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 22,213 papers.
Jason D. Lee, Yuanhe Zhang, Fanghui Liu · 2 Feb 2026
We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz…
1 Feb 2026
Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing.
1 Feb 2026
We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilingual large language models (LLMs).
1 Feb 2026
LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
1 Feb 2026
LLM agent benchmark scores are shaped not only by the model but also by the agent harness, environment, evaluator, and inference budget. Unified execution controls these non-model factors by evaluating candidate models under the same configuration, making observed differences…
1 Feb 2026
Modern deployments require LLMs to enforce safety policies at scale, yet many controls rely on inference-time interventions that add recurring compute cost and serving complexity.
1 Feb 2026
Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model upscaling: initializing larger models from trained smaller ones to accelerate convergence.
1 Feb 2026
Design-to-code translates high-fidelity UI designs into executable front-end implementations, but progress remains hard to compare due to inconsistent datasets, toolchains, and evaluation protocols.
1 Feb 2026
Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary. Yet, we still lack a clear understanding of how decision makers learn from ML-based decision support (ML-DS).
Mario Giulianelli, Gabriele Sarti, Raghu Arghal · 1 Feb 2026
Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with…
1 Feb 2026
Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image analysis. Here, we present LitePath, a deployment-friendly framework that addresses model over-parameterization and patch-level redundancy.
1 Feb 2026
High-fidelity simulations of laser welding capture complex thermo-fluid phenomena, including phase change, free-surface deformation, and keyhole dynamics, however their computational cost limits large-scale process exploration and real-time use.
1 Feb 2026
We establish a general equilibrium theory for systems of large language model (LLM) agents operating under centralized orchestration. The framework is a production economy in the sense of Arrow-Debreu (1954), extended to infinite-dimensional commodity spaces following Bewley…
1 Feb 2026
This paper studies optimization for a family of problems termed $\textbf{compositional entropic risk minimization}$, in which each data's loss is formulated as a Log-Expectation-Exponential (Log-E-Exp) function.
1 Feb 2026
This paper addresses the issue of inversion in cases where (1) the observation system is modeled by a linear transformation and additive error, (2) the problem is ill-posed and regularization relies on a Bayesian strategy, (3)~the prior is modeled by a diffusion process adjusted…
1 Feb 2026
Generalization and approximation capabilities of message passing graph neural networks (MPNNs) are often studied by defining a compact metric on a space of input graphs under which MPNNs are equicontinuous.
1 Feb 2026
Poisson-distributed latent variable models are widely used in computational neuroscience, but differentiating through discrete stochastic samples remains challenging. Two approaches address this: *Exponential Arrival Time* (EAT) simulation and *Gumbel-SoftMax* (GSM) relaxation.
1 Feb 2026
We consider the problem of heteroskedastic generalized linear bandits (GLBs) with adversarial corruptions, which subsumes heteroskedastic linear bandits and logistic/Poisson bandits, in the presence of adversarial corruptions.
1 Feb 2026
Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a learned velocity field, and each sample corresponds to a trajectory with its own dynamical effort.
1 Feb 2026
Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) offers a resource-efficient way to personalize or specialize. However, LoRA is highly sensitive to hyperparameter choices, and exhaustive hyperparameter search is computationally expensive.
1 Feb 2026
Molecular function is largely determined by structure. Accurately aligning molecular structure with natural language is therefore essential for enabling large language models (LLMs) to reason about downstream chemical tasks.
1 Feb 2026
Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different visual modalities.
1 Feb 2026
In general reinforcement learning, all established optimal agents, including AIXI, are model-based, explicitly maintaining and using environment models. This paper introduces Universal AI with Q-Induction (AIQI), the first model-free agent proven to be asymptotically…
1 Feb 2026
Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporary structures) invisible to traditional geometric sensors.