Knowledge catalogue
arXiv:2605.08169v1 Announce Type: cross Abstract: Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-t
arXiv:2605.09822v1 Announce Type: cross Abstract: We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use p
arXiv:2605.08516v1 Announce Type: new Abstract: Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-base
arXiv:2502.06830v5 Announce Type: replace-cross Abstract: Probabilistic intraday electricity price forecasting is becoming increasingly important for short-term power-system operation. With increasing
arXiv:2605.08876v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augmented, multi-step tasks, where latency is a critical f
arXiv:2510.09887v2 Announce Type: replace Abstract: Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confident
arXiv:2602.06733v2 Announce Type: replace-cross Abstract: Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their
arXiv:2605.10341v1 Announce Type: new Abstract: A LaTeX manuscript that compiles without error is not necessarily publication-ready. The resulting PDFs frequently suffer from misplaced floats, overflo
arXiv:2512.02066v2 Announce Type: replace-cross Abstract: Quantum machine learning has emerged as a promising approach to improve feature extraction and classification tasks in high-dimensional data d
arXiv:2605.09781v1 Announce Type: cross Abstract: Large Language Models exhibit mode collapse, producing homogeneous outputs that fail to explore valid solution spaces. We present QD-LLM, a framework
parameter golf was a blast. 2,000+ submissions. 1,000+ verified github accounts. ideas ranging from quantization and depth recurrence to TTT LoRA, SSMs, H-nets, JEPA, and more. autoresearch made itera
arXiv:2605.10219v1 Announce Type: cross Abstract: We study the parameterized complexity of testing approximate first-order stationarity at a prescribed point for continuous piecewise-affine (PA) funct
arXiv:2605.08102v1 Announce Type: new Abstract: We propose PathBoost, a gradient tree boosting method for graph-level classification and regression that learns discriminative path-based features direc
arXiv:2605.09636v1 Announce Type: new Abstract: PDE-to-solver code generation aims to automatically synthesize executable numerical solvers from partial differential equation (PDE) specifications. Thi
arXiv:2605.10136v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) train a single neural approximation by minimizing multiple physics- and data-derived losses, but the gradients
arXiv:2605.10936v1 Announce Type: new Abstract: As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the
arXiv:2605.09119v1 Announce Type: cross Abstract: Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistic
arXiv:2605.08673v1 Announce Type: new Abstract: Online clustering methods that adaptively create and update nodes as data arrive often make node learning explicit, whereas the mapping from the learned
arXiv:2605.10391v1 Announce Type: cross Abstract: We introduce Phoenix-VL 1.5 Medium, a 123B-parameter natively multimodal and multilingual foundation model, adapted to regional languages and the Sing
arXiv:2605.10806v1 Announce Type: cross Abstract: Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern re
arXiv:2502.03749v2 Announce Type: replace Abstract: Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic
arXiv:2602.00593v2 Announce Type: replace Abstract: Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and e
arXiv:2605.10032v1 Announce Type: new Abstract: Cell-type-specific marker genes are fundamental to plant biology, yet existing resources primarily rely on curated databases or high-throughput studies
arXiv:2605.10275v1 Announce Type: new Abstract: Polarimetric imaging captures surface polarization characteristics, such as the Degree of Linear Polarization (DoLP) and the Angle of Polarization (AoP)
arXiv:2410.14702v2 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) exhibit impressive problem-solving abilities in various domains, but their visual comprehension and abstra
arXiv:2605.09504v1 Announce Type: cross Abstract: We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, paral
arXiv:2507.23009v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable results on a range of standardized tests originally designed to assess human cognitive a
arXiv:2605.08800v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) may memorize sensitive cross-modal information during pretraining. However, existing MLLM unlearning benchmar
arXiv:2602.03190v3 Announce Type: replace-cross Abstract: Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown strong potential for improving the mathematical
arXiv:2605.09169v1 Announce Type: cross Abstract: A Mamba state-space model trained only for next-step prediction appears to recover Granger-causal structure through a simple readout S = |W_{out} W_{i
arXiv:2605.08687v1 Announce Type: cross Abstract: Data preparation is a central and time-consuming stage in data analysis workflows. Traditionally, commercial tools have relied on graphical user inter
arXiv:2505.19519v3 Announce Type: replace Abstract: Personalizing text-to-image diffusion models involves integrating novel visual concepts from a small set of reference images while retaining the mod
arXiv:2605.08879v1 Announce Type: new Abstract: Unconstrained fine-tuning of flow-matching Vision-Language-Action (VLA) models drives dense parameter overwrites, degrading pre-trained capabilities. We
arXiv:2605.09825v1 Announce Type: cross Abstract: Why does full-pipeline FP4 training of large language models often diverge, even when forward activations and activation gradients remain stable? We a
arXiv:2605.08786v1 Announce Type: new Abstract: Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge
arXiv:2605.10529v1 Announce Type: new Abstract: Biomedical knowledge graphs underwrite drug repurposing and clinical decision support, yet the upstream ontologies they depend on update on independent
arXiv:2605.08301v1 Announce Type: cross Abstract: Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fad
arXiv:2605.10482v1 Announce Type: cross Abstract: Event-triggered control provides a mechanism for avoiding excessive use of constrained communication bandwidth in networked multi-agent systems. Howev
arXiv:2605.10614v1 Announce Type: new Abstract: Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear
arXiv:2508.21146v2 Announce Type: replace Abstract: Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely
arXiv:2605.09228v1 Announce Type: cross Abstract: Most LLM benchmarks score how well a model responds to explicit requests. They leave unmeasured a different conversational ability: noticing and actin
arXiv:2509.26574v4 Announce Type: replace Abstract: While large language models (LLMs) with reasoning capabilities are progressing rapidly on high-school math competitions and coding, can they reason
arXiv:2605.08578v1 Announce Type: cross Abstract: Developing generalist systems that retain human-like data efficiency is a central challenge. While world models (WMs) offer a promising path, existing
arXiv:2605.06524v2 Announce Type: replace Abstract: Reliable human-machine discrimination is becoming increasingly important as large language models and autonomous agents are deployed in online setti
arXiv:2605.10629v1 Announce Type: new Abstract: Recently, diffusion models have attracted considerable attention for magnetic resonance image reconstruction due to their high sample quality. However,
arXiv:2605.10664v1 Announce Type: cross Abstract: Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream
arXiv:2510.25372v2 Announce Type: replace Abstract: Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for
arXiv:2605.09431v1 Announce Type: new Abstract: Cryptocurrency pump-and-dump schemes coordinated via Telegram threaten market integrity. However, existing research addressing this specific threat has
arXiv:2504.12334v2 Announce Type: replace Abstract: Large language models (LLMs) face significant challenges in specialized biomedical tasks due to the inherent complexity of medical reasoning and the
arXiv:2605.10931v1 Announce Type: cross Abstract: Transformers with self-attention modules as their core components have become an integral architecture in modern large language and foundation models.
arXiv:2605.09808v1 Announce Type: new Abstract: User simulators are increasingly leveraged to build interactive AI assistants, yet how to measure the quality of these simulators remains an open questi
arXiv:2605.08170v1 Announce Type: new Abstract: Neural operators have emerged as a powerful tool for learning mappings between infinite-dimensional function spaces. However, their approximation proper
arXiv:2605.09691v1 Announce Type: new Abstract: Population pharmacokinetic/pharmacodynamic (PK/PD) modeling traditionally relies on classical ordinary differential equations to simulate drug dynamics.
arXiv:2406.19581v2 Announce Type: replace-cross Abstract: Decomposing surface electromyography (EMG) into the spike trains of individual motor neurons is a long-standing inverse problem and a key step
arXiv:2605.08423v1 Announce Type: cross Abstract: We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficienc
arXiv:2605.10296v1 Announce Type: cross Abstract: We participated in the Fifth UNLP shared task on multi-domain document understanding, where systems must answer Ukrainian multiple-choice questions fr
arXiv:2605.10730v1 Announce Type: new Abstract: We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a si
arXiv:2603.11566v2 Announce Type: replace Abstract: 4D radar-camera sensing configuration has gained increasing importance in autonomous driving. However, existing 3D object detection methods that fus
arXiv:2605.10761v1 Announce Type: new Abstract: Cancer screening is a reasoning task. A radiologist observes findings, compares them to prior scans, integrates clinical context, and reaches a diagnost
arXiv:2605.08857v1 Announce Type: new Abstract: Recent advances in uncertainty quantification for time series forecasting show that conformal prediction can provide reliable prediction intervals, yet