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 22,736 papers.
26 Aug 2026
Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent synthetic data generation pipeline that converts longitudinal structured EHR into source-grounded clinical note representations…
26 Aug 2026
Accurate online traffic prediction is essential for intelligent transportation systems, where forecasting must be performed continuously under imperfect sensing conditions.
26 Aug 2026
Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as role-playing, obfuscation, code transformation, and multi-step indirection to elicit harmful outputs.
26 Aug 2026
Physical AI models are evaluated on suites of benchmarks that differ across model reports, leaving the model-by-benchmark matrix sparse and the relationship between benchmarks unmeasured.
26 Aug 2026
Graph retrieval-augmented generation places retrieved subgraphs into the model's context window at query time, paying a recurring token cost and exposing source data on every call.
26 Aug 2026
To apply the techniques of embodied artificial intelligence to human-oid robots for complex manipulations, dexterous robotic hands are indispensable, which are restricted by the dexterity and tactile perception capability.
26 Aug 2026
On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals from a frozen teacher, yet how a sampled loss allocates updates across tokens remains poorly understood.
26 Aug 2026
Partial deepfake speech, where only limited segments of an utterance are synthesized or manipulated, poses a significant challenge to existing deepfake detection systems.
26 Aug 2026
In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data.
25 Aug 2026
Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings.
25 Aug 2026
Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantees due to significant relaxation gaps.
25 Aug 2026
Credit risk models increasingly need to combine predictive accuracy with transparent explanations and auditable fairness constraints. Logistic regression remains attractive because its coefficients are easy to interpret, but it can miss nonlinear structure.
25 Aug 2026
Electric vehicle (EV) charging loads exhibit strong behavioral heterogeneity and temporal variability, posing significant challenges for online probabilistic forecasting under evolving operating conditions.
25 Aug 2026
Real conversations between fraudsters and their targets are among the most informative artifacts for studying telephone scams, yet also the scarcest: passive honeypots overwhelmingly capture automated messages and hang-ups, large-scale studies characterize call metadata rather…
25 Aug 2026
Training neural networks requires balancing the trade-off between fitting the training data and achieving robust performance on unseen inputs. This ability, commonly referred to as generalizability, is determined by the gap between the empirical risk on the training set…
25 Aug 2026
The rapid expansion of large-scale assessments and the growing adoption of automatic item generation have intensified concerns about incidental content redundancy, where construct-irrelevant elements such as wording or contextual framing become unintentionally repetitive across…
25 Aug 2026
Building a self-organising map at MEDLINE scale has been impractical: the best-matching-unit (BMU) search that dominates training is bound by the bandwidth needed to read the codebook every epoch. I show that this bottleneck is largely an artefact of codebook layout.
25 Aug 2026
Neighborhood-based fairness audits evaluate individual fairness by comparing predictions among similar individuals in feature space. Despite their widespread use, little is known about the robustness of the auditing procedure itself.
25 Aug 2026
Mixture-of-Experts (MoE) models provide a flexible framework for partitioning complex prediction problems into simpler local learning tasks through an input-dependent gating mechanism.
25 Aug 2026
LLM-as-a-judge evaluation is usually assessed by agreement and robustness to surface perturbations, but reliability does not establish construct validity. We formalize construct validity for an evaluator as a two-dimensional profile: invariance S, the probability that a verdict…
25 Aug 2026
This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a grammar for executable program essays, a parser that treats names as first-class objects, an internal name-graph which relates…
25 Aug 2026
Phase-field modeling of brittle fracture removes the need to track cracks explicitly by recasting their evolution as the minimization of an energy functional. In return it requires a discretization dense enough to resolve a localization band whose width is set by a…
25 Aug 2026
Precision oncology necessitates a longitudinal model of patient state that captures cancer evolution and treatment over time, integrating multimodal observations. We introduce the oFM, a foundation model developed on a real-world oncology cohort of 1.67 million cancer patients…
25 Aug 2026
As people adopt transformer-based language models (e.g., ChatGPT and Gemini) for an increasing number of use-cases, it is important to know how such models learn and represent the meaning of the language, and to be more informed about what language is.