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.
27 May 2026
Tool-using language agents turn model decisions into external side effects: they read files, run scripts, call APIs, send messages, and invoke Model Context Protocol tools. This makes agent attacks different from jailbreaks.
27 May 2026
Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions.
27 May 2026
Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., ``a photo of a [CLASS]''.
27 May 2026
Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task family, masking two failure modes: performance can collapse as length grows, and strong retrieval need not transfer to…
26 May 2026
Inference from interaction maps, such as centromere identification from genome-wide chromosome conformation capture techniques -- notably Hi-C -- can be formulated as a generic inverse problem: infer a set of parameters given a map summarizing pairwise interactions between…
26 May 2026
ASP(Q) extends Answer Set Programming (ASP) with Quantifiers over answer sets. In this paper we focus on the class of ASP(Q) programs with two quantifiers and weak constraints, denoted as 2-ASP(Q)^w.
26 May 2026
Large Language Models (LLMs) have brought huge improvements to Artificial Intelligence (AI), which can be applied to general-purpose tasks. However, their application to textual or spoken medical consultations is still an open research problem.
26 May 2026
Automated industrial inspection requires both precise defect localization and structured maintenance report generation; in current practice these tasks are handled separately, with linguistic interpretation left to human experts.
26 May 2026
Brain-computer interfaces (BCIs) are limited by low signal-to-noise ratio in modalities such as electroencephalography, which requires multiple trials to reliably decode user intentions. This induces a speed-accuracy trade-off, whereby higher accuracy comes at the cost of speed.
26 May 2026
Estimating CPU power on heterogeneous ARM-based commodity devices is challenging due to limited access to CPU's voltage domains. As a result, state-of-the-art energy-aware Federated Learning (FL) frameworks typically rely on simplified approximate power models to estimate…
26 May 2026
Safety evaluations of language models often treat serving configuration as fixed background infrastructure, but batch condition is an untested treatment variable whenever the same prompt may be evaluated alone, in a synchronized batch, or inside a continuous-batching scheduler.
26 May 2026
Multi-agent LLM systems have become the dominant production workload, but the serving stack was not built for them. The agent framework above knows agent identities, role, schemas, and dispatch structure but never sees an engine-level event; the serving engine below sees every…
26 May 2026
We study transformers' generalization behavior on boolean domains from the perspective of the Fourier spectra of their target functions. In contrast to prior work (Edelman et al., 2022; Trauger & Tosh, 2024), which derived generalization bounds from Rademacher complexity, we…
26 May 2026
Scientific data annotation, such as tracking animals in video or proofreading neural reconstructions, remains bottlenecked by the "last mile" problem: even with strong automation, verification and correction consume substantial human effort.
26 May 2026
The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x…
26 May 2026
This paper examines how estimates of AI use in scientific writing can be biased when evaluation methods ignore contextual differences across countries and fields. Using large-scale data on journal publications from Dimensions, we construct AI-likeness benchmarks based on…
26 May 2026
Rubric-based reward shaping provides interpretable and editable reward signals for fine-tuning LLMs via reinforcement learning (RL), but existing adaptive rubric methods typically update criteria from local evidence such as the current batch or instance-level comparisons.
26 May 2026
Learning-based surrogates have become increasingly effective for wave-field prediction, and neural operators in particular have shown strong performance within observed frequency regimes.
25 May 2026
The widespread deployment of generative artificial intelligence (AI) models has raised serious concerns about the proliferation of AI-generated content. This has led to a surge of interest in, and demand for, reliable tracking and detection mechanisms for content that is…
25 May 2026
Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically in the form of partial differential equations (PDE), into data-driven models. Despite strong empirical performance, its statistical generalisation properties remain poorly understood,…
25 May 2026
The convergence of large language models (LLMs) with 6G networks is fostering a paradigm of autonomous multi-agent cooperation, which in turn is expected to substantially increase east-west traffic.
25 May 2026
Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated report. We ask what this does to a class of defect no single worker can see: a contradiction in the relation between two distant…
25 May 2026
While the primary function of computers lies in computation and processing, the core value of the Internet is rooted in sharing and collaboration. Computers create the Internet, and the Internet empowers the value of computers.
25 May 2026
When language models use test-time sampling, they generate multiple reasoning trajectories and select an answer by majority vote. We show that these trajectories are not independent: for a given question, they concentrate into a small number of clusters, or reasoning basins,…