arXiv:2604.08881v2 Announce Type: replace Abstract: With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods…
arXiv:2607.27566v1 Announce Type: new Abstract: Multi-frame medical VQA appears to reward increasingly complex adaptation: controller-style inference, localization-aware reranking, static hard-negative mixing, and staged continuation all appear…
arXiv:2607.27263v1 Announce Type: new Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where…
arXiv:2511.23310v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective paradigm for post-training large language models, yet the design of…
arXiv:2605.10378v2 Announce Type: replace Abstract: Reliable uncertainty quantification is essential for the use of machine learning in physics, where scientific discoveries depend on validated probabilistic statements.…
arXiv:2607.27066v1 Announce Type: cross Abstract: Scientific figure assessment in peer review differs fundamentally from general image quality evaluation: a figure must be visually legible, faithfully support…
arXiv:2607.26512v1 Announce Type: new Abstract: AI agents can draft claims faster than authors can check whether the cited or retrieved evidence supports them. We study evidence-ledger…
arXiv:2607.27405v1 Announce Type: new Abstract: Both expressions of uncertainty and inferences are ubiquitous in natural language, and valid inferences over natural-language expressions of uncertainty are necessary…
arXiv:2607.12753v2 Announce Type: replace Abstract: Image super-resolution (ISR) has witnessed remarkable progress with diffusion models and flow matching. The dominant text-to-image (T2I) based approaches leverage large-scale…
arXiv:2607.26565v2 Announce Type: replace Abstract: Vision models do not form a representation at once; each block revises it. We ask whether the resulting computation path contains…
arXiv:2505.04999v2 Announce Type: replace-cross Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation. We study a…
arXiv:2607.04044v2 Announce Type: replace-cross Abstract: Recently, Joint Embedding Predictive Architectures (JEPAs) have attracted significant attention in the computer vision and machine learning communities as a promising…
arXiv:2510.22170v3 Announce Type: replace Abstract: Persona conditioning is widely used to steer large language model (LLM) behavior, but it is unclear whether it induces stable behavioral…
arXiv:2504.20903v4 Announce Type: replace-cross Abstract: How should organizations divide and sequence decision tasks between human and artificial agents? We develop a computational model of joint sequential…
arXiv:2607.12790v2 Announce Type: replace-cross Abstract: Self-evolving agent systems create, revise, and retire their own skills, but every such loop assumes a reliable evaluation metric already exists.…
arXiv:2607.27465v1 Announce Type: new Abstract: Semantic segmentation models are vulnerable to transferable adversarial perturbations, yet evaluating transfer attacks on dense prediction models can be computationally expensive.…
arXiv:2607.27585v1 Announce Type: new Abstract: As primary consumers in the marine food chain, zooplankton play a crucial role in maintaining marine ecological balance. However, the Segment…
arXiv:2607.27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting…
arXiv:2607.27280v1 Announce Type: new Abstract: Robust Optimization Over Time (ROOT) is a recent branch of evolutionary dynamic optimization that seeks solutions capable of remaining effective across…
arXiv:2607.26307v1 Announce Type: new Abstract: Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code…
arXiv:2604.07343v2 Announce Type: replace Abstract: Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving…
arXiv:2607.27421v1 Announce Type: new Abstract: Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language…
arXiv:2511.03589v3 Announce Type: replace Abstract: Parametric body models provide the structural basis for many human-centric tasks, yet existing models often rely on costly 3D scans and…
arXiv:2607.23341v2 Announce Type: replace-cross Abstract: Pretrained deep denoisers can be used to solve a wide range of model-based image reconstruction tasks via Plug-and-Play (PnP) and Regularization-by-Denoising…