arXiv:2608.06448v1 Announce Type: new Abstract: Recovering a periodic 3D crystal structure from sparse, unindexed electron diffraction (ED) observations is a challenging generative inverse problem. Existing ED-based…
arXiv:2608.06122v2 Announce Type: replace Abstract: Inspired by recent evidence that transformer architectures benefit from Self-PreTraining (SPT) on long-context benchmarks, we investigate whether similar gains extend to…
arXiv:2608.06545v1 Announce Type: cross Abstract: Distributionally robust Markov decision processes provide a principled framework for sequential decision making under model uncertainty. We study how many samples…
arXiv:2608.06544v1 Announce Type: new Abstract: World models for visual control typically learn compact latent states by reconstructing observations, implicitly encouraging representations to preserve information across the…
arXiv:2608.07411v1 Announce Type: cross Abstract: In the context of geodata, existing Large Language Models have often been studied in a homogeneous setting, which has considerably limited…
arXiv:2607.27853v2 Announce Type: replace Abstract: Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However,…
arXiv:2605.31589v2 Announce Type: replace Abstract: While humans naturally gesture during speech, only a sparse subset of these co-speech gestures are visually depictive and semantically linked to…
arXiv:2608.07463v1 Announce Type: cross Abstract: Recent advances in video diffusion models (VDMs) have enabled high-fidelity video synthesis. However, generating mirror reflections remains challenging because the content…
arXiv:2608.06520v1 Announce Type: new Abstract: We study online cooperative control of a multi-agent system under Byzantine attacks. Namely, an unknown, fixed subset of agents are Byzantine…
arXiv:2601.19597v6 Announce Type: cross Abstract: While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a measure-theoretic framework…
arXiv:2608.06994v1 Announce Type: cross Abstract: World Action Models (WAMs) aim to construct a unified architecture capable of understanding world state evolution and guiding to generative motion…
arXiv:2608.06495v1 Announce Type: new Abstract: Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually…
arXiv:2608.06607v1 Announce Type: new Abstract: Most document-extraction systems use a single model for all documents. This is simple but can be costly for easy cases and…
arXiv:2608.06673v1 Announce Type: new Abstract: Language descriptions in source-free cross-domain few-shot learning (SF-CDFSL) are often selected according to zero-shot accuracy obtained with a frozen vision--language model.…
arXiv:2608.06430v1 Announce Type: new Abstract: Learning from Electronic Health Records (EHRs) has gained significant attention due to its potential to improve clinical prediction. However, effective learning…
arXiv:2602.15957v2 Announce Type: replace-cross Abstract: Complex change is often described as ``evolutionary'' in economics, policy, technology, and organizations, yet many system dynamics models represent behavior within…
arXiv:2501.15790v2 Announce Type: replace-cross Abstract: Synthetic minority oversampling is typically designed and evaluated against a predictive objective, generating samples that improve downstream classification. This paper pursues…
arXiv:2608.00065v3 Announce Type: replace Abstract: Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie…
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behaviors under explicit…
arXiv:2608.06506v1 Announce Type: new Abstract: Language models are often evaluated as though capabilities demonstrated in English remain equally available when the same content is presented in…
arXiv:2604.11240v2 Announce Type: replace Abstract: Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding…
arXiv:2607.23238v2 Announce Type: replace Abstract: Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the reconstruction target remains fundamentally unsettled.…
arXiv:2608.06441v1 Announce Type: new Abstract: Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges. We present…
arXiv:2608.07243v1 Announce Type: cross Abstract: Generative models are often evaluated through singular artifacts, whereas human creativity typically emerges through iterative generation, appraisal, and refinement. This pilot…