced to propel advancements in autonomous driving and intelligent transportation systems resea
arXiv:2604.18245v1 Announce Type: new Abstract: Large language models are increasingly deployed as protocols: structured multi-call procedures that spend additional computation to transform a baseline
arXiv:2604.17555v1 Announce Type: cross Abstract: Agentic search -- the task of training agents that iteratively reason, issue queries, and synthesize retrieved information to answer complex questions
arXiv:2603.07084v2 Announce Type: replace-cross Abstract: Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely m
arXiv:2601.14590v2 Announce Type: replace Abstract: Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine
arXiv:2604.16894v1 Announce Type: new Abstract: Factor-based Structural Equation Modeling (SEM) relies on likelihood-based estimation assuming a nonsingular sample covariance matrix, which breaks down
arXiv:2510.07591v3 Announce Type: replace Abstract: We present a system that uses LLMs as a tool in the development of Constructed Languages -- ConLangs, which we call IASC (Interactive Agentic System
arXiv:2510.06133v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms
arXiv:2604.17297v1 Announce Type: new Abstract: Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. Wh
arXiv:2505.11314v2 Announce Type: replace-cross Abstract: The assessment of evaluation metrics (meta-evaluation) is crucial for determining the suitability of existing metrics in text-to-image (T2I) g
arXiv:2604.16368v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective
arXiv:2604.17217v1 Announce Type: new Abstract: Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-ut
arXiv:2604.16657v1 Announce Type: new Abstract: Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods a
arXiv:2604.16558v1 Announce Type: new Abstract: AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imb
arXiv:2604.16892v1 Announce Type: new Abstract: Domain generalization (DG) aims to maintain performance under domain shift, which in computer vision appears primarily as stylistic variations that caus
arXiv:2604.16826v1 Announce Type: new Abstract: Merging separately trained LoRA adapters is a practical alternative to joint multi-task training, but it often hurts performance. Existing methods usual
arXiv:2604.16363v1 Announce Type: cross Abstract: Text-to-image models are commercially valuable assets often distributed under restrictive licenses, but such licenses are enforceable only when violat
arXiv:2604.16742v1 Announce Type: cross Abstract: Scientists have long sought to accurately predict outcomes of real-world events before they happen. Can AI systems do so more reliably? We study this
arXiv:2507.21934v2 Announce Type: replace Abstract: In cross-cultural recipe adaptation, the goal is not only to ensure cultural appropriateness and retain the original dish's essence, but also to pro
arXiv:2604.18091v1 Announce Type: new Abstract: Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over
arXiv:2509.03070v4 Announce Type: replace-cross Abstract: This letter presents a CWT-enhanced vibration sensing framework for bearing fault monitoring through spatial localization on time-frequency sp
arXiv:2604.17082v1 Announce Type: new Abstract: Capturing both geometry and rigid motion for structured dynamic objects, like multi-part assemblies or jointed mechanisms, remains a key challenge. Exis
arXiv:2604.16940v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incu
arXiv:2604.18343v1 Announce Type: new Abstract: Signal Temporal Logic (STL) is a powerful language for specifying temporally structured robotic tasks. Planning executable trajectories under STL constr
arXiv:2604.16684v1 Announce Type: new Abstract: We study model-free reinforcement learning (RL) in non-stationary finite-horizon episodic Markov decision processes (MDPs) without prior knowledge of th
arXiv:2604.17833v1 Announce Type: new Abstract: What appears effortless to a human waiter remains a major challenge for robots. Manipulating objects nonprehensilely on a tray is inherently difficult,
arXiv:2604.16845v1 Announce Type: new Abstract: Large language models (LLMs) tuned for safety often avoid acknowledging demographic differences, even when such acknowledgment is factually correct (e.g
arXiv:2507.06056v4 Announce Type: replace Abstract: Large Language Models (LLMs) are known to memorize portions of their training data, sometimes even reproduce content verbatim when prompted appropri
arXiv:2604.16380v1 Announce Type: new Abstract: Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training
arXiv:2604.16723v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or c
arXiv:2604.18094v1 Announce Type: new Abstract: Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet their prediction process remains difficult to interpret because i
arXiv:2604.18122v1 Announce Type: new Abstract: Decision-making is a cognitively intensive task that requires synthesizing relevant information from multiple unstructured sources, weighing competing f
arXiv:2604.16366v1 Announce Type: cross Abstract: Artificial intelligence (AI) tutors have become increasingly popular in learning environments. In this study, we propose an AI agent prototype framewo
arXiv:2507.14808v3 Announce Type: replace-cross Abstract: Tokenized U.S. Treasuries have emerged as a prominent subclass of real-world assets (RWAs), offering cryptographically secured, yield-bearing
arXiv:2604.17177v1 Announce Type: new Abstract: Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property
arXiv:2601.03154v2 Announce Type: replace Abstract: Reasoning-tuned LLMs utilizing long Chain-of-Thought (CoT) excel at single-answer tasks, yet their ability to model Human Label Variation--which req
arXiv:2604.16459v1 Announce Type: cross Abstract: Fault intensity diagnosis (FID) plays a pivotal role in intelligent manufacturing while neglecting dependencies among target classes hinders its pract
arXiv:2604.17389v1 Announce Type: new Abstract: Soft-tissue deformation remains a major limitation in image-guided neurosurgery, where intra-operative anatomy can deviate substantially from pre-operat
arXiv:2510.24074v2 Announce Type: replace-cross Abstract: The Heston stochastic volatility model is a widely used tool in financial mathematics for pricing European options. However, its calibration r
arXiv:2604.16341v1 Announce Type: cross Abstract: Virtual Reality (VR) applications require robust user identification systems to ensure secure access to equipment and protect worker identities. Motio
arXiv:2510.17422v4 Announce Type: replace Abstract: Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual o
arXiv:2604.18261v1 Announce Type: cross Abstract: The multi-scale and non-linear nature of phase-field models of solidification requires fine spatial and temporal discretization, leading to long compu
arXiv:2511.15669v2 Announce Type: replace Abstract: Does Chain-of-Thought (CoT) reasoning genuinely improve Vision-Language-Action (VLA) models, or does it merely add overhead? Existing CoT-VLA system
arXiv:2604.16656v1 Announce Type: new Abstract: All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latenc
arXiv:2604.17709v1 Announce Type: new Abstract: Existing works on large language model (LLM) decomposition mainly focus on improving performance on downstream tasks, but they ignore the poor parallel
arXiv:2604.17436v1 Announce Type: new Abstract: This study presents a Shape from Shading (SfS) framework to enhance sub-metre resolution lunar digital elevation models (DEMs) using imagery from the Or
arXiv:2510.19544v2 Announce Type: replace-cross Abstract: Combinatorial optimization problems are central to both practical applications and the development of optimization methods. While classical an
arXiv:2604.17207v1 Announce Type: cross Abstract: Iterative alignment methods based on purely greedy updates are remarkably effective in practice, yet existing theoretical guarantees of (O(log T)) KL-