Knowledge catalogue
arXiv:2605.01338v1 Announce Type: new Abstract: System-level diagrams encode the architectural blueprint of chip design, specifying module functions, dataflows, and interface protocols. However, non-s
arXiv:2605.03175v1 Announce Type: new Abstract: The remote sensing (RS) domain suffers from a lack of densely labeled datasets, which are costly to obtain. Thus, models that can segment RS imagery wel
arXiv:2605.03069v1 Announce Type: cross Abstract: Federated learning (FL) lets distributed nodes train a shared model without exchanging their raw data, but in privacy-sensitive deployments medical se
arXiv:2605.03364v1 Announce Type: new Abstract: The task of Long-tailed Class Incremental Learning (LT-CIL) addresses the sequential learning of new classes from datasets with imbalanced class distrib
arXiv:2605.03061v1 Announce Type: cross Abstract: Time varying dependence is often modeled through dynamic correlations or Gaussian graphical models, yet many multivariate systems change through tail
arXiv:2605.03430v1 Announce Type: new Abstract: High-dimensional tabular data lacks a natural feature order, limiting the applicability of permutation-sensitive deep learning models. We propose DynaTa
arXiv:2605.03790v1 Announce Type: new Abstract: With advances in multimodal research and deep learning, Multimodal Large Language Models (MLLMs) have emerged as a powerful paradigm for a wide range of
arXiv:2605.03441v1 Announce Type: cross Abstract: Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We s
arXiv:2605.03969v1 Announce Type: new Abstract: AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central
arXiv:2605.03425v1 Announce Type: new Abstract: Differentially private (DP) training protects individual examples by adding noise to gradients, but the injected noise interacts nontrivially with adapt
arXiv:2605.03465v1 Announce Type: cross Abstract: Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data
arXiv:2605.03460v1 Announce Type: cross Abstract: Time series (TS) reasoning models (TSRMs) have shown promising capabilities in general domains, yet they consistently fail on financial domain, which
arXiv:2605.03984v1 Announce Type: new Abstract: Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function
arXiv:2605.03749v1 Announce Type: new Abstract: Ground-to-space astronomical super-resolution requires recovering space-quality images from ground-based observations that are simultaneously limited by
arXiv:2605.03669v1 Announce Type: new Abstract: Open-vocabulary semantic mapping enables robots to spatially ground previously unseen concepts without requiring predefined class sets. Current training
arXiv:2605.03750v1 Announce Type: new Abstract: Evidential Deep Learning (EDL) enables single-pass uncertainty estimation by predicting Dirichlet evidence, but it can remain overconfident and poorly c
arXiv:2605.02913v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central post-training tool for improving the reasoning abilities of large language models (LLMs). In these syst
arXiv:2605.03163v1 Announce Type: new Abstract: Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlin
arXiv:2605.03795v1 Announce Type: new Abstract: Urban air quality forecasting is challenging because pollutant concentrations are nonlinear, nonstationary, spatiotemporally dependent, and often affect
arXiv:2605.03901v1 Announce Type: cross Abstract: Local gauge structures play a central role in a wide range of condensed matter systems and synthetic quantum platforms, where they emerge as effective
arXiv:2605.03388v1 Announce Type: new Abstract: Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained mode
arXiv:2605.03403v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It ra
arXiv:2605.02832v1 Announce Type: new Abstract: Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary ch
arXiv:2605.00957v1 Announce Type: cross Abstract: Achieving the right amount of trust in AI systems is important, but challenging. The problem is exacerbated with the rise of Large Language Models (LL
arXiv:2605.03135v1 Announce Type: new Abstract: Standard classification treats all errors equally, but in content moderation, medical screening, and safety-critical applications, mistakes on clear-cut
arXiv:2602.16138v2 Announce Type: replace Abstract: We introduce IRIS (Intent Resolution via Inference-time Saccades), a novel training-free approach that uses eye-tracking data in real-time to resolv
arXiv:2605.02965v1 Announce Type: new Abstract: Artificial intelligence-generated content (AIGC) has emerged as a transformative paradigm for automating the creation of diverse and customized content,
arXiv:2605.02950v1 Announce Type: new Abstract: Transformer-based semantic retrieval is highly effective, yet in many deployments the dominant cost lies in online query encoding rather than corpus ind
Last week I gave a talk at AI Dev ’26 by @DeepLearningAI on “AI can’t read PDFs, how do we fix it” . I’m sharing the slides publicly if others are interested in doing a deep dive into document underst
arXiv:2605.03386v1 Announce Type: new Abstract: Spatiotemporal forecasting in physical systems, such as large-scale traffic networks, requires modeling a dual dynamic: continuous macroscopic rhythms a
arXiv:2605.03438v1 Announce Type: new Abstract: Pre-trained 3D point cloud foundation models (PFMs) have demonstrated strong transferability across diverse downstream tasks. However, full fine-tuning
arXiv:2605.03343v1 Announce Type: new Abstract: Medical image super-resolution (MedSR) is essential for improving diagnostic precision across diverse imaging modalities such as MRI, CT, X-ray, Ultraso
arXiv:2605.03555v1 Announce Type: new Abstract: Continual semantic segmentation requires models to adapt to new domains or modalities without sacrificing performance on previously learned tasks. Exper
arXiv:2602.05048v2 Announce Type: replace Abstract: Joint planning through language-based interactions is a key area of human-AI teaming. Planning problems in the open world often involve various aspe
arXiv:2603.10083v2 Announce Type: replace-cross Abstract: Quantum machine learning models based on parameterized circuits can be viewed as Fourier series approximators. However, they often struggle to
arXiv:2605.01566v1 Announce Type: new Abstract: Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw
arXiv:2605.02971v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain hig
arXiv:2605.03820v1 Announce Type: new Abstract: Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy cor
arXiv:2605.03799v1 Announce Type: new Abstract: This preprint presents a systematic, research-oriented practicum that guides the reader through the entire modern NLP pipeline: from tokenisation and ve
arXiv:2605.01797v1 Announce Type: new Abstract: Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend
arXiv:2605.01562v1 Announce Type: cross Abstract: The Object-Oriented Method for Requirements Authoring and Management (OOMRAM) is a requirements reuse framework that relies on exact identifier matchi
NEW paper from Microsoft Research. (bookmark it) The entire interpretability literature is built around human readers. As more analysis gets delegated to agents, the right target of interpretability s
arXiv:2505.08203v2 Announce Type: replace-cross Abstract: While recent advancements in AI music generation have predominantly focused on direct audio synthesis, these systems suffer from inherent rigi
arXiv:2605.03283v1 Announce Type: cross Abstract: We provide a unified theoretical analysis of Linear Discriminant Analysis with simultaneous multilabel scatter matrix formulations and Stiefel orthogo
arXiv:2412.14737v2 Announce Type: replace Abstract: The rise of large language models (LLMs) and their tight integration into our daily life make it essential to dedicate efforts towards their trustwo
arXiv:2605.04036v1 Announce Type: cross Abstract: Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominat
arXiv:2511.08717v4 Announce Type: replace-cross Abstract: Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (
arXiv:2505.04310v2 Announce Type: replace-cross Abstract: Distributional Reinforcement Learning (DistRL) improves upon expectation-based methods by modeling full return distributions, but standard app
arXiv:2605.01123v1 Announce Type: new Abstract: Large language models (LLMs) can provide automated feedback in educational settings, but aligning an LLMs style with a specific instructors tone while m
arXiv:2605.03399v1 Announce Type: new Abstract: Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operati
arXiv:2604.17654v3 Announce Type: replace Abstract: Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and sca
arXiv:2605.03964v1 Announce Type: new Abstract: Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and th
arXiv:2602.01842v3 Announce Type: replace Abstract: Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive de
arXiv:2605.01865v1 Announce Type: cross Abstract: Cooperative multi-agent reinforcement learning (MARL) requires agents to discover joint strategies in a combinatorially large state-action space, yet
arXiv:2605.03863v1 Announce Type: cross Abstract: The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well establi
arXiv:2605.03434v1 Announce Type: new Abstract: Reinforcement learning is one of the most challenging learning paradigms where efficacy and efficiency gains are extremely valuable. Hierarchical reinfo
arXiv:2605.03344v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning
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:2511.18772v2 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) have become valuable intellectual property of model owners, due to the substantial resources required for their de
arXiv:2605.02912v1 Announce Type: new Abstract: Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor