Knowledge catalogue
arXiv:2605.00974v1 Announce Type: cross Abstract: LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks th
arXiv:2605.02122v1 Announce Type: new Abstract: Human evaluation remains the primary standard for assessing modern AI systems, yet annotator disagreement, bias, and variability make system rankings fr
arXiv:2605.02404v1 Announce Type: new Abstract: Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as
arXiv:2504.17401v2 Announce Type: replace Abstract: Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep lear
arXiv:2605.00924v1 Announce Type: new Abstract: AI-generated content (AIGC) detectors are increasingly deployed in high-stakes settings such as academic integrity screening, yet their reliability rest
arXiv:2506.01097v2 Announce Type: replace Abstract: Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficien
arXiv:2605.01717v1 Announce Type: new Abstract: Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Exist
arXiv:2605.02708v1 Announce Type: cross Abstract: Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control
arXiv:2504.20605v2 Announce Type: replace Abstract: Moral stories are a time-tested vehicle for transmitting values, yet modern NLP lacks a large, structured corpus that couples coherent narratives wi
arXiv:2605.02427v1 Announce Type: cross Abstract: A recurring pattern in 'reasoning without training' is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the
arXiv:2605.01311v1 Announce Type: new Abstract: Offline evaluation of language models from usage logs is biased when model choice is confounded: the same user-side factors that influence which model i
arXiv:2504.15077v5 Announce Type: replace Abstract: Large Language Models (LLMs) can translate natural language into SQL, but small models struggle with multi-table and complex queries in Zero-Shot Le
arXiv:2605.02041v1 Announce Type: new Abstract: The extraction of entities and relationships from threat intelligence reports into structured formats, such as cybersecurity knowledge graphs, is essent
arXiv:2603.07119v2 Announce Type: replace Abstract: Recent text-to-image models have improved global realism, but text rendering remains a persistent failure mode: images may look convincing overall,
arXiv:2605.02223v1 Announce Type: cross Abstract: Recent advances in voice cloning and text-to-speech synthesis have made partial speech manipulation - where an adversary replaces a few words within a
arXiv:2605.01659v1 Announce Type: new Abstract: The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly
arXiv:2605.02743v1 Announce Type: cross Abstract: The field of sensor-based human activity recognition (HAR) mainly uses posture, motion and context data of Inertial Measurement Units (IMUs) to identi
arXiv:2605.00224v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy
arXiv:2510.04142v2 Announce Type: replace Abstract: This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-
arXiv:2602.07262v3 Announce Type: replace Abstract: Second-order feature statistics are central to texture recognition, yet existing mechanisms exhibit a structural tension: bilinear pooling and Gram
arXiv:2605.00826v1 Announce Type: cross Abstract: Text-to-video retrieval enables users to find relevant video content using natural language queries, a task that has grown increasingly important with
arXiv:2605.01517v1 Announce Type: new Abstract: Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence.
arXiv:2605.02280v1 Announce Type: new Abstract: Multiphysics simulation is critical for system-technology co-optimization (STCO) in chiplet-based design, but repeated finite-element solutions of PDE-g
arXiv:2605.01399v1 Announce Type: new Abstract: The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often resu
arXiv:2601.20055v2 Announce Type: replace Abstract: Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental chall
arXiv:2602.22480v2 Announce Type: replace-cross Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-eva
arXiv:2605.01220v1 Announce Type: new Abstract: Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of
arXiv:2605.02735v1 Announce Type: new Abstract: Continuous latent-space reasoning offers a compact alternative to textual chain-of-thought for multimodal models, enabling high-dimensional visual evide
arXiv:2605.01194v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable capabilities and generalization in embodied manipulation. However, their decision-makin
arXiv:2605.02072v1 Announce Type: new Abstract: Conformal prediction (CP) provides powerful, distribution-free prediction sets, but its guarantees rely on the exchangeability of training and test data
arXiv:2605.02323v1 Announce Type: new Abstract: Compositional inference - the decomposition of observations into an unknown number of latent components - is central to perception and scientific data a
arXiv:2605.02782v1 Announce Type: cross Abstract: Automatic speech recognition (ASR) systems remain brittle on dysarthric and other atypical speech. Recent audio-language models raise the possibility
arXiv:2605.02363v1 Announce Type: new Abstract: Deployed language models must produce outputs that are both correct and format-compliant. We study this structured-output reliability gap using two math
arXiv:2601.19827v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-re
arXiv:2605.01111v1 Announce Type: cross Abstract: In this work, we introduce DUET (Dual-model Efficient Two-stage inference), a collaborative inference framework in which a capable model and a lightwe
arXiv:2605.00896v1 Announce Type: new Abstract: Operational phase unwrapping is the primary computational bottleneck in InSAR-based volcanic and seismic monitoring. We challenge the industry trend of
arXiv:2605.01605v1 Announce Type: new Abstract: Large language models are sensitive to minor prompt perturbations, yet existing robustness methods usually enforce consistency at the whole-sequence lev
arXiv:2605.01331v1 Announce Type: new Abstract: Image steganalysis, which aims at detecting secret information concealed within images, has become a critical countermeasure for assessing the security
arXiv:2512.12108v5 Announce Type: replace Abstract: The development of machine learning models based on computed tomography (CT) imaging has been a major focus due to the promise that imaging holds fo
arXiv:2605.00551v1 Announce Type: new Abstract: AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tr
arXiv:2603.22908v3 Announce Type: replace Abstract: Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet c
arXiv:2605.00663v1 Announce Type: cross Abstract: Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occlu
arXiv:2605.00251v1 Announce Type: cross Abstract: Existing voice deepfake detection and localization models rely heavily on representations extracted from speech foundation models (SFMs). However, dow
arXiv:2605.00058v1 Announce Type: cross Abstract: The primary goal of Design Verification (DV) is to ensure that a proposed chip design implementation (either in code, or physical form) exactly matche
arXiv:2605.00078v1 Announce Type: cross Abstract: Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to a
arXiv:2605.00333v1 Announce Type: cross Abstract: Frozen Gemma 4 31B weights pretrained exclusively on text tokens, unmodified, transfer across modality boundaries through a thin trainable interface.
arXiv:2605.00641v1 Announce Type: new Abstract: Both Dimensionality Reduction (DR) and Graph Drawing (GD) aim to visualize abstract, non-linear structures, yet rely on different optimization paradigms
arXiv:2407.10853v5 Announce Type: replace Abstract: Bias and fairness risks in Large Language Models (LLMs) vary substantially across deployment contexts, yet existing approaches lack systematic guida
arXiv:2504.11901v5 Announce Type: replace Abstract: The growing integration of robots in shared environments-such as warehouses, shopping centres, and hospitals-demands a deep understanding of the und
arXiv:2603.01267v2 Announce Type: replace-cross Abstract: We show that the factor graph and certifiable estimation paradigms, which have thus far been treated as essentially independent in the literat
arXiv:2509.06864v2 Announce Type: replace Abstract: This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the co
arXiv:2512.20260v5 Announce Type: replace Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scene
arXiv:2509.21864v2 Announce Type: replace Abstract: The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negat
arXiv:2510.00233v2 Announce Type: replace Abstract: Scientific machine learning has enabled the extraction of physical insights and data-driven modeling of high-dimensional spatiotemporal data, yet ac
arXiv:2601.01082v5 Announce Type: replace Abstract: Quality diversity (QD) optimization searches for a collection of solutions that optimize an objective while attaining diverse outputs of a user-spec
arXiv:2405.13901v4 Announce Type: replace Abstract: Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initializ
arXiv:2605.00195v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) is essential for aligning Large Language Models (LLMs) with user intent, yet it is believed to suppress generative diversit
arXiv:2605.00675v1 Announce Type: new Abstract: Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to comm
arXiv:2605.00159v1 Announce Type: new Abstract: In reinforcement learning (RL) for robotic manipulation, the Decision Transformer (DT) has emerged as an effective framework for addressing long-horizon
arXiv:2605.00628v1 Announce Type: cross Abstract: Text-to-SQL enables non-expert users to query databases in natural language, yet real-world schemas often suffer from ambiguous, abbreviated, or incon