Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2607. 06723v1 Announce Type: cross Abstract: Most gradient-based optimization methods move parameters through a fixed background geometry, even when their internal states implicitly define changing notions of length, curvature, and preconditioning.
arXiv:2607. 07275v1 Announce Type: new Abstract: Bubbly flows exhibit complex multiscale dynamics, with deformable bubbles interacting through the surrounding liquid and giving rise to strongly coupled kinematic and morphological behavior.
arXiv:2607. 07519v1 Announce Type: new Abstract: We address the problem of efficiently sampling multimodal probability distributions, where standard Markov Chain Monte Carlo methods often suffer from poor mixing and mode trapping.
arXiv:2607. 07357v1 Announce Type: cross Abstract: Effective social robot navigation requires sensitivity to human behavior, often revealed through subtle skeletal cues like gait and orientation.
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.
arXiv:2607. 06121v1 Announce Type: cross Abstract: In this paper, we investigate whether a model-free RL agent can identify and exploit price manipulation opportunities more effectively than a traditional model-based approach that assumes correct specification of the data-generating process but relies on noisy parameter estimates.
arXiv:2607. 06595v1 Announce Type: cross Abstract: Personal AI agents powered by large language models can reason and act using available tools to access emails, manage calendars, and push code to remote repositories, all with minimal oversight.
arXiv:2607. 06612v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy.
arXiv:2607. 06617v1 Announce Type: cross Abstract: Wearable motion sensing provides a continuous and scalable window into human behavior and health, making it a natural fit for foundation models, yet its pretraining and scaling principles remain poorly understood.
arXiv:2607. 06641v1 Announce Type: cross Abstract: Large language models (LLMs) achieve promising results on medical question answering benchmarks, yet their use in public health is constrained by hallucinations and the rapid evolution of official guidance.
arXiv:2607. 06887v1 Announce Type: new Abstract: Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional.
arXiv:2607. 06979v1 Announce Type: new Abstract: Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the complexity of coordinating massive client populations.
arXiv:2607. 06839v1 Announce Type: new Abstract: Existing NAS benchmarks (e.
arXiv:2607. 06624v1 Announce Type: new Abstract: We present AgentLens, a production-assessed benchmark for interactive code agents.
arXiv:2607. 07097v1 Announce Type: new Abstract: Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect.
Multi-query vehicle ReID aims to leverage complementary information from diverse views for robust feature learning. However, current methods suffer from simplistic feature fusion and thus easily ignores some important view information and cross-view relationships.
Unsupervised constituency parsing aims to accurately induce latent tree structures from raw text alone. Recent neural parameterizations of PCFGs achieve strong performance in both supervised and unsupervised parsing, yet rely on high-capacity black-box networks for rule scoring -- as exemplified by the Neural PCFG family -- leaving rule probabilities without an interpretable mathematical form.
Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks. Recent research demonstrates that adaptive token generation ordering can significantly improve performance in mathematical reasoning and code synthesis applications.
Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast. We ask whether internal representations offer a more direct window into both.
While neural PDE solvers have demonstrated significant potential for accelerating engineering simulations, existing architectures remain constrained by high memory consumption and the single node bottleneck, where the maximum processable mesh resolution is strictly limited by the VRAM of a single compute unit. To address these challenges, we propose PGD-NO, a neural operator with Precomputed Geometry Decomposition, that relocates the computational overhead of geometric encoding to a deterministic pre-computation phase.