Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,059 papers.
28 May 2026
Recent research demonstrating AI systems exhibiting deception and shutdown resistance suggests that AI loss of control (LOC) is an urgent policy concern , yet current literature focuses almost exclusively on alignment and prevention.
28 May 2026
Post-link optimizers (PLOs) such as Propeller and BOLT have demonstrated that precise, profile-guided code layout can extract significant performance gains from heavily optimized binaries.
28 May 2026
Pipeline parallelism is essential for large-scale model training, but existing asynchronous approaches often degrade convergence due to parameter mismatch between forward and backward passes.
28 May 2026
Medical knowledge is continuously evolving. This creates a need to update or selectively forget information encoded in already-trained medical LLMs. Machine unlearning aims to remove the influence of specific training data from a model without full retraining.
28 May 2026
Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales.
27 May 2026
Multimodal Sentiment Analysis (MSA) fuses text, acoustic, and visual streams to infer sentiment. Because pre-trained text encoders are far more expressive than their acoustic and visual counterparts, the text modality tends to dominate optimization, suppressing weaker modalities…
27 May 2026
Retrieval-augmented generation (RAG) systems are often compared by asking a large language model (LLM) judge which answer is better. For multi-hop RAG, this has become a measurement problem as much as a modeling problem: the same score can reflect retrieval quality, answer…
27 May 2026
Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic literature or practical applications.
27 May 2026
We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspects of the graph topology were leveraged for prediction.
27 May 2026
How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metrics such as BERTScore compare two texts rather than characterizing one.
27 May 2026
As agent capabilities advance, existing benchmarks, such as $τ^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive.
27 May 2026
We propose a minimal dynamical model of adaptive softmax routing for a two-expert Mixture-of-Experts (MoE) layer. The model is obtained as a mean-field limit of a discrete reinforcement rule: the selected expert receives a small score increment, while all scores undergo…
27 May 2026
Evaluating foundation models under appropriate adaptation settings is essential for understanding the quality and transferability of the learned representations. Recent EEG foundation models have demonstrated promising transfer capabilities across tasks and datasets, motivating…
27 May 2026
We describe a new sense-tagged corpus for word sense disambiguation. The corpus is constituted of instances of 20 French polysemous verbs. Each verb instance is annotated with three sense labels: (1) the actual translation of the verb in the english version of this instance in a…
27 May 2026
Recently, Deep Image Prior (DIP) has demonstrated strong capabilities for solving inverse imaging problems (IIPs) by optimizing a randomly initialized convolutional neural network in a training-data-free regime.
27 May 2026
The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it, and the questions worth asking ("show me where the agent got confused") cannot be answered by SQL alone, since text is…
27 May 2026
We study the log-alignment ratio (LAR), a measure of parameter-activation alignment, introduced in parameterization theory. We reformulate it as the overlap between a weight spectrum $p$ of the normalized squared singular values of a matrix and an activation spectrum $q$ of the…
27 May 2026
Diffusion models have emerged as a dominant framework for generative modeling, but their mathematical foundations are often presented separately through diffusion probabilistic models, score-based modeling, stochastic differential equations, and numerical sampling methods.
27 May 2026
Federated Retrieval-Augmented Generation (FedRAG) is attractive for privacy-sensitive applications because full local corpora remain on clients. As a result, routing must rely on client-provided semantic profiles, creating a new opportunity for manipulation.
27 May 2026
On-policy distillation (OPD) transfers reasoning behavior by training a student on teacher feedback along student-generated trajectories, but standard full-rollout training ties every update to a costly completion and can over-allocate supervision to late positions with low…
27 May 2026
The proliferation of Artificial Intelligence (AI) in workplaces is transforming how we work. While existing research on human-AI collaboration at work often prioritizes performance, less is known about their experiential outcomes.
27 May 2026
AI research agents now support large-scale AI-assisted scientific discovery. We examine whether AI-generated ideas broaden scientific exploration or primarily reinforce existing work.
27 May 2026
AI systems are fallible, and humans can make mistakes in deciding whether to trust AI over their own judgment. Thus, improving human-AI collaboration requires understanding when, why, and how humans decide to rely on AI.
27 May 2026
AI models underpin data-centric applications from image and text processing to scientific discovery in biology, physics, and chemistry. Yet developing them remains heavily manual, requiring practitioners to design architectures, build training pipelines, and iteratively refine…