Knowledge catalogue
arXiv:2604.09595v1 Announce Type: cross Abstract: Post-training compression reduces LLM parameter counts but often produces irregular tensor dimensions that degrade GPU performance -- a phenomenon we
arXiv:2602.02343v3 Announce Type: replace-cross Abstract: Methods for controlling large language models (LLMs), including local weight fine-tuning, LoRA-based adaptation, and activation-based interven
arXiv:2604.10079v1 Announce Type: new Abstract: Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent fa
arXiv:2602.08661v2 Announce Type: replace Abstract: Human pose estimation is fundamental to intelligent perception in the Internet of Things (IoT), enabling applications ranging from smart healthcare
arXiv:2512.06879v3 Announce Type: replace-cross Abstract: We present extsc{WisPaper}, an end-to-end agent system that transforms how researchers discover, organize, and track academic literature. The
arXiv:2604.11351v1 Announce Type: new Abstract: Imitation learning is a powerful paradigm for training robotic policies, yet its performance is limited by compounding errors: minor policy inaccuracies
arXiv:2604.10202v1 Announce Type: cross Abstract: Neural networks (NNs) are central to modern machine learning and achieve state-of-the-art results in many applications. However, the relationship betw
arXiv:2604.10569v1 Announce Type: new Abstract: Decision-tree ensembles are a cornerstone of predictive modeling, and SHAP is a standard framework for interpreting their predictions. Among its variant
arXiv:2604.01929v2 Announce Type: replace-cross Abstract: The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines.
arXiv:2604.10589v1 Announce Type: new Abstract: We introduce a hierarchical categorical framework for Schema-Based Learning (SBL) structured across four interconnected levels. At the schema level, a f
arXiv:2601.14477v2 Announce Type: replace-cross Abstract: Until open-world foundation models match the performance of specialized approaches, deep learning systems remain dependent on task- and sensor
arXiv:2604.10968v1 Announce Type: new Abstract: Most conversational agents (CAs) are designed to satisfy user needs through user-driven interactions. However, many real-world settings, such as academi
arXiv:2604.10966v1 Announce Type: cross Abstract: We present a discriminative multimodal reward model that scores all candidate responses in a single forward pass. Conventional discriminative reward m
arXiv:2604.10827v1 Announce Type: new Abstract: Compute scaling for LLM reasoning requires allocating budget between exploring solution approaches (breadth) and refining promising solutions (depth). M
arXiv:2604.09985v1 Announce Type: new Abstract: Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models agains
arXiv:2508.04038v2 Announce Type: replace Abstract: Motion sensor time-series are central to Human Activity Recognition (HAR), yet conventional approaches are constrained to fixed activity sets and ty
arXiv:2604.03420v2 Announce Type: replace-cross Abstract: We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantizati
arXiv:2604.09713v1 Announce Type: new Abstract: Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods st
arXiv:2604.10333v1 Announce Type: new Abstract: Young children demonstrate early abilities to understand their physical world, estimating depth, motion, object coherence, interactions, and many other
arXiv:2604.10898v1 Announce Type: new Abstract: Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reac
arXiv:2604.09244v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as the mainstream of embodied intelligence. Recent VLA models have expanded their input modalities fr
arXiv:2604.08645v1 Announce Type: cross Abstract: Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucin
arXiv:2512.17012v3 Announce Type: replace Abstract: Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4
arXiv:2604.09294v1 Announce Type: new Abstract: Dexterity is a central yet ambiguously defined concept in the design and evaluation of anthropomorphic robotic hands. In practice, the term is often use
arXiv:2604.08890v1 Announce Type: cross Abstract: Modeling causal relationships in graph representation learning remains a fundamental challenge. Existing approaches often draw on theories and methods
arXiv:2511.20151v2 Announce Type: replace Abstract: Learned image compression (LIC) has recently benefited from Transformer- and state space models (SSM)- based backbones for modeling long-range depen
arXiv:2604.09157v1 Announce Type: cross Abstract: We introduce a novel learning framework for accelerated Monte Carlo (MC) dose calculation termed Energy-Shifting. This approach leverages deep learnin
arXiv:2604.08749v1 Announce Type: new Abstract: How many of a neural network's parameters actually encode task-specific information? We investigate this question with LottaLoRA, a training paradigm in
arXiv:2604.08874v1 Announce Type: cross Abstract: This study proposes a temporal modeling framework with a counterfactual policy-simulation layer for student dropout in higher education, using LMS eng
arXiv:2604.08935v1 Announce Type: cross Abstract: Causal discovery from observational data remains a fundamental challenge in machine learning and statistics, particularly when variables represent inh
arXiv:2604.09208v1 Announce Type: cross Abstract: We develop a predictive-first optimisation framework for streaming hidden Markov models. Unlike classical approaches that prioritise full posterior re
arXiv:2604.08561v1 Announce Type: new Abstract: We investigate how successful bias mitigation reshapes the embedding space of encoder-only and decoder-only foundation models, offering an internal audi
arXiv:2604.08610v1 Announce Type: new Abstract: This paper presents a semi-automated framework for transforming two-dimensional miniatures from medieval manuscripts into three-dimensional digital mode
arXiv:2602.22812v2 Announce Type: replace Abstract: Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt cachi
arXiv:2604.08718v1 Announce Type: cross Abstract: Geometric Foundation Models (GFMs) have recently advanced monocular SLAM by providing robust, calibration-free 3D priors. However, deploying these mod
arXiv:2604.08755v1 Announce Type: cross Abstract: Computational models support high-stakes decisions across engineering and science, and practitioners increasingly seek probabilistic predictions to qu
arXiv:2604.09466v1 Announce Type: new Abstract: Under the lens of Marr's levels of analysis, we critique and extend two claims about language models (LMs) and language processing: first, that predicti
arXiv:2604.08588v1 Announce Type: cross Abstract: Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, es
arXiv:2604.08990v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have created new opportunities for facial expression recognition (FER), moving it beyond pur
arXiv:2604.03512v2 Announce Type: replace Abstract: Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven dec
arXiv:2604.08744v1 Announce Type: cross Abstract: The discovery of new energetic materials is critical for advancing technologies from defense to private industry. However, experimental approaches rem
arXiv:2604.05529v2 Announce Type: replace Abstract: Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limi
arXiv:2604.09437v1 Announce Type: new Abstract: A novel regularization technique, AdaCubic, is proposed that adapts the weight of the cubic term. The heart of AdaCubic is an auxiliary optimization pro
arXiv:2604.08742v1 Announce Type: cross Abstract: Adam has achieved strong empirical success, but its theory remains incomplete even in the deterministic full-batch setting, largely because adaptive p
arXiv:2604.04161v2 Announce Type: replace Abstract: In Vision-Language-Action (VLA) models, action chunking (i.e., executing a sequence of actions without intermediate replanning) is a key technique t
arXiv:2604.08891v1 Announce Type: new Abstract: In Bayesian optimization, Thompson sampling selects the evaluation point by sampling from the posterior distribution over the objective function maximiz
arXiv:2604.08893v1 Announce Type: cross Abstract: Glioma is a harmful brain tumor that requires early detection to ensure better health results. Early detection of this tumor is key for effective trea
arXiv:2509.26435v2 Announce Type: replace-cross Abstract: Controllable summarization moves beyond generic outputs toward human-aligned summaries guided by specified attributes. In practice, the interd
arXiv:2604.08595v1 Announce Type: cross Abstract: Existing evaluation methods for LLM-based AI systems, such as LLM-as-a-Judge, verdict systems, and NLI, do not always align well with human assessment
arXiv:2604.08779v1 Announce Type: new Abstract: Large language models (LLMs) have significant potential to improve operational efficiency in operations management. Deploying these models requires spec
arXiv:2512.07417v2 Announce Type: replace Abstract: Effective traffic control is essential for mitigating congestion in transportation networks. Conventional traffic management strategies, including r
arXiv:2604.09462v1 Announce Type: new Abstract: Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces high
arXiv:2604.09210v1 Announce Type: new Abstract: Monocular imaging of animals inherently reduces 3D structures to 2D projections. Detection algorithms lead to 2D bounding boxes that lack information ab
arXiv:2604.08580v1 Announce Type: cross Abstract: Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal contr
arXiv:2604.09035v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) with autoregressive world models suffers from compounding errors, whereas diffusion world models mitigate this
arXiv:2510.20512v2 Announce Type: replace Abstract: Recent progress in accelerating text-to-image diffusion models enables high-fidelity synthesis within a single denoising step. However, customizing
arXiv:2604.08750v1 Announce Type: new Abstract: Plant-level control is an emerging wind energy technology that presents opportunities and challenges. By controlling turbines in a coordinated manner vi
arXiv:2604.06111v2 Announce Type: replace Abstract: Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41% of total evaluation time) and imbal
arXiv:2604.09470v1 Announce Type: new Abstract: Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and com
arXiv:2502.08691v2 Announce Type: replace-cross Abstract: Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significa