Knowledge catalogue
arXiv:2605.01847v1 Announce Type: new Abstract: Outcome-only evaluation under-specifies whether an evaluated agent profile preserves the commitments required to solve a multi-turn task coherently. Neu
arXiv:2603.20562v2 Announce Type: replace Abstract: Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We
arXiv:2605.03999v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art segmentation accuracy but require large training datasets because each layer has unique parameters t
arXiv:2605.02964v1 Announce Type: new Abstract: Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomou
arXiv:2605.03269v1 Announce Type: cross Abstract: While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intellig
arXiv:2605.02946v1 Announce Type: new Abstract: Safety alignment is critical for the responsible deployment of large language models (LLMs). As Mixture-of-Experts (MoE) architectures are increasingly
arXiv:2605.02900v1 Announce Type: cross Abstract: Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, saf
arXiv:2605.03706v1 Announce Type: new Abstract: Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large l
arXiv:2503.06917v5 Announce Type: replace Abstract: We study zeroth-order optimization where solutions must minimize a cost d(s) while maintaining high probability under a complex generative prior L(s
arXiv:2605.03874v1 Announce Type: new Abstract: Classification of EEG signals using shallow Convolutional Neural Networks (CNNs) is a prevalent and successful approach across a variety of fields. Most
arXiv:2605.01307v1 Announce Type: cross Abstract: This paper investigates coordinated downlink transmission in a multi-base station (multi-BS) multi-reconfigurable intelligent surface (multi-RIS)-assi
arXiv:2510.24211v2 Announce Type: replace Abstract: Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrain
arXiv:2605.03303v1 Announce Type: new Abstract: Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that exis
arXiv:2605.03927v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown remarkable performance in various robotic tasks, as they can perceive visual information and understand natural
arXiv:2604.00754v2 Announce Type: replace Abstract: The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest
arXiv:2605.03429v1 Announce Type: cross Abstract: Artificial satellites and space debris increasingly contaminate astronomical images, affecting scientific surveys and producing large volumes of strea
arXiv:2605.03849v1 Announce Type: new Abstract: Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching
arXiv:2605.03315v1 Announce Type: new Abstract: Cross-View Geo-localisation (CVGL) matches ground imagery against satellite tiles to give absolute position fixes, an alternative to GNSS where signals
arXiv:2605.03642v1 Announce Type: new Abstract: Open-vocabulary object detection aims to recognize objects from an open set of categories, which leverages vision-language models (VLMs) pre-trained on
arXiv:2604.25000v2 Announce Type: replace Abstract: Recent work has framed intelligence in verifiable tasks as reducing time-to-solution through learned structure and test-time search, while systems w
arXiv:2605.02958v1 Announce Type: cross Abstract: Representation Engineering typically relies on static refusal vectors derived from terminal representations. We move beyond this paradigm, demonstrati
arXiv:2605.03716v1 Announce Type: new Abstract: Multimodal visual object tracking can be divided into to several kinds of tasks (e.g. RGB and RGB+X tracking), based on the input modality. Existing met
arXiv:2605.02591v1 Announce Type: new Abstract: The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions, yet existing approaches often struggle to bala
arXiv:2605.01278v1 Announce Type: new Abstract: In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understandi
arXiv:2603.28489v2 Announce Type: cross Abstract: The rapid evolution of video generation has enabled models to simulate complex physical dynamics and long-horizon causalities, positioning them as pot
The AI era demands a fundamental shift in security, and that includes identity and access management (IAM). Traditional controls simply aren’t built for autonomous AI agents that interact with sensiti
arXiv:2605.02920v1 Announce Type: cross Abstract: Standard transformer architectures learn fixed slow-weight representations during training and lack mechanisms for rapid adaptation within an episode.
arXiv:2605.02300v1 Announce Type: new Abstract: Applying concepts related to zero-shot meta-learning and pre-training of foundation models, we develop a meta reinforcement learning approach (denoted M
arXiv:2605.02035v1 Announce Type: new Abstract: Ambiguity resolution is a key challenge in multimodal machine translation (MMT), where models must genuinely leverage visual input to map an ambiguous e
arXiv:2605.02525v1 Announce Type: new Abstract: Autonomous indoor mobile robots can navigate reliably to metric coordinates using established frameworks such as ROS 2 Navigation 2, yet they lack the a
arXiv:2605.02472v1 Announce Type: new Abstract: Legal texts often contain computational legal clauses--provisions whose understanding requires complex logic. While frontier Large Reasoning Models (LRM
arXiv:2605.01657v1 Announce Type: new Abstract: Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic in
arXiv:2605.01741v1 Announce Type: new Abstract: Cone Beam Computed Tomography (CBCT) is pivotal for 3D diagnostic imaging in dentistry. However, the development of robust AI models for volumetric anal
arXiv:2605.02892v1 Announce Type: new Abstract: Personalized image completion aims to restore occluded regions in personal photos while preserving identity and appearance. Existing methods either rely
arXiv:2605.02439v1 Announce Type: new Abstract: Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to r
arXiv:2605.00136v1 Announce Type: new Abstract: Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we
arXiv:2601.18569v2 Announce Type: replace-cross Abstract: In this letter, we propose an Attention-Based Neural-Augmented Kalman Filter (AttenNKF) for state estimation in legged robots. Foot slip is a
arXiv:2605.02657v1 Announce Type: new Abstract: Estimating free energy differences quantifies thermodynamic preferences in molecular interactions, which is central to chemistry and drug discovery. Des
arXiv:2401.04139v4 Announce Type: replace Abstract: Handling class imbalance remains a central challenge in machine learning, particularly in pattern recognition tasks where identifying rare but criti
arXiv:2605.01346v1 Announce Type: new Abstract: Standard selective prediction methods typically estimate uncertainty from the output of a single predictive branch. While effective for general uncertai
The world of AI is rapidly shifting from experimental Large Language Models to an era of Agentic AI. In the agentic era, autonomous software agents act on behalf of employees and consumers—driving a f
arXiv:2601.21766v3 Announce Type: replace Abstract: Transformers are arguably the preferred architecture for language generation. In this paper, inspired by continued fractions, we introduce a new fun
arXiv:2605.01330v1 Announce Type: new Abstract: Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment.
arXiv:2605.00908v1 Announce Type: new Abstract: This paper presents a comparative evaluation of convolutional and transformer-based object detection architectures for early weed detection in realistic
arXiv:2603.07615v2 Announce Type: replace-cross Abstract: Modern visual generative models acquire rich visual knowledge through large-scale training, yet existing visual representations (such as pixel
arXiv:2605.01291v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are widely regarded as an energy-efficient paradigm for modeling and processing temporal and event-driven information. In
arXiv:2605.02600v1 Announce Type: new Abstract: While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understand
arXiv:2603.16969v2 Announce Type: replace-cross Abstract: This paper presents DeepStage, a deep reinforcement learning (DRL) framework for adaptive and stage-aware defense against Advanced Persistent
arXiv:2510.09883v2 Announce Type: replace Abstract: Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but th
arXiv:2605.00977v1 Announce Type: cross Abstract: The record of the beginning of the most widespread legal system in the world is contained in millions of pages of handwritten text. Most of the record
arXiv:2605.02109v1 Announce Type: new Abstract: The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathe
arXiv:2605.02313v1 Announce Type: new Abstract: Deep neural networks dominate modern machine learning, while alternative function approximators remain comparatively underexplored at scale. In this wor
Shares of DigitalOcean Holdings Inc. rocketed more than 40% today after the developer-oriented cloud infrastructure provider topped Wall Street targets in its fiscal 2026 first quarter. It also lifted
arXiv:2605.01848v1 Announce Type: new Abstract: Synthesizing longitudinal medical images at controllable disease stages while preserving patient-specific anatomy is hindered by the entanglement of pat
arXiv:2605.00941v1 Announce Type: cross Abstract: Flow matching has become a leading framework for generative modeling, but quantifying the uncertainty of its samples remains an open problem. Existing
arXiv:2603.19675v2 Announce Type: replace Abstract: Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically
arXiv:2605.01916v1 Announce Type: new Abstract: Infrared-visible image fusion aims to create an information-rich fused image by integrating the complementary thermal saliency from infrared sensing and
arXiv:2605.02794v1 Announce Type: new Abstract: We propose a modular framework for hybrid image restoration that integrates transformer and state-space model (SSM) blocks with a focus on improving run
arXiv:2605.01024v1 Announce Type: new Abstract: Multimodal Emotion Recognition (MER) is critical for interpreting real-world interactions. While Multimodal Large Language Models (MLLM) have shown prom
arXiv:2605.00960v1 Announce Type: cross Abstract: We introduce energy-based constraint networks -- a modality-agnostic architecture that learns structural coherence from contrastive pairs. The system