arXiv:2603.03354v2 Announce Type: replace Abstract: Although obtaining deep brain activity from non-invasive scalp electroencephalography (sEEG) is crucial for neuroscience and clinical diagnosis, directly generating high-fidelity intracranial electroencephalography (iEEG) signals remains a largely unexplored field, limiting our understanding of deep brain dynamics. Current research primarily focuses on traditional signal processing or source localization methods, which struggle […]
GRADIEND: Feature Learning within Neural Networks Exemplified through Biases
arXiv:2502.01406v4 Announce Type: replace-cross Abstract: AI systems frequently exhibit and amplify social biases, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to learn a feature neuron encoding societal bias information such as gender, race, and religion. We show that our method can not only identify […]
LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling
arXiv:2507.00790v4 Announce Type: replace-cross Abstract: Unified image restoration is a significantly challenging task in low-level vision. Existing methods either make tailored designs for specific tasks, limiting their generalizability across various types of degradation, or rely on training with paired datasets, thereby suffering from closed-set constraints. To address these issues, we propose a novel, dataset-free, and […]
Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
arXiv:2510.19195v4 Announce Type: replace-cross Abstract: Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often overlook the evaluation of downstream perception tasks, which are $mathbfreally crucial$ for the performance of autonomous driving. Existing methods […]
The Algorithmic Gaze of Image Quality Assessment: An Audit and Trace Ethnography of the LAION-Aesthetics Predictor
arXiv:2601.09896v3 Announce Type: replace-cross Abstract: Visual generative AI models are trained using a one-size-fits-all measure of aesthetic appeal. However, what is deemed “aesthetic” is inextricably linked to personal taste and cultural values, raising the question of whose taste is represented in visual generative AI models. In this work, we study an aesthetic evaluation model–LAION-Aesthetics Predictor […]
A cocktail of chemical reaction networks and mathematical epidemiology tools for positive ODE stability problems
arXiv:2603.06778v1 Announce Type: new Abstract: We continue recent attempts to put together concepts and results of Chemical Reaction Networks theory (CRNT) and Mathematical Epidemiology (ME), for solving problems of stability of positive ODEs. We provide first an elegant CRN-flavored generalization of the most cited result in ME, the Next Generation Matrix (NGM) theorem. We review […]
Evaluating LLM-Based Grant Proposal Review via Structured Perturbations
arXiv:2603.08281v1 Announce Type: cross Abstract: As AI-assisted grant proposals outpace manual review capacity in a kind of “Malthusian trap” for the research ecosystem, this paper investigates the capabilities and limitations of LLM-based grant reviewing for high-stakes evaluation. Using six EPSRC proposals, we develop a perturbation-based framework probing LLM sensitivity across six quality axes: funding, timeline, […]
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
arXiv:2603.06594v1 Announce Type: cross Abstract: Automated enquoteLLM-as-a-Judge frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to benchmark the robustness of safety against adversarial attacks. However, we show that existing validation protocols fail to account […]
Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
arXiv:2603.03099v2 Announce Type: replace-cross Abstract: Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the existing theory yields guarantees essentially comparable to those of SGD, leaving the empirical performance gap insufficiently explained. In this paper, we uncover a key second-moment normalization in Adam and develop a stopping-time/martingale analysis that provably distinguishes […]
CrystaL: Spontaneous Emergence of Visual Latents in MLLMs
arXiv:2602.20980v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in continuous hidden states, facilitating seamless vision-language integration and faster inference. However, existing heuristically predefined supervision signals in latent CoT provide limited guidance […]
Not all tokens are needed(NAT): token efficient reinforcement learning
arXiv:2603.06619v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with optimized rollout engines, full-token updates can consume a large fraction of total training cost, turning token length […]
Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark
arXiv:2603.06582v1 Announce Type: cross Abstract: Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted “agentic” AI applications, which, powered by LLMs’ planning capabilities, promise to solve complex tasks with the access of external tools and data sources. In this context, publicly available SPARQL endpoints offer […]