Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2607. 23913v1 Announce Type: new Abstract: Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream language-model inference cost.
arXiv:2607. 23927v1 Announce Type: new Abstract: A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts.
arXiv:2607. 23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.
arXiv:2607. 23219v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theory (DFT) or wave-function methods---at a fraction of the cost.
arXiv:2607. 23123v1 Announce Type: new Abstract: Existing evaluations of large language models cover knowledge, reasoning, coding, and tool use, but they rarely treat a verifiable deliverable produced within a constrained workflow as the unit of evaluation.
arXiv:2607. 22689v1 Announce Type: new Abstract: Graphical user interface (GUI) agents are systems powered by large multimodal models (LMMs).
arXiv:2607. 22663v1 Announce Type: new Abstract: Block diffusion has emerged as the dominant paradigm for scaling discrete diffusion language models (dLLMs), because decoding text in fixed-size blocks preserves parallel generation within each block while keeping the quadratic attention cost tractable.
arXiv:2607. 22573v1 Announce Type: new Abstract: Imaginary phonon modes remain a practical bottleneck in computational materials screening because otherwise plausible structures can be locally dynamically unstable under a chosen workflow.
arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.
arXiv:2607. 22699v1 Announce Type: new Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.
arXiv:2607. 23466v1 Announce Type: new Abstract: Parameterized and coupled partial differential equations (PDEs) are central to modeling phenomena in science and engineering, yet neural operator methods that address both aspects remain limited.
arXiv:2607. 23348v1 Announce Type: cross Abstract: Mixed continuous--categorical data pose a representation problem for continuous generative models.
arXiv:2607. 23869v1 Announce Type: cross Abstract: Randomized features provide a scalable approximation to kernel machines, but their performance depends strongly on the choice of feature distribution.
arXiv:2607. 22749v1 Announce Type: cross Abstract: Tracking residual tumor after surgery is essential for catching recurrence early, but automating post-operative glioma segmentation remains a difficult task.
arXiv:2607. 24056v1 Announce Type: cross Abstract: Network-wide traffic volume estimation typically relies on propagating measurements from fixed sensors, making performance highly dependent on sensor density and limiting deployment in sparsely instrumented networks.
arXiv:2507. 21134v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compliance becomes critical.
arXiv:2510. 16077v2 Announce Type: replace-cross Abstract: Domain Incremental Learning (DIL) is a sub-branch of continual learning that aims to address the never-ending arrival of new domains without catastrophic forgetting.
arXiv:2607. 24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words.
arXiv:2607. 24110v1 Announce Type: cross Abstract: Mobile infrared-visible imaging typically pairs a compact infrared sensor with a high-resolution visible camera for complementary perception.
arXiv:2607. 23310v1 Announce Type: cross Abstract: We study an online variant of discrete fair division under generalized assignment budget constraints.