Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods.
Verification of neural networks against relational specifications, such as global robustness, is crucial for safety-critical applications of cyber-physical systems (CPS), given their increasing adoption of AI components. Compared to simple trace properties (e.
Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically evaluating the cognitive plasticity of open-weight architectures when subjected to rigorous behavioral reprogramming.
Driven by the availability of large-scale datasets, Human Pose Estimation (HPE) plays a critical role in numerous downstream tasks. However, mainstream benchmarks exhibit severe representation bias, predominantly featuring able-bodied individuals.
The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an now-unfamiliar language (e. g.
Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a proposal-alignment question: should the contrastive signal shape the drafter, or should it remain only in verification?
Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks. While optimizing activation designs offers a potential solution, current fixed-form functions suffer from an inherent spectral bias towards low-frequency variations, whereas learnable variants permit unconstrained updates that induce catastrophic forgetting.
Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface curvature: the trace of the Hessian of the log-likelihood. Recent work regularizes this trace globally to bias learning toward flatter, better generalizing optima.
arXiv:2608. 12083v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) achieve strong predictive performance on graph-structured data across domains such as chemistry, biology, and network analysis, yet they provide no intrinsic explanation of their predictions.
arXiv:2608. 12231v1 Announce Type: new Abstract: We study adversarial combinatorial bandits with $m$-set actions, where at each round the learner selects $m$ out of $d$ items and observes only the aggregate loss of the selected items.
arXiv:2608. 11860v1 Announce Type: cross Abstract: Data-driven inverse design enables efficient generation of nanophotonic structures with prescribed optical responses, but spectrum-to-geometry mapping remains challenging due to non-uniqueness and fine geometric features.
arXiv:2608. 11980v1 Announce Type: cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively generating this token sequence.
arXiv:2608. 11691v1 Announce Type: new Abstract: Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning.
arXiv:2608. 11250v1 Announce Type: new Abstract: Language models can propose many plausible trading factors, but an autonomous research system must also allocate its evaluation budget, verify its own evidence, and preserve how each candidate was produced.
arXiv:2608. 11590v1 Announce Type: cross Abstract: Human voice generation has made rapid progress in speech generation, singing voice generation, voice cloning, and voice editing.
arXiv:2608. 11283v1 Announce Type: cross Abstract: Computation-ready metal-organic framework (MOF) databases are essential for high-throughput screening, yet many reported crystal structures remain chemically unreasonable or disordered, compromising simulation fidelity.
arXiv:2608. 11604v1 Announce Type: new Abstract: Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction logs that provide valuable supervision for improving these agents.
arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.
arXiv:2608. 11656v1 Announce Type: new Abstract: Recent advances in EEG foundation models have demonstrated the potential of large-scale pretraining to enable generalizable neural decoding across subjects, recording environments, and datasets.
arXiv:2412. 18081v3 Announce Type: replace-cross Abstract: We study Heterogeneous Transfer Learning (HTL) for high-dimensional regression with differing feature sets.