🏢 Northwestern University

Boosting toxicity classification robustness, this paper introduces a novel bi-level optimization framework integrating crowdsourced soft-labels and GroupDRO to enhance resistance against out-of-distri…

Universal Unsupervised Cross-Domain Retrieval (U2CDR) framework learns semantic features to enable accurate retrieval even when category spaces differ across domains.

Researchers achieve provably optimal memory capacity in transformer-compatible Hopfield models by framing the problem as an optimal spherical code arrangement, resulting in a novel sublinear time algo…

RLHF’s overoptimization problem is mitigated by RPO, a novel algorithm that uses SFT loss as an implicit adversarial regularizer, ensuring efficient and effective LLM alignment.

Latent Diffusion Transformers (DiTs) achieve almost-linear time training and inference through low-rank gradient approximations and efficient criteria, overcoming high dimensionality challenges.

Anchored Confidence (AnCon) significantly improves self-training under distribution shifts by using a temporal ensemble to smooth noisy pseudo-labels, achieving 8-16% performance gains without computa…

Unlocking latent community structures from multiple correlated networks is now possible with greater precision, as this research pinpoints the information-theoretic threshold for exact recovery, even …

Discover optimal embedding dimensions for contrastive learning & k-NN using graph arboricity; achieve efficient model design & performance.

Efficient algorithm achieves near-perfect graph matching in correlated stochastic block models, resolving a key open problem and enabling improved community detection.