Knowledge catalogue
arXiv:2605.16524v1 Announce Type: cross Abstract: Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under
arXiv:2605.16879v1 Announce Type: new Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for ensur
arXiv:2605.17064v1 Announce Type: new Abstract: Large language models optimized for instruction following and agentic tasks remain poorly aligned with the requirements of high-quality creative writing
arXiv:2602.10503v2 Announce Type: replace Abstract: Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. H
arXiv:2511.02610v2 Announce Type: replace Abstract: The development of smart systems (i.e., systems enhanced with AI components) has thrived thanks to the rapid advancements in neural networks (NNs).
arXiv:2605.17250v1 Announce Type: new Abstract: Test-time adaptation (TTA) has recently emerged as a promising approach for improving time series forecasting (TSF) under distribution shift. Existing T
arXiv:2605.17247v1 Announce Type: new Abstract: Argumentative essays serve as a vital medium for assessing critical thinking and reasoning skills, yet there is limited works on accurately understandin
arXiv:2605.17994v1 Announce Type: cross Abstract: New item growth is critical for maintaining a healthy ecosystem in large-scale e-commerce platforms. However, existing systems tend to prioritize pres
arXiv:2605.18385v1 Announce Type: cross Abstract: We present UbiSLAM, an innovative solution for real-time mapping and localization in dynamic indoor environments. By deploying a network of fixed RGB-
arXiv:2605.17772v1 Announce Type: new Abstract: Physical adversarial attacks often overfit single surrogate models and optimization objectives. While ensemble attacks can mitigate this, existing metho
arXiv:2605.17704v1 Announce Type: new Abstract: The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights an
arXiv:2601.20306v2 Announce Type: replace Abstract: All-in-one image restoration aims to address diverse degradation types using a single unified model. Existing methods typically rely on degradation
arXiv:2512.11089v4 Announce Type: replace-cross Abstract: We introduce test prediction variance (TPV)--the first-order sensitivity of a trained model's outputs to parameter perturbations--as a unifyin
arXiv:2605.16740v1 Announce Type: new Abstract: Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora.
arXiv:2605.18163v1 Announce Type: new Abstract: Hallucination correction is not a one-direction problem. We show that intermediate layers are neither uniformly more truthful than final layers nor unif
arXiv:2603.04161v2 Announce Type: replace Abstract: The False Belief Test (FBT) has been the main method for assessing Theory of Mind (ToM) and related socio-cognitive competencies. For Large Language
arXiv:2601.19624v2 Announce Type: replace-cross Abstract: Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy,
arXiv:2605.16269v1 Announce Type: cross Abstract: Modern military operations expose soldiers to sustained psychological stress, leading to acute reactions, post-traumatic stress symptoms, and other me
arXiv:2605.17938v1 Announce Type: cross Abstract: Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current
arXiv:2605.16810v1 Announce Type: new Abstract: We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable
arXiv:2605.17660v1 Announce Type: cross Abstract: Transformers have become the dominant architecture in modern machine learning, yet the theoretical understanding of their training dynamics remains li
arXiv:2605.16397v1 Announce Type: cross Abstract: The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving ef
arXiv:2605.17928v1 Announce Type: cross Abstract: Transfer Learning, a technique where a model/agent can use the knowledge/expertise that it gained from one task and exploit that to solve another clos
arXiv:2605.16735v1 Announce Type: cross Abstract: The deployment of 5G Multicast-Broadcast Services (MBS) is emerging as a critical technology for spectral-efficient UHD content delivery and serving a
arXiv:2505.03205v3 Announce Type: replace Abstract: Transformers serve as the foundational architecture for large language and video generation models, such as GPT, BERT, SORA and their successors. Em
arXiv:2605.17342v1 Announce Type: cross Abstract: Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General P
arXiv:2605.16572v1 Announce Type: new Abstract: Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly i
arXiv:2605.17170v1 Announce Type: new Abstract: Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context process
arXiv:2605.17465v1 Announce Type: new Abstract: Learning causal relations from observational data is challenging because the graph search space grows super-exponentially with the number of variables.
arXiv:2605.17453v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly rely on external tools to make consequential decisions, yet most existing agent-security benchmarks and defenses im
arXiv:2602.12687v2 Announce Type: replace-cross Abstract: The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how clas
arXiv:2409.10102v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs). Although ex
arXiv:2510.06388v2 Announce Type: replace Abstract: Calibrated predictions are useful because their numerical values can be interpreted as probabilities. Calibration errors are therefore widely used t
arXiv:2605.16638v1 Announce Type: new Abstract: Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradig
arXiv:2509.23986v2 Announce Type: replace Abstract: Scientific discovery is often slowed by the manual development of computational tools needed to analyze complex experimental data. Building such too
arXiv:2605.16443v1 Announce Type: cross Abstract: Despite the success of deep neural networks in vision, medical diagnosis, and IoT scenarios, their deployment on resource-limited platforms poses seri
arXiv:2605.17942v1 Announce Type: new Abstract: Feed-forward 3D reconstruction has recently demonstrated strong generalization across diverse scenes, yet its performance in UAV imagery remains underex
arXiv:2605.16690v1 Announce Type: new Abstract: Heterogeneous LoRA-rank methods address system heterogeneity in federated fine-tuning of foundation models by assigning client-specific ranks based on c
arXiv:2601.12696v2 Announce Type: replace Abstract: Current guardian models are predominantly Western-centric and optimized for high-resource languages, leaving low-resource African languages vulnerab
arXiv:2605.17140v1 Announce Type: cross Abstract: Brain tumor diagnosis is largely dependent on Magnetic Resonance Imaging (MRI) evaluation, which requires radiologists to synthesize thousands of imag
arXiv:2605.17788v1 Announce Type: cross Abstract: A fundamental challenge in recommender systems is balancing reliability for Low-Active Users (LAUs) with diversity for High-Active Users (HAUs). The k
arXiv:2502.17007v2 Announce Type: replace-cross Abstract: In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an il
arXiv:2605.18008v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is critical for safety-critical domains like healthcare, yet it is rarely evaluated under realistic out-of-distribution
arXiv:2506.10959v3 Announce Type: replace-cross Abstract: While in-context learning (ICL) has achieved remarkable success in natural language and vision domains, its theoretical understanding-particul
arXiv:2605.17575v1 Announce Type: cross Abstract: Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution s
arXiv:2605.16750v1 Announce Type: cross Abstract: Personalized exercise recommendation dynamically aligns pedagogical resources with individual knowledge mastery, which is crucial for satisfying stude
arXiv:2605.18611v1 Announce Type: new Abstract: We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 huma
arXiv:2603.02667v2 Announce Type: replace Abstract: Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives d
arXiv:2605.17356v1 Announce Type: new Abstract: Existing works typically focus on presentation generation under isolated input settings, whereas real-world use cases span diverse scenarios, including
arXiv:2605.17936v1 Announce Type: new Abstract: Recent works have illustrated that modern NLP models trained for diverse tasks ranging from sentiment analysis to language generation succumb to univers
arXiv:2605.16719v1 Announce Type: cross Abstract: Scientific and technological frontiers advance through punctuated dynamics, yet the principles governing these dynamics remain poorly understood. Here
arXiv:2605.16815v1 Announce Type: cross Abstract: Graph neural networks (GNNs) have achieved remarkable success in relational learning. However, their vulnerability to graph backdoor attacks (GBAs) po
arXiv:2509.22459v4 Announce Type: replace-cross Abstract: While achieving exceptional generative quality, modern diffusion, flow, and other matching models suffer from slow inference, as they require
arXiv:2602.19710v2 Announce Type: replace Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level percept
arXiv:2401.03717v4 Announce Type: replace-cross Abstract: Time-series data exists in every corner of real-world systems and services, ranging from satellites in the sky to wearable devices on human bo
arXiv:2504.20734v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external kn
arXiv:2505.16831v3 Announce Type: replace-cross Abstract: Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like
arXiv:2605.17976v1 Announce Type: new Abstract: Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for
arXiv:2602.22801v2 Announce Type: replace-cross Abstract: Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving
arXiv:2605.17822v1 Announce Type: new Abstract: Infrared object detection is crucial for perception in autonomous driving and surveillance but remains vulnerable to physical adversarial attacks. Unlik