Knowledge catalogue
arXiv:2604.27308v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) methods face a tradeoff between adapter size and expressivity: ultra-low-parameter adapters are confined to fix
arXiv:2604.27840v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have shown great promise in time series forecasting. However, most existing LLM-based forecasting methods still
arXiv:2602.07915v2 Announce Type: replace-cross Abstract: Causal discovery from time series is a fundamental task in machine learning. However, its widespread adoption is hindered by a reliance on unt
arXiv:2602.00937v2 Announce Type: replace-cross Abstract: Leveraging pre-trained 2D image representations in behavior cloning policies has achieved great success and has become a standard approach for
arXiv:2604.27591v1 Announce Type: cross Abstract: Video moment retrieval is the task of retrieving specific segments of a video corresponding to a given text query. Recent studies have been conducted
arXiv:2604.26999v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) approximate solutions of partial differential equations (PDEs) by embedding physical laws into the loss functio
arXiv:2604.27149v1 Announce Type: cross Abstract: Conformal Prediction provides distribution-free prediction intervals with guaranteed coverage, but its reliance on a single global calibration thresho
arXiv:2601.22993v3 Announce Type: replace Abstract: We introduce the Value-at-Risk Constrained Policy Optimization algorithm (VaR-CPO), a sample efficient and conservative method designed to optimize
arXiv:2604.27744v1 Announce Type: new Abstract: AI applications are increasingly being introduced into digital health. While technical performance has advanced rapidly, successful deployment mainly de
arXiv:2604.27445v1 Announce Type: new Abstract: Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other
arXiv:2602.24262v4 Announce Type: replace Abstract: Identifying the full landscape of small and medium-sized enterprises (SMEs) in specialized industry sectors is critical for supply-chain resilience,
arXiv:2604.28138v1 Announce Type: cross Abstract: Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restor
arXiv:2602.17469v2 Announce Type: replace Abstract: Recent advances in multilingual representation learning aim to bridge the performance gap between high- and low-resource languages, yet their abilit
arXiv:2603.09117v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) significantly enhances large language models (LLMs) reasoning but severely suffers from
arXiv:2604.26962v1 Announce Type: cross Abstract: Education represents one of the most promising real-world applications for Large Language Models (LLMs). However, conventional tutoring systems rely o
arXiv:2604.28119v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption
arXiv:2604.28011v1 Announce Type: new Abstract: Ultrasound interpretation requires both precise lesion localization and holistic clinical reasoning, yet existing methods typically excel at only one of
arXiv:2512.14067v2 Announce Type: replace-cross Abstract: Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning
arXiv:2603.02226v2 Announce Type: replace Abstract: Real-world sequential signals, such as audio or video, contain critical information that is often embedded within long periods of silence or noise.
arXiv:2511.14070v3 Announce Type: replace-cross Abstract: Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independentl
arXiv:2604.27369v1 Announce Type: new Abstract: Clickbait is characterized by disproportionately high emotional intensity relative to informational content, often reinforced by specific structural pat
arXiv:2510.19322v3 Announce Type: replace-cross Abstract: Collective communication (CC) is critical for scaling distributed machine learning (DML). The predictable traffic patterns of DML present a gr
arXiv:2604.27309v1 Announce Type: new Abstract: Clinical AI systems require not just point-in-time evaluation but continuous governance: the ongoing practice of monitoring, evaluating, iterating, and
arXiv:2604.27695v1 Announce Type: cross Abstract: Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi
arXiv:2604.27454v1 Announce Type: new Abstract: Large language models (LLMs) sometimes exhibit qualitative shifts in response style under sustained self-referential dialogue conditions (Berg et al., 2
arXiv:2604.27346v1 Announce Type: cross Abstract: This study examines the factors influencing pre-service teachers' behavioral intention to use AI-enabled educational tools during their practicum, usi
arXiv:2604.28016v1 Announce Type: new Abstract: 3D Gaussian Splatting has emerged as a powerful scene representation for real-time novel-view synthesis. However, its standard adaptive density control
arXiv:2501.04066v2 Announce Type: replace Abstract: As a special type of multimedia data, Lithography Hotspot Detection (LHD) training often requires stronger privacy protection than conventional mult
arXiv:2604.28024v1 Announce Type: new Abstract: Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learnin
arXiv:2604.27014v1 Announce Type: new Abstract: The scarcity of high-quality annotated medical data, particularly in mental health, poses a significant bottleneck for training robust machine learning
arXiv:2601.06992v2 Announce Type: replace-cross Abstract: Financial question answering (QA) over long corporate filings requires evidence to satisfy strict constraints on entities, financial metrics,
arXiv:2604.27510v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its performance deteriorates und
arXiv:2604.27807v1 Announce Type: new Abstract: The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by
arXiv:2306.10407v3 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is a powerful paradigm for uncovering the incentive structure that drives agent behavior, by inferring an
arXiv:2604.28115v1 Announce Type: cross Abstract: Existing learning-based occupancy prediction methods rely on large-scale 3D annotations and generalize poorly across environments. We present FreeOcc,
arXiv:2505.22701v3 Announce Type: replace Abstract: A major challenge in rare animal image classification is the scarcity of data, as many species usually have only a small number of labeled samples.
arXiv:2604.27875v1 Announce Type: new Abstract: AI-generated images are becoming increasingly realistic and diverse, posing significant challenges for generalizable detection. While Vision Foundation
arXiv:2604.27453v1 Announce Type: new Abstract: Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, exi
arXiv:2604.27660v1 Announce Type: new Abstract: Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learn
arXiv:2510.05192v2 Announce Type: replace-cross Abstract: When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or
arXiv:2604.27653v1 Announce Type: new Abstract: Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectra
arXiv:2604.27353v1 Announce Type: new Abstract: Gait recognition has emerged as a compelling biometric modality for surveillance and security applications, offering inherent advantages such as non-int
arXiv:2601.19768v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be appare
arXiv:2604.28193v1 Announce Type: new Abstract: Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions.
arXiv:2604.27918v1 Announce Type: new Abstract: Existing talking avatar methods typically adopt an image-to-video pipeline conditioned on a static reference image within the same scene as the target g
arXiv:2503.01448v5 Announce Type: replace Abstract: Realistic human geometry generation is an important yet challenging task, requiring both the preservation of fine clothing details and the accurate
arXiv:2604.27636v1 Announce Type: new Abstract: Predicting stable and metastable structures is central to molecular and materials discovery, but remains limited by the cost of searching high-dimension
arXiv:2604.27914v1 Announce Type: new Abstract: When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than adm
arXiv:2604.27175v1 Announce Type: new Abstract: Contact-rich manipulation is challenging due to its high dimensionality, the requirement for long time horizons, and the presence of hybrid contact dyna
arXiv:2411.18796v2 Announce Type: replace Abstract: Early diagnosis and discovery of therapeutic drug targets are crucial objectives for effective management of Alzheimer's Disease (AD). Current appro
arXiv:2509.16248v3 Announce Type: replace-cross Abstract: This paper presents GRAPHMEND, a high-level compiler technique that eliminates FX graph breaks in PyTorch 2 programs. Although PyTorch 2 intro
arXiv:2602.11084v2 Announce Type: replace-cross Abstract: Feature selection remains a major challenge in medical prediction, where existing approaches such as LASSO often lack robustness and interpret
arXiv:2604.28111v1 Announce Type: new Abstract: End-to-end (E2E) autonomous driving presents a promising approach for translating perceptual inputs directly into driving actions. However, prohibitive
arXiv:2603.26571v3 Announce Type: replace-cross Abstract: At ultra-low bitrates, high-fidelity reconstruction requires sampling plausible videos from the posterior rather than regressing to oversmooth
arXiv:2604.28196v1 Announce Type: new Abstract: Driving world models serve as a pivotal technology for autonomous driving by simulating environmental dynamics. However, existing approaches predominant
arXiv:2604.04306v2 Announce Type: replace-cross Abstract: The increasing frequency and severity of climate related disasters have intensified the need for real time monitoring, early warning, and info
arXiv:2604.27903v1 Announce Type: new Abstract: The rapid evolution of generative models has enabled the creation of highly realistic and diverse synthetic images, posing significant challenges to rel
arXiv:2604.27790v1 Announce Type: cross Abstract: Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generativ
arXiv:2604.27147v1 Announce Type: cross Abstract: In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human prefe
arXiv:2604.27364v1 Announce Type: new Abstract: Hyperspectral image classification demands spatially coherent predictions and precise boundary delineation. Yet prevailing superpixel-based methods face