Current models of representational reliability in neural populations focus on temporal stability: whether population centroids are preserved across sessions and days. This framing leaves a fundamental…
arXiv:2606.28514v1 Announce Type: new Abstract: Multimodal models are increasingly deployed to solve tasks collaboratively with humans or other artificial agents. Existing benchmarks show that these models…
arXiv:2606.29459v1 Announce Type: cross Abstract: Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine-learning models…
arXiv:2407.02351v3 Announce Type: replace Abstract: The rapid spread of false and misleading information on online platforms poses a growing societal challenge, overwhelming the capacity of manual…
arXiv:2606.28386v1 Announce Type: new Abstract: Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the…
arXiv:2603.02043v2 Announce Type: replace Abstract: We revisit transductive learning where predictions are made with the set of all covariates known in advance. In the leave-one-out (LOO)…
arXiv:2606.28525v1 Announce Type: new Abstract: Fine-tuning on harmless data can partially undo behaviors acquired earlier in training. Safety can erode under benign post-alignment updates, unlearned capabilities…
arXiv:2606.29354v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly…
arXiv:2406.13944v2 Announce Type: replace-cross Abstract: This paper establishes the generalization error of pooled min-$ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available. Min-norm…
arXiv:2606.30328v1 Announce Type: new Abstract: Rapid prototyping of algorithms is a critical step in modern machine learning. Most algorithms exploit linear algebra, creating a need for…
arXiv:2506.13932v3 Announce Type: replace-cross Abstract: The rise of large language models (LLMs) has led to dramatic improvements across a wide range of natural language tasks. Their…
arXiv:2606.30201v1 Announce Type: cross Abstract: Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or…
arXiv:2606.28725v1 Announce Type: new Abstract: Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, and strategic adaptation…
arXiv:2606.28383v1 Announce Type: new Abstract: Identifying complex and safety-critical driving scenarios in large unlabelled datasets is an important but expensive problem. Existing approaches rely on human…
arXiv:2606.30310v1 Announce Type: cross Abstract: The Sliced Wasserstein (SW) distance has emerged as a computationally attractive alternative to the Wasserstein distance by leveraging one-dimensional optimal transport…
arXiv:2506.18295v2 Announce Type: replace Abstract: Neural ray tracing (RT) has emerged as a promising paradigm for channel modeling by integrating physical propagation principles with neural networks.…
arXiv:2606.29528v1 Announce Type: new Abstract: Modern machine learning applications employ deep neural networks training with the error backpropagation algorithm. Although this algorithm is very effective, it…
arXiv:2606.29326v1 Announce Type: new Abstract: Gradient boosting in the form of decision tree ensembles has successfully been applied to a variety of problems using simple objective…
arXiv:2606.09820v2 Announce Type: replace-cross Abstract: We generalize the universal approximation theorem for functional input neural networks (FNN) to differentiable maps by including the approximation of the…
arXiv:2606.28710v1 Announce Type: new Abstract: We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market,…
arXiv:2606.28562v1 Announce Type: new Abstract: On-policy distillation (OPD) has a property absent in offline distillation and RL: teacher supervision quality depends on student competence. Incoherent rollouts…
arXiv:2511.05852v4 Announce Type: replace Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation…
arXiv:2606.30599v1 Announce Type: new Abstract: Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios.…
arXiv:2405.16472v2 Announce Type: replace Abstract: Contemporary AI faces the challenge of balancing generality with user-specific personalization. In federated learning (FL), this challenge is amplified by highly…