Knowledge catalogue
arXiv:2608.25579v1 Announce Type: new Abstract: Metaphor-identification performance can change markedly across datasets that differ in text distribution and annotation policy. We examine whether a fix
arXiv:2608.25568v1 Announce Type: new Abstract: To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has att
arXiv:2608.25023v1 Announce Type: cross Abstract: Multimodal product models can complete missing e-commerce attributes, yet current methods still optimize attribute-answer accuracy without verifying v
arXiv:2608.24987v1 Announce Type: new Abstract: Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence
arXiv:2608.25421v1 Announce Type: cross Abstract: The Stochastic Simulation Algorithm (SSA), widely considered an exact algorithm for stochastic chemical reaction networks, suffers from high computati
arXiv:2608.25061v1 Announce Type: new Abstract: GPUs increasingly accelerate database systems, but query-specific peak performance still often relies on hand-written kernels. Existing LLM kernel bench
arXiv:2608.25635v1 Announce Type: new Abstract: Industrial e-commerce search systems ultimately aim to optimize the user-level long-term objective, such as n-day cumulative purchases or gross merchand
arXiv:2608.25428v1 Announce Type: new Abstract: Correcting flawed reasoning traces remains a significant challenge for Large Language Models (LLMs), whose autoregressive generation can propagate early
arXiv:2608.25480v1 Announce Type: new Abstract: Dataset distillation compresses a large training set into a compact synthetic set while preserving its downstream utility. However, existing methods pri
arXiv:2505.15661v2 Announce Type: replace Abstract: Gradient-based learning imposes (deep) neural networks to be differentiable at all steps. This includes model-based architectures constructed by unr
arXiv:2608.25675v1 Announce Type: new Abstract: Objective: Diffusion-weighted MRI (DWI-MRI) is the gold standard for visualizing and quantifying acute ischaemic stroke (AIS). Although deep learning me
arXiv:2608.25851v1 Announce Type: new Abstract: Self-supervised learning (SSL) encoders are vulnerable to backdoor attacks, posing threats to both visual SSL encoders and vision-language encoders. Exi
arXiv:2608.25073v1 Announce Type: new Abstract: Digital mobility outcomes (DMOs) derived from wearable sensors characterise mobility in daily life and offer a promising means of monitoring disease pro
arXiv:2608.24949v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling
arXiv:2608.26002v1 Announce Type: new Abstract: Advanced automation is a key technology for enhancing the safety of ground operations amidst the increasing density of commercial air traffic. While mot
arXiv:2608.24901v1 Announce Type: new Abstract: A decodable 'empathy' direction is routinely read as a causal lever, conflating decodability, automated-metric control, and human-perceived change. We t
arXiv:2608.25222v1 Announce Type: new Abstract: The impairment of the hands can seriously affect the abilities of every individual to perform the every-day activity, so the design of stable and contro
arXiv:2404.11754v4 Announce Type: replace Abstract: This paper focuses on reducing the communication cost of federated learning by exploring generalization bounds and representation learning. We first
arXiv:2608.25710v1 Announce Type: new Abstract: Data augmentation is a standard component of modern semantic segmentation pipelines, but most augmentation techniques allocate transformations uniformly
arXiv:2608.25652v1 Announce Type: new Abstract: We present RoofDiT, a generative framework for 2D roof graph synthesis and reconstruction. Roofs are compactly described as planar graphs of junctions a
arXiv:2608.25429v1 Announce Type: cross Abstract: Machine unlearning aims to make a model forget specific data, yet unlearned LLMs often fail to stay unlearned: brief fine-tuning can revive removed kn
arXiv:2608.25999v1 Announce Type: new Abstract: Linguistic meaning is grounded in conceptual content, from which reference to particular entities emerges as words enter discourse. To examine the proce
arXiv:2608.25876v1 Announce Type: cross Abstract: Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as 'more elegant' or 'more minimalis
arXiv:2608.24988v1 Announce Type: new Abstract: Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a way t
arXiv:2608.25773v1 Announce Type: new Abstract: Understanding user preferences from noisy and temporally evolving social media behaviors is fundamentally challenging due to interest drift, where user
arXiv:2608.25138v1 Announce Type: new Abstract: Stochastic masking, cropping, or modality removal makes deterministic reconstruction an incomplete target: one observation can admit many clean completi
arXiv:2608.26019v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a privileged copy of the student model to provide dense supervision without an external teacher. OPSD keeps this
arXiv:2608.24904v1 Announce Type: new Abstract: Inertial sensors at multiple body locations can improve activity recognition, but requiring every sensor at inference increases the deployment burden. W
arXiv:2608.25509v1 Announce Type: new Abstract: Robotic welding is widely used in industrial manufacturing, where the welding torch is often connected to the generator through an external umbilical. W
arXiv:2510.24069v2 Announce Type: replace Abstract: To generate reliable motion for legged robots through trajectory optimization, it is crucial to simultaneously compute the robot's path and contact
arXiv:2510.22733v3 Announce Type: replace Abstract: Text embedding models deliver competitive retrieval performance with high efficiency, but their ranking fidelity remains limited compared to LLM-bas
arXiv:2511.11635v2 Announce Type: replace-cross Abstract: In intelligent education, personalized mathematics question generation aims to produce mathematics questions that satisfy educational requirem
arXiv:2510.12899v3 Announce Type: replace Abstract: Recently, several multi-turn dialogue benchmarks have been proposed to evaluate the conversational abilities of large language models (LLMs). As LLM
arXiv:2608.25887v1 Announce Type: cross Abstract: An intuitive method for dimensionality reduction is proposed, which is highly effective for finding interesting projections of multivariate data. Foll
arXiv:2608.25386v1 Announce Type: new Abstract: Autoregressive (AR) image generation has shown strong potential for scalable high-fidelity synthesis by modeling images as discrete token sequences. How
arXiv:2608.25561v1 Announce Type: new Abstract: VLMs are increasingly positioned as daily assistants that perceive first-person environments, follow user dialogue, and decide how to help. Existing ego
arXiv:2608.25642v1 Announce Type: new Abstract: Image-goal navigation using lightweight topological maps is a practical paradigm for indoor robot deployment: the map requires only geotagged images, an
arXiv:2608.25888v1 Announce Type: new Abstract: Timely detection of crop stress is critical for sustaining yields under increasing drought frequency, yet conventional vegetation index thresholds or im
arXiv:2503.05788v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial genera
arXiv:2606.19377v2 Announce Type: replace Abstract: Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy a
arXiv:2608.25019v1 Announce Type: cross Abstract: Main sequence stars of spectral types late F through M exhibit systematic variability in photometric light curves, particularly when they are young. R
arXiv:2608.25448v1 Announce Type: cross Abstract: To resiliently and sustainably meet our future energy demand, photovoltaic (PV) modules must be deployed across a broad and diverse range of geographi
arXiv:2510.16899v2 Announce Type: replace Abstract: AI memory mechanisms primarily focus on preserving information content, often neglecting the validity conditions under which knowledge remains appli
arXiv:2608.25354v1 Announce Type: cross Abstract: Model merging provides an efficient way to construct multi-task generalist models without additional training, but its performance often degrades unde
arXiv:2608.24903v1 Announce Type: cross Abstract: Mobile and wearable sensing enables longitudinal observation of behavior, yet translating these signals into meaningful mental health constructs remai
arXiv:2506.14006v2 Announce Type: replace-cross Abstract: We present a framework for chemical learning based on Competitive Dimerization Networks (CDNs) - systems in which multiple molecular species,
arXiv:2608.25774v1 Announce Type: new Abstract: EXAONE Tabular is a compact tabular foundation model family for classification and regression via in-context learning, producing predictions without dat
arXiv:2608.24938v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale capacity for strong quality while keeping per-token compute bounded through sparse expert activation. Yet low-late
arXiv:2608.25135v1 Announce Type: new Abstract: This paper presents a novel method that extends targetless LiDAR-IMU calibration for ground vehicles to non- flat environments. Calibration typically ne
arXiv:2608.25707v1 Announce Type: new Abstract: Vision-language models have displayed remarkable capabilities in multi-modal understanding and are increasingly used in critical applications where econ
arXiv:2608.24945v1 Announce Type: new Abstract: Recent years have witnessed remarkable achievements of Large Language Models (LLMs) in multiple domains, while the excessive resource requirements of LL
arXiv:2608.26076v1 Announce Type: new Abstract: Grasp synthesis is a core task in robotic manipulation, for which the solution typically forms a multimodal distribution rather than a point estimate. G
arXiv:2608.25706v1 Announce Type: cross Abstract: Exact Bayes prediction enjoys fast predictive regret guarantees, but exact posterior updating or representation may be too costly for online use. We s
arXiv:2608.25496v1 Announce Type: new Abstract: Reliable access selection in dynamic and heterogeneous indoor-outdoor environments is challenging because instantaneous radio measurements alone cannot
arXiv:2608.26090v1 Announce Type: cross Abstract: We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying a neutrino foundation model pret
arXiv:2608.26060v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) technologies have achieved remarkable performance in recent years through the use of large multilingual foundation mo
arXiv:2608.25325v1 Announce Type: cross Abstract: Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the s
arXiv:2608.25360v1 Announce Type: new Abstract: High-quality surface normal estimation is preferred for detailed surface shape recovery and image editing. Existing single image-based methods, though b
arXiv:2608.25114v1 Announce Type: new Abstract: Federated learning (FL) has emerged as a key approach for training models across decentralized data, yet benchmarking in FL remains difficult to reprodu
arXiv:2607.18227v2 Announce Type: replace Abstract: In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image