arXiv:2512.10966v2 Announce Type: replace Abstract: Accurate and early diagnosis of Alzheimer’s disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data. However, conventional fusion approaches often rely on simple concatenation of features, which cannot…
arXiv:2604.09952v1 Announce Type: new Abstract: Many applications today use large language models for code generation; however, production systems have strict latency requirements that can be difficult to meet with large models. Small language models with a few billion parameters are…
arXiv:2602.10420v2 Announce Type: replace Abstract: Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this paradigm to binary manifolds,…
arXiv:2604.09964v1 Announce Type: new Abstract: We present a family of Kaczmarz-based preference learning algorithms for real-time personalized matchmaking in reciprocal recommender systems. Post-step L2 normalization, common in Kaczmarz-inspired online learners, induces exponential recency bias: the influence of the t-th interaction…
arXiv:2603.09145v2 Announce Type: replace Abstract: Current expansion-based methods for Class Incremental Learning (CIL) effectively mitigate catastrophic forgetting by freezing old features. However, such task-specific features learned from the new task may collide with the old features. From a causal perspective,…
A chemical-free approach to balancing ocean acidity protects marine life and could dramatically impact the global aquaculture market.
arXiv:2509.13047v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across many domains, yet their application to specialized fields remains constrained by the scarcity and complexity of domain-specific training data. We present a novel approach that achieves…
arXiv:2601.07224v2 Announce Type: replace-cross Abstract: While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation between these stages remain largely underexplored. Current data arbitration strategies often…
arXiv:2602.17375v2 Announce Type: replace Abstract: We cast episodic Markov decision process (MDP) planning as Bayesian inference over policies. A policy is treated as the latent variable and is assigned an unnormalized probability of optimality that is monotone in its expected…
arXiv:2405.03063v2 Announce Type: replace-cross Abstract: We propose a generalized debiased Lasso estimator based on a stability principle. When a single column of the design matrix is perturbed, the estimator admits a simple update formula that can be computed from the…
