arXiv:2405.12410v2 Announce Type: replace-cross Abstract: Sometimes local search algorithms cannot efficiently find even local peaks. To understand why, I look at the structure of ascents in…
arXiv:2607.20309v1 Announce Type: new Abstract: Covariate shift often occurs because, in many real applications, the source and the target observations may be generated from different distributions.…
arXiv:2607.20255v1 Announce Type: cross Abstract: LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling -- deterministic, narrowly scoped, and operated by trained practitioners --…
arXiv:2607.19363v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform frequency schedule…
arXiv:2607.19573v1 Announce Type: new Abstract: Structural generalization has been measured repeatedly by several benchmarks, yet it has never been formally defined. We give a definition that…
arXiv:2602.00462v5 Announce Type: replace Abstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a…
arXiv:2607.19793v1 Announce Type: cross Abstract: Multimodal agentic search systems increasingly rely on external tools to answer knowledge-intensive visual questions. However, existing evaluations mainly focus on final-answer…
arXiv:2607.19385v1 Announce Type: new Abstract: This paper tackles the problem of stock ranking and portfolio construction under realistic investment settings by jointly modeling temporal dynamics and…
arXiv:2602.06595v5 Announce Type: replace Abstract: This paper presents a principled framework for designing energy-aware metaheuristics that operate under fixed energy budgets. We introduce a unified operator-level…
arXiv:2605.21107v3 Announce Type: replace-cross Abstract: We study constrained online convex optimization with adversarial time-varying constraints. At each round the learner acts before observing the loss and…
arXiv:2510.05592v2 Announce Type: replace Abstract: Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that…
arXiv:2503.22998v3 Announce Type: replace-cross Abstract: Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness. Certified robustness via randomized smoothing offers provable…
arXiv:2607.20058v1 Announce Type: cross Abstract: Large language models can answer scientific questions, yet a correct output does not reveal whether the model represents or uses the…
arXiv:2607.19600v1 Announce Type: cross Abstract: The shape of a planar curve is the geometric information that remains once translation, rotation, scale and reparametrisation are removed and…
arXiv:2607.19701v1 Announce Type: new Abstract: VLMs are increasingly deployed in AD systems, creating an urgent need for rigorous safety evaluation under rare yet safety-critical scenarios. Among…
arXiv:2607.19382v1 Announce Type: new Abstract: Deep learning models have shown strong potential for time series forecasting, yet their deployment in real-world environmental monitoring remains challenging due…
arXiv:2607.19973v1 Announce Type: cross Abstract: AI researchers describe state-of-the-art models as one thing repeated at scale: the Transformer, wired identically for text, pixels, or speech. Neuroscientists…
arXiv:2607.19378v1 Announce Type: cross Abstract: Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input dependency, while…
arXiv:2607.19357v1 Announce Type: new Abstract: Recent advances in recommender systems (RS) have shown substantial performance gains through generative modelling. In practice, recommendation often involves constructing slates…
arXiv:2607.19364v1 Announce Type: new Abstract: Activation steering offers a lightweight alternative to fine-tuning for behavioral control of large language models, but SAE-based steering methods often rely…
arXiv:2607.19691v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling…
arXiv:2607.19971v1 Announce Type: cross Abstract: Accurate motion prediction of surrounding agents and safe motion planning are two closely coupled key tasks for social robot navigation in…
arXiv:2506.04122v4 Announce Type: replace Abstract: Open-loop performance evaluation of 3D multi-object tracking in autonomous driving requires matching criteria that effectively penalize translational, shape, and orientation errors…
arXiv:2607.19381v1 Announce Type: new Abstract: Air pollution causes an estimated 7.9 million premature deaths annually, making accurate forecasting a critical public health priority. Machine learning is…