arXiv:2602.03814v2 Announce Type: replace-cross Abstract: Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases, motivating adaptive reasoning — spending tokens when they improve reliability and stopping early when additional computation is unlikely…
arXiv:2602.11534v3 Announce Type: replace Abstract: Self-attention in Transformers relies on globally normalized softmax weights, causing all tokens to compete for influence at every layer. When composed across depth, this interaction pattern induces strong synchronization dynamics that favor convergence toward a…
arXiv:2605.08506v2 Announce Type: replace Abstract: Robust optimization (RO) provides a principled framework for decision-making under uncertainty, but its performance critically depends on the choice of the uncertainty set. While large sets ensure reliability, they often lead to overly conservative decisions,…
arXiv:2605.13942v1 Announce Type: new Abstract: Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in heterogeneous, long-running, and dynamic…
arXiv:2510.23818v2 Announce Type: replace Abstract: As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight updates to…
arXiv:2605.13936v1 Announce Type: new Abstract: The recent success of large language models (LLMs) has been largely driven by vast public datasets. However, the next frontier for LLM development lies beyond public data. Much of the world’s most valuable information is…
arXiv:2605.13941v1 Announce Type: new Abstract: Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at…
arXiv:2605.13935v1 Announce Type: new Abstract: Diffusion language models are a promising alternative to autoregressive models, yet post-training methods for them largely adapt reward-maximizing objectives. We identify a central failure mode in this setting we call trajectory locking: sampled reward-driven updates…
arXiv:2605.13933v1 Announce Type: new Abstract: Acquisition differences across sites, scanners, and protocols in dMRI introduce variability that complicates structural connectome analysis. This motivates deep learning models that can represent high-dimensional connectomes in a low-dimensional space while explicitly separating acquisition-related effects…
arXiv:2605.13932v1 Announce Type: new Abstract: Robust prediction of molecular properties under extreme out-of-distribution (OOD) scenarios is a pivotal bottleneck in AI-driven drug discovery. Current scaffold-splitting protocols fail to obstruct microscopic semantic overlap, predisposing models to shortcut learning and overestimating their…
